Publications from 2001

Abstract

We suggest representing light field (LF) videos as "one-off" neural networks (NN), i.e., a learned mapping from view-plus-time coordinates to high-resolution color values, trained on sparse views. Initially, this sounds like a bad idea for three main reasons: First, a NN LF will likely have less quality than a same-sized pixel basis representation. Second, only few training data, e.g., 9 exemplars per frame are available for sparse LF videos. Third, there is no generalization across LFs, but across view and time instead. Consequently, a network needs to be trained for each LF video. Surprisingly, these problems can turn into substantial advantages: Other than the linear pixel basis, a NN has to come up with a compact, non-linear i.e., more intelligent, explanation of color, conditioned on the sparse view and time coordinates. As observed for many NN however, this representation now is interpolatable: if the image output for sparse view coordinates is plausible, it is for all intermediate, continuous coordinates as well. Our specific network architecture involves a differentiable occlusion-aware warping step, which leads to a compact set of trainable parameters and consequently fast learning and fast execution.

Links

[arXiv]

Export

BibTeX

@online{Bemana_arXiv1910.13921, TITLE = {Neural View-Interpolation for Sparse Light Field Video}, AUTHOR = {Bemana, Mojtaba and Myszkowski, Karol and Seidel, Hans-Peter and Ritschel, Tobias}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1910.13921}, EPRINT = {1910.13921}, EPRINTTYPE = {arXiv}, YEAR = {2019}, ABSTRACT = {We suggest representing light field (LF) videos as "one-off" neural networks (NN), i.e., a learned mapping from view-plus-time coordinates to high-resolution color values, trained on sparse views. Initially, this sounds like a bad idea for three main reasons: First, a NN LF will likely have less quality than a same-sized pixel basis representation. Second, only few training data, e.g., 9 exemplars per frame are available for sparse LF videos. Third, there is no generalization across LFs, but across view and time instead. Consequently, a network needs to be trained for each LF video. Surprisingly, these problems can turn into substantial advantages: Other than the linear pixel basis, a NN has to come up with a compact, non-linear i.e., more intelligent, explanation of color, conditioned on the sparse view and time coordinates. As observed for many NN however, this representation now is interpolatable: if the image output for sparse view coordinates is plausible, it is for all intermediate, continuous coordinates as well. Our specific network architecture involves a differentiable occlusion-aware warping step, which leads to a compact set of trainable parameters and consequently fast learning and fast execution. }, }

Endnote

%0 Report %A Bemana, Mojtaba %A Myszkowski, Karol %A Seidel, Hans-Peter %A Ritschel, Tobias %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Neural View-Interpolation for Sparse Light Field Video : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7B16-9 %U http://arxiv.org/abs/1910.13921 %D 2019 %X We suggest representing light field (LF) videos as "one-off" neural networks (NN), i.e., a learned mapping from view-plus-time coordinates to high-resolution color values, trained on sparse views. Initially, this sounds like a bad idea for three main reasons: First, a NN LF will likely have less quality than a same-sized pixel basis representation. Second, only few training data, e.g., 9 exemplars per frame are available for sparse LF videos. Third, there is no generalization across LFs, but across view and time instead. Consequently, a network needs to be trained for each LF video. Surprisingly, these problems can turn into substantial advantages: Other than the linear pixel basis, a NN has to come up with a compact, non-linear i.e., more intelligent, explanation of color, conditioned on the sparse view and time coordinates. As observed for many NN however, this representation now is interpolatable: if the image output for sparse view coordinates is plausible, it is for all intermediate, continuous coordinates as well. Our specific network architecture involves a differentiable occlusion-aware warping step, which leads to a compact set of trainable parameters and consequently fast learning and fast execution. %K Computer Science, Graphics, cs.GR,Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Learning, cs.LG,eess.IV

Bemana, M., Keinert, J., Myszkowski, K., et al. 2019b. Learning to Predict Image-based Rendering Artifacts with Respect to a Hidden Reference Image. Computer Graphics Forum (Proc. Pacific Graphics 2019)38, 7.

Links

Export

BibTeX

@article{Bemana_PG2019, TITLE = {Learning to Predict Image-based Rendering Artifacts with Respect to a Hidden Reference Image}, AUTHOR = {Bemana, Mojtaba and Keinert, Joachim and Myszkowski, Karol and B{\"a}tz, Michel and Ziegler, Matthias and Seidel, Hans-Peter and Ritschel, Tobias}, LANGUAGE = {eng}, ISSN = {1467-8659}, DOI = {10.1111/cgf.13862}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford, UK}, YEAR = {2019}, DATE = {2019}, JOURNAL = {Computer Graphics Forum (Proc. Pacific Graphics)}, VOLUME = {38}, NUMBER = {7}, PAGES = {579--589}, BOOKTITLE = {27th Annual International Conference on Computer Graphics and Applications (Pacific Graphics 2019)}, }

Endnote

%0 Journal Article %A Bemana, Mojtaba %A Keinert, Joachim %A Myszkowski, Karol %A Bätz, Michel %A Ziegler, Matthias %A Seidel, Hans-Peter %A Ritschel, Tobias %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Learning to Predict Image-based Rendering Artifacts with Respect to a Hidden Reference Image : %G eng %U http://hdl.handle.net/21.11116/0000-0004-9BC5-F %R 10.1111/cgf.13862 %7 2019 %D 2019 %J Computer Graphics Forum %V 38 %N 7 %& 579 %P 579 - 589 %I Wiley-Blackwell %C Oxford, UK %@ false %B 27th Annual International Conference on Computer Graphics and Applications %O Pacific Graphics 2019 PG 2019 Seoul, October 14-17, 2019

2018

Zayer, R., Mlakar, D., Steinberger, M., and Seidel, H.-P. 2018a. Layered Fields for Natural Tessellations on Surfaces. ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia 2018)37, 6.

Links

Export

BibTeX

@article{Zayer:2018:LFN, TITLE = {Layered Fields for Natural Tessellations on Surfaces}, AUTHOR = {Zayer, Rhaleb and Mlakar, Daniel and Steinberger, Markus and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0730-0301}, ISBN = {978-1-4503-6008-1}, DOI = {10.1145/3272127.3275072}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2018}, DATE = {2018}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia)}, VOLUME = {37}, NUMBER = {6}, EID = {264}, BOOKTITLE = {Proceedings of ACM SIGGRAPH Asia 2018}, }

Endnote

%0 Journal Article %A Zayer, Rhaleb %A Mlakar, Daniel %A Steinberger, Markus %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Layered Fields for Natural Tessellations on Surfaces : %G eng %U http://hdl.handle.net/21.11116/0000-0002-E5E0-E %R 10.1145/3272127.3275072 %7 2018 %D 2018 %J ACM Transactions on Graphics %V 37 %N 6 %Z sequence number: 264 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH Asia 2018 %O ACM SIGGRAPH Asia 2018 Tokyo, Japan, December 04 - 07, 2018 SA'18 SA 2018 %@ 978-1-4503-6008-1

Zayer, R., Mlakar, D., Steinberger, M., and Seidel, H.-P. 2018b. Layered Fields for Natural Tessellations on Surfaces. http://arxiv.org/abs/1804.09152.

(arXiv: 1804.09152)

Abstract

Mimicking natural tessellation patterns is a fascinating multi-disciplinary problem. Geometric methods aiming at reproducing such partitions on surface meshes are commonly based on the Voronoi model and its variants, and are often faced with challenging issues such as metric estimation, geometric, topological complications, and most critically parallelization. In this paper, we introduce an alternate model which may be of value for resolving these issues. We drop the assumption that regions need to be separated by lines. Instead, we regard region boundaries as narrow bands and we model the partition as a set of smooth functions layered over the surface. Given an initial set of seeds or regions, the partition emerges as the solution of a time dependent set of partial differential equations describing concurrently evolving fronts on the surface. Our solution does not require geodesic estimation, elaborate numerical solvers, or complicated bookkeeping data structures. The cost per time-iteration is dominated by the multiplication and addition of two sparse matrices. Extension of our approach in a Lloyd's algorithm fashion can be easily achieved and the extraction of the dual mesh can be conveniently preformed in parallel through matrix algebra. As our approach relies mainly on basic linear algebra kernels, it lends itself to efficient implementation on modern graphics hardware.

Links

Export

BibTeX

@online{Zayer_arXiv1804.09152, TITLE = {Layered Fields for Natural Tessellations on Surfaces}, AUTHOR = {Zayer, Rhaleb and Mlakar, Daniel and Steinberger, Markus and Seidel, Hans-Peter}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1804.09152}, EPRINT = {1804.09152}, EPRINTTYPE = {arXiv}, YEAR = {2018}, ABSTRACT = {Mimicking natural tessellation patterns is a fascinating multi-disciplinary problem. Geometric methods aiming at reproducing such partitions on surface meshes are commonly based on the Voronoi model and its variants, and are often faced with challenging issues such as metric estimation, geometric, topological complications, and most critically parallelization. In this paper, we introduce an alternate model which may be of value for resolving these issues. We drop the assumption that regions need to be separated by lines. Instead, we regard region boundaries as narrow bands and we model the partition as a set of smooth functions layered over the surface. Given an initial set of seeds or regions, the partition emerges as the solution of a time dependent set of partial differential equations describing concurrently evolving fronts on the surface. Our solution does not require geodesic estimation, elaborate numerical solvers, or complicated bookkeeping data structures. The cost per time-iteration is dominated by the multiplication and addition of two sparse matrices. Extension of our approach in a Lloyd's algorithm fashion can be easily achieved and the extraction of the dual mesh can be conveniently preformed in parallel through matrix algebra. As our approach relies mainly on basic linear algebra kernels, it lends itself to efficient implementation on modern graphics hardware.}, }

Endnote

%0 Report %A Zayer, Rhaleb %A Mlakar, Daniel %A Steinberger, Markus %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Layered Fields for Natural Tessellations on Surfaces : %G eng %U http://hdl.handle.net/21.11116/0000-0002-152D-5 %U http://arxiv.org/abs/1804.09152 %D 2018 %X Mimicking natural tessellation patterns is a fascinating multi-disciplinary problem. Geometric methods aiming at reproducing such partitions on surface meshes are commonly based on the Voronoi model and its variants, and are often faced with challenging issues such as metric estimation, geometric, topological complications, and most critically parallelization. In this paper, we introduce an alternate model which may be of value for resolving these issues. We drop the assumption that regions need to be separated by lines. Instead, we regard region boundaries as narrow bands and we model the partition as a set of smooth functions layered over the surface. Given an initial set of seeds or regions, the partition emerges as the solution of a time dependent set of partial differential equations describing concurrently evolving fronts on the surface. Our solution does not require geodesic estimation, elaborate numerical solvers, or complicated bookkeeping data structures. The cost per time-iteration is dominated by the multiplication and addition of two sparse matrices. Extension of our approach in a Lloyd's algorithm fashion can be easily achieved and the extraction of the dual mesh can be conveniently preformed in parallel through matrix algebra. As our approach relies mainly on basic linear algebra kernels, it lends itself to efficient implementation on modern graphics hardware. %K Computer Science, Graphics, cs.GR,Computer Science, Distributed, Parallel, and Cluster Computing, cs.DC

Xu, W., Chatterjee, A., Zollhöfer, M., et al. 2018a. MonoPerfCap: Human Performance Capture from Monocular Video. ACM Transactions on Graphics37, 2.

Abstract

We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video. Our approach reconstructs articulated human skeleton motion as well as medium-scale non-rigid surface deformations in general scenes. Human performance capture is a challenging problem due to the large range of articulation, potentially fast motion, and considerable non-rigid deformations, even from multi-view data. Reconstruction from monocular video alone is drastically more challenging, since strong occlusions and the inherent depth ambiguity lead to a highly ill-posed reconstruction problem. We tackle these challenges by a novel approach that employs sparse 2D and 3D human pose detections from a convolutional neural network using a batch-based pose estimation strategy. Joint recovery of per-batch motion allows to resolve the ambiguities of the monocular reconstruction problem based on a low dimensional trajectory subspace. In addition, we propose refinement of the surface geometry based on fully automatically extracted silhouettes to enable medium-scale non-rigid alignment. We demonstrate state-of-the-art performance capture results that enable exciting applications such as video editing and free viewpoint video, previously infeasible from monocular video. Our qualitative and quantitative evaluation demonstrates that our approach significantly outperforms previous monocular methods in terms of accuracy, robustness and scene complexity that can be handled.

Links

Export

BibTeX

@article{Xu_ToG2018, TITLE = {{MonoPerfCap}: Human Performance Capture from Monocular Video}, AUTHOR = {Xu, Weipeng and Chatterjee, Avishek and Zollh{\"o}fer, Michael and Rhodin, Helge and Mehta, Dushyant and Seidel, Hans-Peter and Theobalt, Christian}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3181973}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2018}, DATE = {2018}, ABSTRACT = {We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video. Our approach reconstructs articulated human skeleton motion as well as medium-scale non-rigid surface deformations in general scenes. Human performance capture is a challenging problem due to the large range of articulation, potentially fast motion, and considerable non-rigid deformations, even from multi-view data. Reconstruction from monocular video alone is drastically more challenging, since strong occlusions and the inherent depth ambiguity lead to a highly ill-posed reconstruction problem. We tackle these challenges by a novel approach that employs sparse 2D and 3D human pose detections from a convolutional neural network using a batch-based pose estimation strategy. Joint recovery of per-batch motion allows to resolve the ambiguities of the monocular reconstruction problem based on a low dimensional trajectory subspace. In addition, we propose refinement of the surface geometry based on fully automatically extracted silhouettes to enable medium-scale non-rigid alignment. We demonstrate state-of-the-art performance capture results that enable exciting applications such as video editing and free viewpoint video, previously infeasible from monocular video. Our qualitative and quantitative evaluation demonstrates that our approach significantly outperforms previous monocular methods in terms of accuracy, robustness and scene complexity that can be handled.}, JOURNAL = {ACM Transactions on Graphics}, VOLUME = {37}, NUMBER = {2}, EID = {27}, }

Endnote

%0 Journal Article %A Xu, Weipeng %A Chatterjee, Avishek %A Zollhöfer, Michael %A Rhodin, Helge %A Mehta, Dushyant %A Seidel, Hans-Peter %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T MonoPerfCap: Human Performance Capture from Monocular Video : %G eng %U http://hdl.handle.net/21.11116/0000-0001-E20E-1 %R 10.1145/3181973 %7 2017 %D 2018 %X We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video. Our approach reconstructs articulated human skeleton motion as well as medium-scale non-rigid surface deformations in general scenes. Human performance capture is a challenging problem due to the large range of articulation, potentially fast motion, and considerable non-rigid deformations, even from multi-view data. Reconstruction from monocular video alone is drastically more challenging, since strong occlusions and the inherent depth ambiguity lead to a highly ill-posed reconstruction problem. We tackle these challenges by a novel approach that employs sparse 2D and 3D human pose detections from a convolutional neural network using a batch-based pose estimation strategy. Joint recovery of per-batch motion allows to resolve the ambiguities of the monocular reconstruction problem based on a low dimensional trajectory subspace. In addition, we propose refinement of the surface geometry based on fully automatically extracted silhouettes to enable medium-scale non-rigid alignment. We demonstrate state-of-the-art performance capture results that enable exciting applications such as video editing and free viewpoint video, previously infeasible from monocular video. Our qualitative and quantitative evaluation demonstrates that our approach significantly outperforms previous monocular methods in terms of accuracy, robustness and scene complexity that can be handled. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Graphics, cs.GR %J ACM Transactions on Graphics %V 37 %N 2 %Z sequence number: 27 %I ACM %C New York, NY %@ false

Xu, W., Chatterjee, A., Zollhöfer, M., et al. 2018b. Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera. http://arxiv.org/abs/1803.05959.

(arXiv: 1803.05959)

Abstract

We propose the first real-time approach for the egocentric estimation of 3D human body pose in a wide range of unconstrained everyday activities. This setting has a unique set of challenges, such as mobility of the hardware setup, and robustness to long capture sessions with fast recovery from tracking failures. We tackle these challenges based on a novel lightweight setup that converts a standard baseball cap to a device for high-quality pose estimation based on a single cap-mounted fisheye camera. From the captured egocentric live stream, our CNN based 3D pose estimation approach runs at 60Hz on a consumer-level GPU. In addition to the novel hardware setup, our other main contributions are: 1) a large ground truth training corpus of top-down fisheye images and 2) a novel disentangled 3D pose estimation approach that takes the unique properties of the egocentric viewpoint into account. As shown by our evaluation, we achieve lower 3D joint error as well as better 2D overlay than the existing baselines.

Links

Export

BibTeX

@online{Xu_arXiv1803.05959, TITLE = {{Mo2Cap2}: Real-time Mobile {3D} Motion Capture with a Cap-mounted Fisheye Camera}, AUTHOR = {Xu, Weipeng and Chatterjee, Avishek and Zollh{\"o}fer, Michael and Rhodin, Helge and Fua, Pascal and Seidel, Hans-Peter and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1803.05959}, EPRINT = {1803.05959}, EPRINTTYPE = {arXiv}, YEAR = {2018}, ABSTRACT = {We propose the first real-time approach for the egocentric estimation of 3D human body pose in a wide range of unconstrained everyday activities. This setting has a unique set of challenges, such as mobility of the hardware setup, and robustness to long capture sessions with fast recovery from tracking failures. We tackle these challenges based on a novel lightweight setup that converts a standard baseball cap to a device for high-quality pose estimation based on a single cap-mounted fisheye camera. From the captured egocentric live stream, our CNN based 3D pose estimation approach runs at 60Hz on a consumer-level GPU. In addition to the novel hardware setup, our other main contributions are: 1) a large ground truth training corpus of top-down fisheye images and 2) a novel disentangled 3D pose estimation approach that takes the unique properties of the egocentric viewpoint into account. As shown by our evaluation, we achieve lower 3D joint error as well as better 2D overlay than the existing baselines.}, }

Endnote

%0 Report %A Xu, Weipeng %A Chatterjee, Avishek %A Zollhöfer, Michael %A Rhodin, Helge %A Fua, Pascal %A Seidel, Hans-Peter %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera : %G eng %U http://hdl.handle.net/21.11116/0000-0001-3C65-B %U http://arxiv.org/abs/1803.05959 %D 2018 %X We propose the first real-time approach for the egocentric estimation of 3D human body pose in a wide range of unconstrained everyday activities. This setting has a unique set of challenges, such as mobility of the hardware setup, and robustness to long capture sessions with fast recovery from tracking failures. We tackle these challenges based on a novel lightweight setup that converts a standard baseball cap to a device for high-quality pose estimation based on a single cap-mounted fisheye camera. From the captured egocentric live stream, our CNN based 3D pose estimation approach runs at 60Hz on a consumer-level GPU. In addition to the novel hardware setup, our other main contributions are: 1) a large ground truth training corpus of top-down fisheye images and 2) a novel disentangled 3D pose estimation approach that takes the unique properties of the egocentric viewpoint into account. As shown by our evaluation, we achieve lower 3D joint error as well as better 2D overlay than the existing baselines. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV

Wolski, K., Giunchi, D., Ye, N., et al. 2018. Dataset and Metrics for Predicting Local Visible Differences. ACM Transactions on Graphics37, 5.

Links

Export

BibTeX

@article{wolski2018dataset, TITLE = {Dataset and Metrics for Predicting Local Visible Differences}, AUTHOR = {Wolski, Krzysztof and Giunchi, Daniele and Ye, Nanyang and Didyk, Piotr and Myszkowski, Karol and Mantiuk, Rados{\textbackslash}l{\textbraceleft}{\textbraceright}aw and Seidel, Hans-Peter and Steed, Anthony and Mantiuk, Rafa{\l} K.}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3196493}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2018}, DATE = {2018}, JOURNAL = {ACM Transactions on Graphics}, VOLUME = {37}, NUMBER = {5}, EID = {172}, }

Endnote

%0 Journal Article %A Wolski, Krzysztof %A Giunchi, Daniele %A Ye, Nanyang %A Didyk, Piotr %A Myszkowski, Karol %A Mantiuk, Rados\l{}aw %A Seidel, Hans-Peter %A Steed, Anthony %A Mantiuk, Rafał K. %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations %T Dataset and Metrics for Predicting Local Visible Differences : %G eng %U http://hdl.handle.net/21.11116/0000-0001-5F75-2 %R 10.1145/3196493 %7 2018 %D 2018 %J ACM Transactions on Graphics %V 37 %N 5 %Z sequence number: 172 %I ACM %C New York, NY %@ false

Winter, M., Mlakar, D., Zayer, R., Seidel, H.-P., and Steinberger, M. 2018. faimGraph: High Performance Management of Fully-Dynamic Graphs Under Tight Memory Constraints on the GPU. The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2018), IEEE.

Links

Export

BibTeX

@inproceedings{Winter:2018:FHP, TITLE = {{faimGraph}: {H}igh Performance Management of Fully-Dynamic Graphs Under Tight Memory Constraints on the {GPU}}, AUTHOR = {Winter, Martin and Mlakar, Daniel and Zayer, Rhaleb and Seidel, Hans-Peter and Steinberger, Markus}, LANGUAGE = {eng}, ISBN = {978-1-5386-8384-2}, URL = {http://conferences.computer.org/sc/2018/#!/home}, PUBLISHER = {IEEE}, YEAR = {2018}, BOOKTITLE = {The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2018)}, PAGES = {754--766}, ADDRESS = {Dallas, TX, USA}, }

Endnote

%0 Conference Proceedings %A Winter, Martin %A Mlakar, Daniel %A Zayer, Rhaleb %A Seidel, Hans-Peter %A Steinberger, Markus %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T faimGraph: High Performance Management of Fully-Dynamic Graphs Under Tight Memory Constraints on the GPU : %G eng %U http://hdl.handle.net/21.11116/0000-0002-E5E6-8 %D 2018 %B The International Conference for High Performance Computing, Networking, Storage, and Analysis %Z date of event: 2018-11-11 - 2018-11-16 %C Dallas, TX, USA %B The International Conference for High Performance Computing, Networking, Storage, and Analysis %P 754 - 766 %I IEEE %@ 978-1-5386-8384-2

Tewari, A., Bernard, F., Garrido, P., et al. 2018. FML: Face Model Learning from Videos. http://arxiv.org/abs/1812.07603.

(arXiv: 1812.07603)

Abstract

Monocular image-based 3D reconstruction of faces is a long-standing problem in computer vision. Since image data is a 2D projection of a 3D face, the resulting depth ambiguity makes the problem ill-posed. Most existing methods rely on data-driven priors that are built from limited 3D face scans. In contrast, we propose multi-frame video-based self-supervised training of a deep network that (i) learns a face identity model both in shape and appearance while (ii) jointly learning to reconstruct 3D faces. Our face model is learned using only corpora of in-the-wild video clips collected from the Internet. This virtually endless source of training data enables learning of a highly general 3D face model. In order to achieve this, we propose a novel multi-frame consistency loss that ensures consistent shape and appearance across multiple frames of a subject's face, thus minimizing depth ambiguity. At test time we can use an arbitrary number of frames, so that we can perform both monocular as well as multi-frame reconstruction.

Links

Export

BibTeX

@online{tewari2018fml, TITLE = {{FML}: {Face Model Learning from Videos}}, AUTHOR = {Tewari, Ayush and Bernard, Florian and Garrido, Pablo and Bharaj, Gaurav and Elgharib, Mohamed and Seidel, Hans-Peter and P{\'e}rez, Patrick and Zollh{\"o}fer, Michael and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1812.07603}, EPRINT = {1812.07603}, EPRINTTYPE = {arXiv}, YEAR = {2018}, ABSTRACT = {Monocular image-based 3D reconstruction of faces is a long-standing problem in computer vision. Since image data is a 2D projection of a 3D face, the resulting depth ambiguity makes the problem ill-posed. Most existing methods rely on data-driven priors that are built from limited 3D face scans. In contrast, we propose multi-frame video-based self-supervised training of a deep network that (i) learns a face identity model both in shape and appearance while (ii) jointly learning to reconstruct 3D faces. Our face model is learned using only corpora of in-the-wild video clips collected from the Internet. This virtually endless source of training data enables learning of a highly general 3D face model. In order to achieve this, we propose a novel multi-frame consistency loss that ensures consistent shape and appearance across multiple frames of a subject's face, thus minimizing depth ambiguity. At test time we can use an arbitrary number of frames, so that we can perform both monocular as well as multi-frame reconstruction. }, }

Endnote

%0 Report %A Tewari, Ayush %A Bernard, Florian %A Garrido, Pablo %A Bharaj, Gaurav %A Elgharib, Mohamed %A Seidel, Hans-Peter %A Pérez, Patrick %A Zollhöfer, Michael %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T FML: Face Model Learning from Videos : %G eng %U http://hdl.handle.net/21.11116/0000-0002-EF79-A %U http://arxiv.org/abs/1812.07603 %D 2018 %X Monocular image-based 3D reconstruction of faces is a long-standing problem in computer vision. Since image data is a 2D projection of a 3D face, the resulting depth ambiguity makes the problem ill-posed. Most existing methods rely on data-driven priors that are built from limited 3D face scans. In contrast, we propose multi-frame video-based self-supervised training of a deep network that (i) learns a face identity model both in shape and appearance while (ii) jointly learning to reconstruct 3D faces. Our face model is learned using only corpora of in-the-wild video clips collected from the Internet. This virtually endless source of training data enables learning of a highly general 3D face model. In order to achieve this, we propose a novel multi-frame consistency loss that ensures consistent shape and appearance across multiple frames of a subject's face, thus minimizing depth ambiguity. At test time we can use an arbitrary number of frames, so that we can perform both monocular as well as multi-frame reconstruction. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV %U https://www.youtube.com/watch?v=SG2BwxCw0lQ

Serrano, A., Gutierrez, D., Myszkowski, K., Seidel, H.-P., and Masia, B. 2018. An Intuitive Control Space for Material Appearance. http://arxiv.org/abs/1806.04950.

(arXiv: 1806.04950)

Abstract

Many different techniques for measuring material appearance have been proposed in the last few years. These have produced large public datasets, which have been used for accurate, data-driven appearance modeling. However, although these datasets have allowed us to reach an unprecedented level of realism in visual appearance, editing the captured data remains a challenge. In this paper, we present an intuitive control space for predictable editing of captured BRDF data, which allows for artistic creation of plausible novel material appearances, bypassing the difficulty of acquiring novel samples. We first synthesize novel materials, extending the existing MERL dataset up to 400 mathematically valid BRDFs. We then design a large-scale experiment, gathering 56,000 subjective ratings on the high-level perceptual attributes that best describe our extended dataset of materials. Using these ratings, we build and train networks of radial basis functions to act as functionals mapping the perceptual attributes to an underlying PCA-based representation of BRDFs. We show that our functionals are excellent predictors of the perceived attributes of appearance. Our control space enables many applications, including intuitive material editing of a wide range of visual properties, guidance for gamut mapping, analysis of the correlation between perceptual attributes, or novel appearance similarity metrics. Moreover, our methodology can be used to derive functionals applicable to classic analytic BRDF representations. We release our code and dataset publicly, in order to support and encourage further research in this direction.

Links

Export

BibTeX

@online{Serrano_arXiv1806.04950, TITLE = {An Intuitive Control Space for Material Appearance}, AUTHOR = {Serrano, Ana and Gutierrez, Diego and Myszkowski, Karol and Seidel, Hans-Peter and Masia, Belen}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1806.04950}, EPRINT = {1806.04950}, EPRINTTYPE = {arXiv}, YEAR = {2018}, ABSTRACT = {Many different techniques for measuring material appearance have been proposed in the last few years. These have produced large public datasets, which have been used for accurate, data-driven appearance modeling. However, although these datasets have allowed us to reach an unprecedented level of realism in visual appearance, editing the captured data remains a challenge. In this paper, we present an intuitive control space for predictable editing of captured BRDF data, which allows for artistic creation of plausible novel material appearances, bypassing the difficulty of acquiring novel samples. We first synthesize novel materials, extending the existing MERL dataset up to 400 mathematically valid BRDFs. We then design a large-scale experiment, gathering 56,000 subjective ratings on the high-level perceptual attributes that best describe our extended dataset of materials. Using these ratings, we build and train networks of radial basis functions to act as functionals mapping the perceptual attributes to an underlying PCA-based representation of BRDFs. We show that our functionals are excellent predictors of the perceived attributes of appearance. Our control space enables many applications, including intuitive material editing of a wide range of visual properties, guidance for gamut mapping, analysis of the correlation between perceptual attributes, or novel appearance similarity metrics. Moreover, our methodology can be used to derive functionals applicable to classic analytic BRDF representations. We release our code and dataset publicly, in order to support and encourage further research in this direction. }, }

Endnote

%0 Report %A Serrano, Ana %A Gutierrez, Diego %A Myszkowski, Karol %A Seidel, Hans-Peter %A Masia, Belen %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T An Intuitive Control Space for Material Appearance : %G eng %U http://hdl.handle.net/21.11116/0000-0002-151E-6 %U http://arxiv.org/abs/1806.04950 %D 2018 %X Many different techniques for measuring material appearance have been proposed in the last few years. These have produced large public datasets, which have been used for accurate, data-driven appearance modeling. However, although these datasets have allowed us to reach an unprecedented level of realism in visual appearance, editing the captured data remains a challenge. In this paper, we present an intuitive control space for predictable editing of captured BRDF data, which allows for artistic creation of plausible novel material appearances, bypassing the difficulty of acquiring novel samples. We first synthesize novel materials, extending the existing MERL dataset up to 400 mathematically valid BRDFs. We then design a large-scale experiment, gathering 56,000 subjective ratings on the high-level perceptual attributes that best describe our extended dataset of materials. Using these ratings, we build and train networks of radial basis functions to act as functionals mapping the perceptual attributes to an underlying PCA-based representation of BRDFs. We show that our functionals are excellent predictors of the perceived attributes of appearance. Our control space enables many applications, including intuitive material editing of a wide range of visual properties, guidance for gamut mapping, analysis of the correlation between perceptual attributes, or novel appearance similarity metrics. Moreover, our methodology can be used to derive functionals applicable to classic analytic BRDF representations. We release our code and dataset publicly, in order to support and encourage further research in this direction. %K Computer Science, Graphics, cs.GR

Myszkowski, K., Tursun, O.T., Kellnhofer, P., et al. 2018. Perceptual Display: Apparent Enhancement of Scene Detail and Depth. Electronic Imaging (Proc. HVEI 2018), SPIE/IS&T.

(Keynote Talk)

Abstract

Predicting human visual perception of image differences has several applications such as compression, rendering, editing and retargeting. Current approaches however, ignore the fact that the human visual system compensates for geometric transformations, e.g. we see that an image and a rotated copy are identical. Instead, they will report a large, false-positive difference. At the same time, if the transformations become too strong or too spatially incoherent, comparing two images indeed gets increasingly difficult. Between these two extremes, we propose a system to quantify the effect of transformations, not only on the perception of image differences, but also on saliency and motion parallax. To this end, we first fit local homographies to a given optical flow field and then convert this field into a field of elementary transformations such as translation, rotation, scaling, and perspective. We conduct a perceptual experiment quantifying the increase of difficulty when compensating for elementary transformations. Transformation entropy is proposed as a novel measure of complexity in a flow field. This representation is then used for applications, such as comparison of non-aligned images, where transformations cause threshold elevation, and detection of salient transformations.

Links

Export

BibTeX

@inproceedings{Myszkowski2018Perceptual, TITLE = {Perceptual Display: Apparent Enhancement of Scene Detail and Depth}, AUTHOR = {Myszkowski, Karol and Tursun, Okan Tarhan and Kellnhofer, Petr and Templin, Krzysztof and Arabadzhiyska, Elena and Didyk, Piotr and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {2470-1173}, DOI = {10.2352/ISSN.2470-1173.2018.14.HVEI-501}, PUBLISHER = {SPIE/IS\&T}, YEAR = {2018}, ABSTRACT = {Predicting human visual perception of image differences has several applications such as compression, rendering, editing and retargeting. Current approaches however, ignore the fact that the human visual system compensates for geometric transformations, e.g. we see that an image and a rotated copy are identical. Instead, they will report a large, false-positive difference. At the same time, if the transformations become too strong or too spatially incoherent, comparing two images indeed gets increasingly difficult. Between these two extremes, we propose a system to quantify the effect of transformations, not only on the perception of image differences, but also on saliency and motion parallax. To this end, we first fit local homographies to a given optical flow field and then convert this field into a field of elementary transformations such as translation, rotation, scaling, and perspective. We conduct a perceptual experiment quantifying the increase of difficulty when compensating for elementary transformations. Transformation entropy is proposed as a novel measure of complexity in a flow field. This representation is then used for applications, such as comparison of non-aligned images, where transformations cause threshold elevation, and detection of salient transformations.}, BOOKTITLE = {Human Vision and Electronic Imaging (HVEI 2018)}, PAGES = {1--10}, EID = {501}, JOURNAL = {Electronic Imaging (Proc. HVEI)}, VOLUME = {2018}, ADDRESS = {San Francisco, CA, USA}, }

Endnote

%0 Conference Proceedings %A Myszkowski, Karol %A Tursun, Okan Tarhan %A Kellnhofer, Petr %A Templin, Krzysztof %A Arabadzhiyska, Elena %A Didyk, Piotr %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Perceptual Display: Apparent Enhancement of Scene Detail and Depth : %G eng %U http://hdl.handle.net/21.11116/0000-0001-5F64-5 %R 10.2352/ISSN.2470-1173.2018.14.HVEI-501 %D 2018 %B Human Vision and Electronic Imaging %Z date of event: 2018-01-28 - 2018-02-02 %C San Francisco, CA, USA %X Predicting human visual perception of image differences has several applications such as compression, rendering, editing and retargeting. Current approaches however, ignore the fact that the human visual system compensates for geometric transformations, e.g. we see that an image and a rotated copy are identical. Instead, they will report a large, false-positive difference. At the same time, if the transformations become too strong or too spatially incoherent, comparing two images indeed gets increasingly difficult. Between these two extremes, we propose a system to quantify the effect of transformations, not only on the perception of image differences, but also on saliency and motion parallax. To this end, we first fit local homographies to a given optical flow field and then convert this field into a field of elementary transformations such as translation, rotation, scaling, and perspective. We conduct a perceptual experiment quantifying the increase of difficulty when compensating for elementary transformations. Transformation entropy is proposed as a novel measure of complexity in a flow field. This representation is then used for applications, such as comparison of non-aligned images, where transformations cause threshold elevation, and detection of salient transformations. %B Human Vision and Electronic Imaging %P 1 - 10 %Z sequence number: 501 %I SPIE/IS&T %J Electronic Imaging %V 2018 %@ false

Mlakar, D., Winter, M., Seidel, H.-P., Steinberger, M., and Zayer, R. 2018. AlSub: Fully Parallel and Modular Subdivision. http://arxiv.org/abs/1809.06047.

(arXiv: 1809.06047)

Abstract

In recent years, mesh subdivision---the process of forging smooth free-form surfaces from coarse polygonal meshes---has become an indispensable production instrument. Although subdivision performance is crucial during simulation, animation and rendering, state-of-the-art approaches still rely on serial implementations for complex parts of the subdivision process. Therefore, they often fail to harness the power of modern parallel devices, like the graphics processing unit (GPU), for large parts of the algorithm and must resort to time-consuming serial preprocessing. In this paper, we show that a complete parallelization of the subdivision process for modern architectures is possible. Building on sparse matrix linear algebra, we show how to structure the complete subdivision process into a sequence of algebra operations. By restructuring and grouping these operations, we adapt the process for different use cases, such as regular subdivision of dynamic meshes, uniform subdivision for immutable topology, and feature-adaptive subdivision for efficient rendering of animated models. As the same machinery is used for all use cases, identical subdivision results are achieved in all parts of the production pipeline. As a second contribution, we show how these linear algebra formulations can effectively be translated into efficient GPU kernels. Applying our strategies to $\sqrt{3}$, Loop and Catmull-Clark subdivision shows significant speedups of our approach compared to state-of-the-art solutions, while we completely avoid serial preprocessing.

Links

Export

BibTeX

@online{Mlakar_arXiv1809.06047, TITLE = {{AlSub}: {Fully Parallel and Modular Subdivision}}, AUTHOR = {Mlakar, Daniel and Winter, Martin and Seidel, Hans-Peter and Steinberger, Markus and Zayer, Rhaleb}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1809.06047}, EPRINT = {1809.06047}, EPRINTTYPE = {arXiv}, YEAR = {2018}, ABSTRACT = {In recent years, mesh subdivision---the process of forging smooth free-form surfaces from coarse polygonal meshes---has become an indispensable production instrument. Although subdivision performance is crucial during simulation, animation and rendering, state-of-the-art approaches still rely on serial implementations for complex parts of the subdivision process. Therefore, they often fail to harness the power of modern parallel devices, like the graphics processing unit (GPU), for large parts of the algorithm and must resort to time-consuming serial preprocessing. In this paper, we show that a complete parallelization of the subdivision process for modern architectures is possible. Building on sparse matrix linear algebra, we show how to structure the complete subdivision process into a sequence of algebra operations. By restructuring and grouping these operations, we adapt the process for different use cases, such as regular subdivision of dynamic meshes, uniform subdivision for immutable topology, and feature-adaptive subdivision for efficient rendering of animated models. As the same machinery is used for all use cases, identical subdivision results are achieved in all parts of the production pipeline. As a second contribution, we show how these linear algebra formulations can effectively be translated into efficient GPU kernels. Applying our strategies to $\sqrt{3}$, Loop and Catmull-Clark subdivision shows significant speedups of our approach compared to state-of-the-art solutions, while we completely avoid serial preprocessing. }, }

Endnote

%0 Report %A Mlakar, Daniel %A Winter, Martin %A Seidel, Hans-Peter %A Steinberger, Markus %A Zayer, Rhaleb %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T AlSub: Fully Parallel and Modular Subdivision : %G eng %U http://hdl.handle.net/21.11116/0000-0002-E5E2-C %U http://arxiv.org/abs/1809.06047 %D 2018 %X In recent years, mesh subdivision---the process of forging smooth free-form surfaces from coarse polygonal meshes---has become an indispensable production instrument. Although subdivision performance is crucial during simulation, animation and rendering, state-of-the-art approaches still rely on serial implementations for complex parts of the subdivision process. Therefore, they often fail to harness the power of modern parallel devices, like the graphics processing unit (GPU), for large parts of the algorithm and must resort to time-consuming serial preprocessing. In this paper, we show that a complete parallelization of the subdivision process for modern architectures is possible. Building on sparse matrix linear algebra, we show how to structure the complete subdivision process into a sequence of algebra operations. By restructuring and grouping these operations, we adapt the process for different use cases, such as regular subdivision of dynamic meshes, uniform subdivision for immutable topology, and feature-adaptive subdivision for efficient rendering of animated models. As the same machinery is used for all use cases, identical subdivision results are achieved in all parts of the production pipeline. As a second contribution, we show how these linear algebra formulations can effectively be translated into efficient GPU kernels. Applying our strategies to $\sqrt{3}$, Loop and Catmull-Clark subdivision shows significant speedups of our approach compared to state-of-the-art solutions, while we completely avoid serial preprocessing. %K Computer Science, Graphics, cs.GR

Meka, A., Maximov, M., Zollhöfer, M., et al. 2018a. LIME: Live Intrinsic Material Estimation. http://arxiv.org/abs/1801.01075.

(arXiv: 1801.01075)

Abstract

We present the first end to end approach for real time material estimation for general object shapes with uniform material that only requires a single color image as input. In addition to Lambertian surface properties, our approach fully automatically computes the specular albedo, material shininess, and a foreground segmentation. We tackle this challenging and ill posed inverse rendering problem using recent advances in image to image translation techniques based on deep convolutional encoder decoder architectures. The underlying core representations of our approach are specular shading, diffuse shading and mirror images, which allow to learn the effective and accurate separation of diffuse and specular albedo. In addition, we propose a novel highly efficient perceptual rendering loss that mimics real world image formation and obtains intermediate results even during run time. The estimation of material parameters at real time frame rates enables exciting mixed reality applications, such as seamless illumination consistent integration of virtual objects into real world scenes, and virtual material cloning. We demonstrate our approach in a live setup, compare it to the state of the art, and demonstrate its effectiveness through quantitative and qualitative evaluation.

Links

Export

BibTeX

@online{Meka_arXiv1801.01075, TITLE = {LIME: {L}ive Intrinsic Material Estimation}, AUTHOR = {Meka, Abhimitra and Maximov, Maxim and Zollh{\"o}fer, Michael and Chatterjee, Avishek and Seidel, Hans-Peter and Richardt, Christian and Theobalt, Christian}, URL = {http://arxiv.org/abs/1801.01075}, EPRINT = {1801.01075}, EPRINTTYPE = {arXiv}, YEAR = {2018}, ABSTRACT = {We present the first end to end approach for real time material estimation for general object shapes with uniform material that only requires a single color image as input. In addition to Lambertian surface properties, our approach fully automatically computes the specular albedo, material shininess, and a foreground segmentation. We tackle this challenging and ill posed inverse rendering problem using recent advances in image to image translation techniques based on deep convolutional encoder decoder architectures. The underlying core representations of our approach are specular shading, diffuse shading and mirror images, which allow to learn the effective and accurate separation of diffuse and specular albedo. In addition, we propose a novel highly efficient perceptual rendering loss that mimics real world image formation and obtains intermediate results even during run time. The estimation of material parameters at real time frame rates enables exciting mixed reality applications, such as seamless illumination consistent integration of virtual objects into real world scenes, and virtual material cloning. We demonstrate our approach in a live setup, compare it to the state of the art, and demonstrate its effectiveness through quantitative and qualitative evaluation.}, }

Endnote

%0 Report %A Meka, Abhimitra %A Maximov, Maxim %A Zollhöfer, Michael %A Chatterjee, Avishek %A Seidel, Hans-Peter %A Richardt, Christian %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society D2 External Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T LIME: Live Intrinsic Material Estimation : %U http://hdl.handle.net/21.11116/0000-0001-40D9-2 %U http://arxiv.org/abs/1801.01075 %D 2018 %X We present the first end to end approach for real time material estimation for general object shapes with uniform material that only requires a single color image as input. In addition to Lambertian surface properties, our approach fully automatically computes the specular albedo, material shininess, and a foreground segmentation. We tackle this challenging and ill posed inverse rendering problem using recent advances in image to image translation techniques based on deep convolutional encoder decoder architectures. The underlying core representations of our approach are specular shading, diffuse shading and mirror images, which allow to learn the effective and accurate separation of diffuse and specular albedo. In addition, we propose a novel highly efficient perceptual rendering loss that mimics real world image formation and obtains intermediate results even during run time. The estimation of material parameters at real time frame rates enables exciting mixed reality applications, such as seamless illumination consistent integration of virtual objects into real world scenes, and virtual material cloning. We demonstrate our approach in a live setup, compare it to the state of the art, and demonstrate its effectiveness through quantitative and qualitative evaluation. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV

Meka, A., Maximov, M., Zollhöfer, M., et al. 2018b. LIME: Live Intrinsic Material Estimation. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018), IEEE.

Links

Export

BibTeX

@inproceedings{Meka:2018, TITLE = {{LIME}: {L}ive Intrinsic Material Estimation}, AUTHOR = {Meka, Abhimitra and Maximov, Maxim and Zollh{\"o}fer, Michael and Chatterjee, Avishek and Seidel, Hans-Peter and Richardt, Christian and Theobalt, Christian}, LANGUAGE = {eng}, ISBN = {978-1-5386-6420-9}, DOI = {10.1109/CVPR.2018.00661}, PUBLISHER = {IEEE}, YEAR = {2018}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018)}, PAGES = {6315--6324}, ADDRESS = {Salt Lake City, UT, USA}, }

Endnote

%0 Conference Proceedings %A Meka, Abhimitra %A Maximov, Maxim %A Zollhöfer, Michael %A Chatterjee, Avishek %A Seidel, Hans-Peter %A Richardt, Christian %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T LIME: Live Intrinsic Material Estimation : %G eng %U http://hdl.handle.net/21.11116/0000-0002-F391-7 %R 10.1109/CVPR.2018.00661 %D 2018 %B 31st IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2018-06-18 - 2018-06-22 %C Salt Lake City, UT, USA %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 6315 - 6324 %I IEEE %@ 978-1-5386-6420-9 %U http://gvv.mpi-inf.mpg.de/projects/LIME/

Leimkühler, T., Singh, G., Myszkowski, K., Seidel, H.-P., and Ritschel, T. 2018a. End-to-end Sampling Patterns. http://arxiv.org/abs/1806.06710.

(arXiv: 1806.06710)

Abstract

Sample patterns have many uses in Computer Graphics, ranging from procedural object placement over Monte Carlo image synthesis to non-photorealistic depiction. Their properties such as discrepancy, spectra, anisotropy, or progressiveness have been analyzed extensively. However, designing methods to produce sampling patterns with certain properties can require substantial hand-crafting effort, both in coding, mathematical derivation and compute time. In particular, there is no systematic way to derive the best sampling algorithm for a specific end-task. Tackling this issue, we suggest another level of abstraction: a toolkit to end-to-end optimize over all sampling methods to find the one producing user-prescribed properties such as discrepancy or a spectrum that best fit the end-task. A user simply implements the forward losses and the sampling method is found automatically -- without coding or mathematical derivation -- by making use of back-propagation abilities of modern deep learning frameworks. While this optimization takes long, at deployment time the sampling method is quick to execute as iterated unstructured non-linear filtering using radial basis functions (RBFs) to represent high-dimensional kernels. Several important previous methods are special cases of this approach, which we compare to previous work and demonstrate its usefulness in several typical Computer Graphics applications. Finally, we propose sampling patterns with properties not shown before, such as high-dimensional blue noise with projective properties.

Links

Export

BibTeX

@online{Leimkuehler_arXiv1806.06710, TITLE = {End-to-end Sampling Patterns}, AUTHOR = {Leimk{\"u}hler, Thomas and Singh, Gurprit and Myszkowski, Karol and Seidel, Hans-Peter and Ritschel, Tobias}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1806.06710}, EPRINT = {1806.06710}, EPRINTTYPE = {arXiv}, YEAR = {2018}, ABSTRACT = {Sample patterns have many uses in Computer Graphics, ranging from procedural object placement over Monte Carlo image synthesis to non-photorealistic depiction. Their properties such as discrepancy, spectra, anisotropy, or progressiveness have been analyzed extensively. However, designing methods to produce sampling patterns with certain properties can require substantial hand-crafting effort, both in coding, mathematical derivation and compute time. In particular, there is no systematic way to derive the best sampling algorithm for a specific end-task. Tackling this issue, we suggest another level of abstraction: a toolkit to end-to-end optimize over all sampling methods to find the one producing user-prescribed properties such as discrepancy or a spectrum that best fit the end-task. A user simply implements the forward losses and the sampling method is found automatically -- without coding or mathematical derivation -- by making use of back-propagation abilities of modern deep learning frameworks. While this optimization takes long, at deployment time the sampling method is quick to execute as iterated unstructured non-linear filtering using radial basis functions (RBFs) to represent high-dimensional kernels. Several important previous methods are special cases of this approach, which we compare to previous work and demonstrate its usefulness in several typical Computer Graphics applications. Finally, we propose sampling patterns with properties not shown before, such as high-dimensional blue noise with projective properties.}, }

Endnote

%0 Report %A Leimkühler, Thomas %A Singh, Gurprit %A Myszkowski, Karol %A Seidel, Hans-Peter %A Ritschel, Tobias %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T End-to-end Sampling Patterns : %G eng %U http://hdl.handle.net/21.11116/0000-0002-1376-4 %U http://arxiv.org/abs/1806.06710 %D 2018 %X Sample patterns have many uses in Computer Graphics, ranging from procedural object placement over Monte Carlo image synthesis to non-photorealistic depiction. Their properties such as discrepancy, spectra, anisotropy, or progressiveness have been analyzed extensively. However, designing methods to produce sampling patterns with certain properties can require substantial hand-crafting effort, both in coding, mathematical derivation and compute time. In particular, there is no systematic way to derive the best sampling algorithm for a specific end-task. Tackling this issue, we suggest another level of abstraction: a toolkit to end-to-end optimize over all sampling methods to find the one producing user-prescribed properties such as discrepancy or a spectrum that best fit the end-task. A user simply implements the forward losses and the sampling method is found automatically -- without coding or mathematical derivation -- by making use of back-propagation abilities of modern deep learning frameworks. While this optimization takes long, at deployment time the sampling method is quick to execute as iterated unstructured non-linear filtering using radial basis functions (RBFs) to represent high-dimensional kernels. Several important previous methods are special cases of this approach, which we compare to previous work and demonstrate its usefulness in several typical Computer Graphics applications. Finally, we propose sampling patterns with properties not shown before, such as high-dimensional blue noise with projective properties. %K Computer Science, Graphics, cs.GR

Leimkühler, T., Kellnhofer, P., Ritschel, T., Myszkowski, K., and Seidel, H.-P. 2018b. Perceptual Real-Time 2D-to-3D Conversion Using Cue Fusion. IEEE Transactions on Visualization and Computer Graphics24, 6.

Links

Export

BibTeX

@article{Leimkuehler2018, TITLE = {Perceptual real-time {2D}-to-{3D} conversion using cue fusion}, AUTHOR = {Leimk{\"u}hler, Thomas and Kellnhofer, Petr and Ritschel, Tobias and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {1077-2626}, DOI = {10.1109/TVCG.2017.2703612}, PUBLISHER = {IEEE Computer Society}, ADDRESS = {New York, NY}, YEAR = {2018}, DATE = {2018}, JOURNAL = {IEEE Transactions on Visualization and Computer Graphics}, VOLUME = {24}, NUMBER = {6}, PAGES = {2037--2050}, }

Endnote

%0 Journal Article %A Leimkühler, Thomas %A Kellnhofer, Petr %A Ritschel, Tobias %A Myszkowski, Karol %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Perceptual Real-Time 2D-to-3D Conversion Using Cue Fusion : %G eng %U http://hdl.handle.net/21.11116/0000-0001-409A-9 %R 10.1109/TVCG.2017.2703612 %7 2018 %D 2018 %J IEEE Transactions on Visualization and Computer Graphics %V 24 %N 6 %& 2037 %P 2037 - 2050 %I IEEE Computer Society %C New York, NY %@ false

Leimkühler, T., Seidel, H.-P., and Ritschel, T. 2018c. Laplacian Kernel Splatting for Efficient Depth-of-field and Motion Blur Synthesis or Reconstruction. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2018)37, 4.

Links

Export

BibTeX

@article{LeimkuehlerSIGGRAPH2018, TITLE = {Laplacian Kernel Splatting for Efficient Depth-of-field and Motion Blur Synthesis or Reconstruction}, AUTHOR = {Leimk{\"u}hler, Thomas and Seidel, Hans-Peter and Ritschel, Tobias}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3197517.3201379}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2018}, DATE = {2018}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {37}, NUMBER = {4}, PAGES = {1--11}, EID = {55}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2018}, }

Endnote

%0 Journal Article %A Leimkühler, Thomas %A Seidel, Hans-Peter %A Ritschel, Tobias %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Laplacian Kernel Splatting for Efficient Depth-of-field and Motion Blur Synthesis or Reconstruction : %G eng %U http://hdl.handle.net/21.11116/0000-0002-0630-1 %R 10.1145/3197517.3201379 %7 2018 %D 2018 %J ACM Transactions on Graphics %V 37 %N 4 %& 1 %P 1 - 11 %Z sequence number: 55 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2018 %O ACM SIGGRAPH 2018 Vancouver, Canada , 12 - 16 August

Golla, B., Seidel, H.-P., and Chen, R. 2018. Piecewise Linear Mapping Optimization Based on the Complex View. Computer Graphics Forum (Proc. Pacific Graphics 2018)37, 7.

Links

Export

BibTeX

@article{Golla_PG2018, TITLE = {Piecewise Linear Mapping Optimization Based on the Complex View}, AUTHOR = {Golla, Bj{\"o}rn and Seidel, Hans-Peter and Chen, Renjie}, LANGUAGE = {eng}, ISSN = {1467-8659}, DOI = {10.1111/cgf.13563}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford, UK}, YEAR = {2018}, DATE = {2018}, JOURNAL = {Computer Graphics Forum (Proc. Pacific Graphics)}, VOLUME = {37}, NUMBER = {7}, PAGES = {233--243}, BOOKTITLE = {The 26th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2018)}, }

Endnote

%0 Journal Article %A Golla, Björn %A Seidel, Hans-Peter %A Chen, Renjie %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Piecewise Linear Mapping Optimization Based on the Complex View : %G eng %U http://hdl.handle.net/21.11116/0000-0002-72CD-7 %R 10.1111/cgf.13563 %7 2018 %D 2018 %J Computer Graphics Forum %V 37 %N 7 %& 233 %P 233 - 243 %I Wiley-Blackwell %C Oxford, UK %@ false %B The 26th Pacific Conference on Computer Graphics and Applications %O Pacific Graphics 2018 PG 2018 Hong Kong, 8-11 October 2018

Beigpour, S., Shekhar, S., Mansouryar, M., Myszkowski, K., and Seidel, H.-P. 2018. Light-Field Appearance Editing Based on Intrinsic Decomposition. Journal of Perceptual Imaging1, 1.

Links

Export

BibTeX

@article{Beigpour2018, TITLE = {Light-Field Appearance Editing Based on Intrinsic Decomposition}, AUTHOR = {Beigpour, Shida and Shekhar, Sumit and Mansouryar, Mohsen and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, DOI = {10.2352/J.Percept.Imaging.2018.1.1.010502}, YEAR = {2018}, JOURNAL = {Journal of Perceptual Imaging}, VOLUME = {1}, NUMBER = {1}, PAGES = {1--15}, EID = {10502}, }

Endnote

%0 Journal Article %A Beigpour, Shida %A Shekhar, Sumit %A Mansouryar, Mohsen %A Myszkowski, Karol %A Seidel, Hans-Peter %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Light-Field Appearance Editing Based on Intrinsic Decomposition : %G eng %U http://hdl.handle.net/21.11116/0000-0001-5F88-C %R 10.2352/J.Percept.Imaging.2018.1.1.010502 %7 2018 %D 2018 %J Journal of Perceptual Imaging %O JPI %V 1 %N 1 %& 1 %P 1 - 15 %Z sequence number: 10502

2017

Zayer, R., Steinberger, M., and Seidel, H.-P. 2017a. Sparse Matrix Assembly on the GPU Through Multiplication Patterns. IEEE High Performance Extreme Computing Conference (HPEC 2017), IEEE.

Links

Export

BibTeX

@inproceedings{Zayer_HPEC2017, TITLE = {Sparse Matrix Assembly on the {GPU} Through Multiplication Patterns}, AUTHOR = {Zayer, Rhaleb and Steinberger, Markus and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-1-5386-3472-1}, DOI = {10.1109/HPEC.2017.8091057}, PUBLISHER = {IEEE}, YEAR = {2017}, DATE = {2017}, BOOKTITLE = {IEEE High Performance Extreme Computing Conference (HPEC 2017)}, PAGES = {1--8}, ADDRESS = {Waltham, MA, USA}, }

Endnote

%0 Conference Proceedings %A Zayer, Rhaleb %A Steinberger, Markus %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Sparse Matrix Assembly on the GPU Through Multiplication Patterns : %G eng %U http://hdl.handle.net/21.11116/0000-0000-3B33-5 %R 10.1109/HPEC.2017.8091057 %D 2017 %B IEEE High Performance Extreme Computing Conference %Z date of event: 2017-09-12 - 2017-09-14 %C Waltham, MA, USA %B IEEE High Performance Extreme Computing Conference %P 1 - 8 %I IEEE %@ 978-1-5386-3472-1

Zayer, R., Steinberger, M., and Seidel, H.-P. 2017b. A GPU-adapted Structure for Unstructured Grids. Computer Graphics Forum (Proc. EUROGRAPHICS 2017)36, 2.

Links

Export

BibTeX

@article{Zayer2017, TITLE = {A {GPU}-adapted Structure for Unstructured Grids}, AUTHOR = {Zayer, Rhaleb and Steinberger, Markus and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.13144}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2017}, DATE = {2017}, JOURNAL = {Computer Graphics Forum (Proc. EUROGRAPHICS)}, VOLUME = {36}, NUMBER = {2}, PAGES = {495--507}, BOOKTITLE = {The European Association for Computer Graphics 38th Annual Conference (EUROGRAPHICS 2017)}, }

Endnote

%0 Journal Article %A Zayer, Rhaleb %A Steinberger, Markus %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T A GPU-adapted Structure for Unstructured Grids : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-5A05-7 %R 10.1111/cgf.13144 %7 2017 %D 2017 %J Computer Graphics Forum %V 36 %N 2 %& 495 %P 495 - 507 %I Wiley-Blackwell %C Oxford %@ false %B The European Association for Computer Graphics 38th Annual Conference %O EUROGRAPHICS 2017 Lyon, France, 24-28 April 2017 EG 2017

Xu, W., Chatterjee, A., Zollhöfer, M., et al. 2017. MonoPerfCap: Human Performance Capture from Monocular Video. http://arxiv.org/abs/1708.02136.

(arXiv: 1708.02136)

Abstract

Links

Export

BibTeX

@online{Xu2017, TITLE = {{MonoPerfCap}: Human Performance Capture from Monocular Video}, AUTHOR = {Xu, Weipeng and Chatterjee, Avishek and Zollh{\"o}fer, Michael and Rhodin, Helge and Mehta, Dushyant and Seidel, Hans-Peter and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1708.02136}, EPRINT = {1708.02136}, EPRINTTYPE = {arXiv}, YEAR = {2017}, ABSTRACT = {We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video. Our approach reconstructs articulated human skeleton motion as well as medium-scale non-rigid surface deformations in general scenes. Human performance capture is a challenging problem due to the large range of articulation, potentially fast motion, and considerable non-rigid deformations, even from multi-view data. Reconstruction from monocular video alone is drastically more challenging, since strong occlusions and the inherent depth ambiguity lead to a highly ill-posed reconstruction problem. We tackle these challenges by a novel approach that employs sparse 2D and 3D human pose detections from a convolutional neural network using a batch-based pose estimation strategy. Joint recovery of per-batch motion allows to resolve the ambiguities of the monocular reconstruction problem based on a low dimensional trajectory subspace. In addition, we propose refinement of the surface geometry based on fully automatically extracted silhouettes to enable medium-scale non-rigid alignment. We demonstrate state-of-the-art performance capture results that enable exciting applications such as video editing and free viewpoint video, previously infeasible from monocular video. Our qualitative and quantitative evaluation demonstrates that our approach significantly outperforms previous monocular methods in terms of accuracy, robustness and scene complexity that can be handled.}, }

Endnote

%0 Report %A Xu, Weipeng %A Chatterjee, Avishek %A Zollhöfer, Michael %A Rhodin, Helge %A Mehta, Dushyant %A Seidel, Hans-Peter %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T MonoPerfCap: Human Performance Capture from Monocular Video : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002E-05C2-9 %U http://arxiv.org/abs/1708.02136 %D 2017 %X We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video. Our approach reconstructs articulated human skeleton motion as well as medium-scale non-rigid surface deformations in general scenes. Human performance capture is a challenging problem due to the large range of articulation, potentially fast motion, and considerable non-rigid deformations, even from multi-view data. Reconstruction from monocular video alone is drastically more challenging, since strong occlusions and the inherent depth ambiguity lead to a highly ill-posed reconstruction problem. We tackle these challenges by a novel approach that employs sparse 2D and 3D human pose detections from a convolutional neural network using a batch-based pose estimation strategy. Joint recovery of per-batch motion allows to resolve the ambiguities of the monocular reconstruction problem based on a low dimensional trajectory subspace. In addition, we propose refinement of the surface geometry based on fully automatically extracted silhouettes to enable medium-scale non-rigid alignment. We demonstrate state-of-the-art performance capture results that enable exciting applications such as video editing and free viewpoint video, previously infeasible from monocular video. Our qualitative and quantitative evaluation demonstrates that our approach significantly outperforms previous monocular methods in terms of accuracy, robustness and scene complexity that can be handled. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Graphics, cs.GR

Wang, Z., Martinez Esturo, J., Seidel, H.-P., and Weinkauf, T. 2017. Stream Line–Based Pattern Search in Flows. Computer Graphics Forum36, 8.

Links

Export

BibTeX

@article{Wang:Esturo:Seidel:Weinkauf2016, TITLE = {Stream Line--Based Pattern Search in Flows}, AUTHOR = {Wang, Zhongjie and Martinez Esturo, Janick and Seidel, Hans-Peter and Weinkauf, Tino}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12990}, PUBLISHER = {Blackwell-Wiley}, ADDRESS = {Oxford}, YEAR = {2017}, DATE = {2017}, JOURNAL = {Computer Graphics Forum}, VOLUME = {36}, NUMBER = {8}, PAGES = {7--18}, }

Endnote

%0 Journal Article %A Wang, Zhongjie %A Martinez Esturo, Janick %A Seidel, Hans-Peter %A Weinkauf, Tino %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Stream Line–Based Pattern Search in Flows : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-4301-A %R 10.1111/cgf.12990 %7 2016 %D 2017 %J Computer Graphics Forum %O Computer Graphics Forum : journal of the European Association for Computer Graphics Comput. Graph. Forum %V 36 %N 8 %& 7 %P 7 - 18 %I Blackwell-Wiley %C Oxford %@ false

Steinberger, M., Zayer, R., and Seidel, H.-P. 2017. Globally Homogeneous, Locally Adaptive Sparse Matrix-Vector Multiplication on the GPU. ICS 2017, International Conference on Supercomputing, ACM.

Links

Export

BibTeX

@inproceedings{SteinbergerICS2017, TITLE = {Globally Homogeneous, Locally Adaptive Sparse Matrix-Vector Multiplication on the {GPU}}, AUTHOR = {Steinberger, Markus and Zayer, Rhaleb and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-1-4503-5020-4}, DOI = {10.1145/3079079.3079086}, PUBLISHER = {ACM}, YEAR = {2017}, DATE = {2017}, BOOKTITLE = {ICS 2017, International Conference on Supercomputing}, PAGES = {1--11}, EID = {13}, ADDRESS = {Chicago, IL, USA}, }

Endnote

%0 Conference Proceedings %A Steinberger, Markus %A Zayer, Rhaleb %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Globally Homogeneous, Locally Adaptive Sparse Matrix-Vector Multiplication on the GPU : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002D-7D71-2 %R 10.1145/3079079.3079086 %D 2017 %B International Conference on Supercomputing %Z date of event: 2017-06-14 - 2017-06-16 %C Chicago, IL, USA %B ICS 2017 %P 1 - 11 %Z sequence number: 13 %I ACM %@ 978-1-4503-5020-4

Saikia, H., Seidel, H.-P., and Weinkauf, T. 2017. Fast Similarity Search in Scalar Fields using Merging Histograms. In: Topological Methods in Data Analysis and Visualization IV. Springer, Cham.

Links

Export

BibTeX

@incollection{Saikia_Seidel_Weinkauf2017, TITLE = {Fast Similarity Search in Scalar Fields using Merging Histograms}, AUTHOR = {Saikia, Himangshu and Seidel, Hans-Peter and Weinkauf, Tino}, LANGUAGE = {eng}, ISBN = {978-3-319-44682-0}, DOI = {10.1007/978-3-319-44684-4_7}, PUBLISHER = {Springer}, ADDRESS = {Cham}, YEAR = {2017}, DATE = {2017}, BOOKTITLE = {Topological Methods in Data Analysis and Visualization IV}, EDITOR = {Carr, Hamish and Garth, Christoph and Weinkauf, Tino}, PAGES = {121--134}, SERIES = {Mathematics and Visualization}, }

Endnote

%0 Book Section %A Saikia, Himangshu %A Seidel, Hans-Peter %A Weinkauf, Tino %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Fast Similarity Search in Scalar Fields using Merging Histograms : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002D-772A-0 %R 10.1007/978-3-319-44684-4_7 %D 2017 %B Topological Methods in Data Analysis and Visualization IV %E Carr, Hamish; Garth, Christoph; Weinkauf, Tino %P 121 - 134 %I Springer %C Cham %@ 978-3-319-44682-0 %S Mathematics and Visualization

Nalbach, O., Seidel, H.-P., and Ritschel, T. 2017a. Practical Capture and Reproduction of Phosphorescent Appearance. Computer Graphics Forum (Proc. EUROGRAPHICS 2017)36, 2.

Links

Export

BibTeX

@article{Nalbach2017, TITLE = {Practical Capture and Reproduction of Phosphorescent Appearance}, AUTHOR = {Nalbach, Oliver and Seidel, Hans-Peter and Ritschel, Tobias}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.13136}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2017}, DATE = {2017}, JOURNAL = {Computer Graphics Forum (Proc. EUROGRAPHICS)}, VOLUME = {36}, NUMBER = {2}, PAGES = {409--420}, BOOKTITLE = {The European Association for Computer Graphics 38th Annual Conference (EUROGRAPHICS 2017)}, }

Endnote

%0 Journal Article %A Nalbach, Oliver %A Seidel, Hans-Peter %A Ritschel, Tobias %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Practical Capture and Reproduction of Phosphorescent Appearance : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-4A53-9 %R 10.1111/cgf.13136 %7 2017 %D 2017 %J Computer Graphics Forum %V 36 %N 2 %& 409 %P 409 - 420 %I Wiley-Blackwell %C Oxford %@ false %B The European Association for Computer Graphics 38th Annual Conference %O EUROGRAPHICS 2017 Lyon, France, 24-28 April 2017 EG 2017

Nalbach, O., Arabadzhiyska, E., Mehta, D., Seidel, H.-P., and Ritschel, T. 2017b. Deep Shading: Convolutional Neural Networks for Screen Space Shading. Computer Graphics Forum (Proc. Eurographics Symposium on Rendering 2017)36, 4.

Links

Export

BibTeX

@article{NalbachEGSR2017, TITLE = {Deep Shading: {C}onvolutional Neural Networks for Screen Space Shading}, AUTHOR = {Nalbach, Oliver and Arabadzhiyska, Elena and Mehta, Dushyant and Seidel, Hans-Peter and Ritschel, Tobias}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.13225}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2017}, DATE = {2017}, JOURNAL = {Computer Graphics Forum (Proc. Eurographics Symposium on Rendering)}, VOLUME = {36}, NUMBER = {4}, PAGES = {65--78}, BOOKTITLE = {Eurographics Symposium on Rendering 2017}, EDITOR = {Zwicker, Matthias and Sander, Pedro}, }

Endnote

%0 Journal Article %A Nalbach, Oliver %A Arabadzhiyska, Elena %A Mehta, Dushyant %A Seidel, Hans-Peter %A Ritschel, Tobias %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Deep Shading: Convolutional Neural Networks for Screen Space Shading : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002D-CD86-6 %R 10.1111/cgf.13225 %7 2017 %D 2017 %J Computer Graphics Forum %V 36 %N 4 %& 65 %P 65 - 78 %I Wiley-Blackwell %C Oxford %@ false %B Eurographics Symposium on Rendering 2017 %O Eurographics Symposium on Rendering 2017 EGSR 2017 Helsinki, Finland, 19-21 June 2017

Mehta, D., Sridhar, S., Sotnychenko, O., et al. 2017a. VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera. http://arxiv.org/abs/1705.01583.

(arXiv: 1705.01583)

Abstract

We present the first real-time method to capture the full global 3D skeletal pose of a human in a stable, temporally consistent manner using a single RGB camera. Our method combines a new convolutional neural network (CNN) based pose regressor with kinematic skeleton fitting. Our novel fully-convolutional pose formulation regresses 2D and 3D joint positions jointly in real time and does not require tightly cropped input frames. A real-time kinematic skeleton fitting method uses the CNN output to yield temporally stable 3D global pose reconstructions on the basis of a coherent kinematic skeleton. This makes our approach the first monocular RGB method usable in real-time applications such as 3D character control---thus far, the only monocular methods for such applications employed specialized RGB-D cameras. Our method's accuracy is quantitatively on par with the best offline 3D monocular RGB pose estimation methods. Our results are qualitatively comparable to, and sometimes better than, results from monocular RGB-D approaches, such as the Kinect. However, we show that our approach is more broadly applicable than RGB-D solutions, i.e. it works for outdoor scenes, community videos, and low quality commodity RGB cameras.

Links

Export

BibTeX

@online{MehtaArXiv2017, TITLE = {{VNect}: Real-time {3D} Human Pose Estimation with a Single {RGB} Camera}, AUTHOR = {Mehta, Dushyant and Sridhar, Srinath and Sotnychenko, Oleksandr and Rhodin, Helge and Shafiei, Mohammad and Seidel, Hans-Peter and Xu, Weipeng and Casas, Dan and Theobalt, Christian}, URL = {http://arxiv.org/abs/1705.01583}, DOI = {10.1145/3072959.3073596}, EPRINT = {1705.01583}, EPRINTTYPE = {arXiv}, YEAR = {2017}, ABSTRACT = {We present the first real-time method to capture the full global 3D skeletal pose of a human in a stable, temporally consistent manner using a single RGB camera. Our method combines a new convolutional neural network (CNN) based pose regressor with kinematic skeleton fitting. Our novel fully-convolutional pose formulation regresses 2D and 3D joint positions jointly in real time and does not require tightly cropped input frames. A real-time kinematic skeleton fitting method uses the CNN output to yield temporally stable 3D global pose reconstructions on the basis of a coherent kinematic skeleton. This makes our approach the first monocular RGB method usable in real-time applications such as 3D character control---thus far, the only monocular methods for such applications employed specialized RGB-D cameras. Our method's accuracy is quantitatively on par with the best offline 3D monocular RGB pose estimation methods. Our results are qualitatively comparable to, and sometimes better than, results from monocular RGB-D approaches, such as the Kinect. However, we show that our approach is more broadly applicable than RGB-D solutions, i.e. it works for outdoor scenes, community videos, and low quality commodity RGB cameras.}, }

Endnote

%0 Report %A Mehta, Dushyant %A Sridhar, Srinath %A Sotnychenko, Oleksandr %A Rhodin, Helge %A Shafiei, Mohammad %A Seidel, Hans-Peter %A Xu, Weipeng %A Casas, Dan %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera : %U http://hdl.handle.net/11858/00-001M-0000-002D-7D78-3 %R 10.1145/3072959.3073596 %U http://arxiv.org/abs/1705.01583 %D 2017 %X We present the first real-time method to capture the full global 3D skeletal pose of a human in a stable, temporally consistent manner using a single RGB camera. Our method combines a new convolutional neural network (CNN) based pose regressor with kinematic skeleton fitting. Our novel fully-convolutional pose formulation regresses 2D and 3D joint positions jointly in real time and does not require tightly cropped input frames. A real-time kinematic skeleton fitting method uses the CNN output to yield temporally stable 3D global pose reconstructions on the basis of a coherent kinematic skeleton. This makes our approach the first monocular RGB method usable in real-time applications such as 3D character control---thus far, the only monocular methods for such applications employed specialized RGB-D cameras. Our method's accuracy is quantitatively on par with the best offline 3D monocular RGB pose estimation methods. Our results are qualitatively comparable to, and sometimes better than, results from monocular RGB-D approaches, such as the Kinect. However, we show that our approach is more broadly applicable than RGB-D solutions, i.e. it works for outdoor scenes, community videos, and low quality commodity RGB cameras. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Graphics, cs.GR

Mehta, D., Sridhar, S., Sotnychenko, O., et al. 2017b. VNect: Real-Time 3D Human Pose Estimation With a Single RGB Camera. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2017)36, 4.

Links

Export

BibTeX

@article{MehtaSIGGRAPH2017, TITLE = {{VNect}: {R}eal-Time {3D} Human Pose Estimation With a Single {RGB} Camera}, AUTHOR = {Mehta, Dushyant and Sridhar, Srinath and Sotnychenko, Oleksandr and Rhodin, Helge and Shafiei, Mohammad and Seidel, Hans-Peter and Xu, Weipeng and Casas, Dan and Theobalt, Christian}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3072959.3073596}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2017}, DATE = {2017}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {36}, NUMBER = {4}, PAGES = {1--14}, EID = {44}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2017}, }

Endnote

%0 Journal Article %A Mehta, Dushyant %A Sridhar, Srinath %A Sotnychenko, Oleksandr %A Rhodin, Helge %A Shafiei, Mohammad %A Seidel, Hans-Peter %A Xu, Weipeng %A Casas, Dan %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T VNect: Real-Time 3D Human Pose Estimation With a Single RGB Camera : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002D-7D95-0 %R 10.1145/3072959.3073596 %7 2017 %D 2017 %J ACM Transactions on Graphics %V 36 %N 4 %& 1 %P 1 - 14 %Z sequence number: 44 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2017 %O ACM SIGGRAPH 2017 Los Angeles, California, 30 July - 3 August

Leimkühler, T., Seidel, H.-P., and Ritschel, T. 2017. Minimal Warping: Planning Incremental Novel-view Synthesis. Computer Graphics Forum (Proc. Eurographics Symposium on Rendering 2017)36, 4.

Links

Export

BibTeX

@article{LeimkuehlerEGSR2017, TITLE = {Minimal Warping: {P}lanning Incremental Novel-view Synthesis}, AUTHOR = {Leimk{\"u}hler, Thomas and Seidel, Hans-Peter and Ritschel, Tobias}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.13219}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2017}, DATE = {2017}, JOURNAL = {Computer Graphics Forum (Proc. Eurographics Symposium on Rendering)}, VOLUME = {36}, NUMBER = {4}, PAGES = {1--14}, BOOKTITLE = {Eurographics Symposium on Rendering 2017}, EDITOR = {Zwicker, Matthias and Sander, Pedro}, }

Endnote

%0 Journal Article %A Leimkühler, Thomas %A Seidel, Hans-Peter %A Ritschel, Tobias %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Minimal Warping: Planning Incremental Novel-view Synthesis : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002D-CD7C-D %R 10.1111/cgf.13219 %7 2017 %D 2017 %J Computer Graphics Forum %V 36 %N 4 %& 1 %P 1 - 14 %I Wiley-Blackwell %C Oxford %@ false %B Eurographics Symposium on Rendering 2017 %O Eurographics Symposium on Rendering 2017 EGSR 2017 Helsinki, Finland, 19-21 June 2017

Kol, T.R., Klehm, O., Seidel, H.-P., and Eisemann, E. 2017. Expressive Single Scattering for Light Shaft Stylization. IEEE Transactions on Visualization and Computer Graphics23, 7.

Links

Export

BibTeX

@article{kol2016expressive, TITLE = {Expressive Single Scattering for Light Shaft Stylization}, AUTHOR = {Kol, Timothy R. and Klehm, Oliver and Seidel, Hans-Peter and Eisemann, Elmar}, LANGUAGE = {eng}, ISSN = {1077-2626}, DOI = {10.1109/TVCG.2016.2554114}, PUBLISHER = {IEEE Computer Society}, ADDRESS = {New York, NY}, YEAR = {2017}, DATE = {2017}, JOURNAL = {IEEE Transactions on Visualization and Computer Graphics}, VOLUME = {23}, NUMBER = {7}, PAGES = {1753--1766}, }

Endnote

%0 Journal Article %A Kol, Timothy R. %A Klehm, Oliver %A Seidel, Hans-Peter %A Eisemann, Elmar %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Expressive Single Scattering for Light Shaft Stylization : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-64E7-2 %R 10.1109/TVCG.2016.2554114 %7 2016-04-14 %D 2017 %J IEEE Transactions on Visualization and Computer Graphics %V 23 %N 7 %& 1753 %P 1753 - 1766 %I IEEE Computer Society %C New York, NY %@ false

Kerbl, B., Kenzel, M., Schmalstieg, D., Seidel, H.-P., and Steinberger, M. 2017. Hierarchical Bucket Queuing for Fine-Grained Priority Scheduling on the GPU. Computer Graphics Forum36, 8.

Links

Export

BibTeX

@article{Seidel_Steinberger2016, TITLE = {Hierarchical Bucket Queuing for Fine-Grained Priority Scheduling on the {GPU}}, AUTHOR = {Kerbl, Bernhard and Kenzel, Michael and Schmalstieg, Dieter and Seidel, Hans-Peter and Steinberger, Markus}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.13075}, PUBLISHER = {Blackwell-Wiley}, ADDRESS = {Oxford}, YEAR = {2017}, DATE = {2017}, JOURNAL = {Computer Graphics Forum}, VOLUME = {36}, NUMBER = {8}, PAGES = {232--246}, }

Endnote

%0 Journal Article %A Kerbl, Bernhard %A Kenzel, Michael %A Schmalstieg, Dieter %A Seidel, Hans-Peter %A Steinberger, Markus %+ External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Hierarchical Bucket Queuing for Fine-Grained Priority Scheduling on the GPU : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-1823-8 %R 10.1111/cgf.13075 %7 2016-12-05 %D 2017 %J Computer Graphics Forum %O Computer Graphics Forum : journal of the European Association for Computer Graphics Comput. Graph. Forum %V 36 %N 8 %& 232 %P 232 - 246 %I Blackwell-Wiley %C Oxford %@ false

Jiang, C., Tang, C., Seidel, H.-P., and Wonka, P. 2017. Design and Volume Optimization of Space Structures. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2017)36, 4.

Links

Export

BibTeX

@article{JiangSIGGRAPH2017, TITLE = {Design and Volume Optimization of Space Structures}, AUTHOR = {Jiang, Caigui and Tang, Chengcheng and Seidel, Hans-Peter and Wonka, Peter}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3072959.3073619}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2017}, DATE = {2017}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {36}, NUMBER = {4}, PAGES = {1--14}, EID = {159}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2017}, }

Endnote

%0 Journal Article %A Jiang, Caigui %A Tang, Chengcheng %A Seidel, Hans-Peter %A Wonka, Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Design and Volume Optimization of Space Structures : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002D-7D8E-2 %R 10.1145/3072959.3073619 %7 2017 %D 2017 %J ACM Transactions on Graphics %V 36 %N 4 %& 1 %P 1 - 14 %Z sequence number: 159 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2017 %O ACM SIGGRAPH 2017 Los Angeles, California, 30 July - 3 August

Haubenwallner, K., Seidel, H.-P., and Steinberger, M. 2017. ShapeGenetics: Using Genetic Algorithms for Procedural Modeling. Computer Graphics Forum (Proc. EUROGRAPHICS 2017)36, 2.

Links

Export

BibTeX

@article{haubenwallner2017shapegenetics, TITLE = {{ShapeGenetics}: {U}sing Genetic Algorithms for Procedural Modeling}, AUTHOR = {Haubenwallner, Karl and Seidel, Hans-Peter and Steinberger, Markus}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.13120}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2017}, DATE = {2017}, JOURNAL = {Computer Graphics Forum (Proc. EUROGRAPHICS)}, VOLUME = {36}, NUMBER = {2}, PAGES = {213--223}, BOOKTITLE = {The European Association for Computer Graphics 38th Annual Conference (EUROGRAPHICS 2017)}, }

Endnote

%0 Journal Article %A Haubenwallner, Karl %A Seidel, Hans-Peter %A Steinberger, Markus %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T ShapeGenetics: Using Genetic Algorithms for Procedural Modeling : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-5C69-8 %R 10.1111/cgf.13120 %7 2017 %D 2017 %J Computer Graphics Forum %V 36 %N 2 %& 213 %P 213 - 223 %I Wiley-Blackwell %C Oxford %@ false %B The European Association for Computer Graphics 38th Annual Conference %O EUROGRAPHICS 2017 Lyon, France, 24-28 April 2017 EG 2017

Derler, A., Zayer, R., Seidel, H.-P., and Steinberger, M. 2017. Dynamic Scheduling for Efficient Hierarchical Sparse Matrix Operations on the GPU. ICS 2017, International Conference on Supercomputing, ACM.

Links

Export

BibTeX

@inproceedings{DerlerICS2017, TITLE = {Dynamic Scheduling for Efficient Hierarchical Sparse Matrix Operations on the {GPU}}, AUTHOR = {Derler, Andreas and Zayer, Rhaleb and Seidel, Hans-Peter and Steinberger, Markus}, LANGUAGE = {eng}, ISBN = {978-1-4503-5020-4}, DOI = {10.1145/3079079.3079085}, PUBLISHER = {ACM}, YEAR = {2017}, DATE = {2017}, BOOKTITLE = {ICS 2017, International Conference on Supercomputing}, EID = {7}, ADDRESS = {Chicago, IL, USA}, }

Endnote

%0 Conference Proceedings %A Derler, Andreas %A Zayer, Rhaleb %A Seidel, Hans-Peter %A Steinberger, Markus %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Dynamic Scheduling for Efficient Hierarchical Sparse Matrix Operations on the GPU : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002D-7D73-D %R 10.1145/3079079.3079085 %D 2017 %B International Conference on Supercomputing %Z date of event: 2017-06-13 - 2017-06-16 %C Chicago, IL, USA %B ICS 2017 %Z sequence number: 7 %I ACM %@ 978-1-4503-5020-4

Arabadzhiyska, E., Tursun, O.T., Myszkowski, K., Seidel, H.-P., and Didyk, P. 2017. Saccade Landing Position Prediction for Gaze-Contingent Rendering. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2017)36, 4.

Links

Export

BibTeX

@article{ArabadzhiyskaSIGGRAPH2017, TITLE = {Saccade Landing Position Prediction for Gaze-Contingent Rendering}, AUTHOR = {Arabadzhiyska, Elena and Tursun, Okan Tarhan and Myszkowski, Karol and Seidel, Hans-Peter and Didyk, Piotr}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3072959.3073642}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2017}, DATE = {2017}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {36}, NUMBER = {4}, PAGES = {1--12}, EID = {50}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2017}, }

Endnote

%0 Journal Article %A Arabadzhiyska, Elena %A Tursun, Okan Tarhan %A Myszkowski, Karol %A Seidel, Hans-Peter %A Didyk, Piotr %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Saccade Landing Position Prediction for Gaze-Contingent Rendering : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002D-7D82-9 %R 10.1145/3072959.3073642 %7 2017 %D 2017 %J ACM Transactions on Graphics %V 36 %N 4 %& 1 %P 1 - 12 %Z sequence number: 50 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2017 %O ACM SIGGRAPH 2017 Los Angeles, California, 30 July - 3 August

Adhikarla, V.K., Vinkler, M., Sumin, D., et al. 2017a. Towards a Quality Metric for Dense Light Fields. http://arxiv.org/abs/1704.07576.

(arXiv: 1704.07576)

Abstract

Light fields become a popular representation of three dimensional scenes, and there is interest in their processing, resampling, and compression. As those operations often result in loss of quality, there is a need to quantify it. In this work, we collect a new dataset of dense reference and distorted light fields as well as the corresponding quality scores which are scaled in perceptual units. The scores were acquired in a subjective experiment using an interactive light-field viewing setup. The dataset contains typical artifacts that occur in light-field processing chain due to light-field reconstruction, multi-view compression, and limitations of automultiscopic displays. We test a number of existing objective quality metrics to determine how well they can predict the quality of light fields. We find that the existing image quality metrics provide good measures of light-field quality, but require dense reference light- fields for optimal performance. For more complex tasks of comparing two distorted light fields, their performance drops significantly, which reveals the need for new, light-field-specific metrics.

Links

Export

BibTeX

@online{AdhikarlaArXiv17, TITLE = {Towards a Quality Metric for Dense Light Fields}, AUTHOR = {Adhikarla, Vamsi Kiran and Vinkler, Marek and Sumin, Denis and Mantiuk, Rafa{\l} K. and Myszkowski, Karol and Seidel, Hans-Peter and Didyk, Piotr}, URL = {http://arxiv.org/abs/1704.07576}, EPRINT = {1704.07576}, EPRINTTYPE = {arXiv}, YEAR = {2017}, ABSTRACT = {Light fields become a popular representation of three dimensional scenes, and there is interest in their processing, resampling, and compression. As those operations often result in loss of quality, there is a need to quantify it. In this work, we collect a new dataset of dense reference and distorted light fields as well as the corresponding quality scores which are scaled in perceptual units. The scores were acquired in a subjective experiment using an interactive light-field viewing setup. The dataset contains typical artifacts that occur in light-field processing chain due to light-field reconstruction, multi-view compression, and limitations of automultiscopic displays. We test a number of existing objective quality metrics to determine how well they can predict the quality of light fields. We find that the existing image quality metrics provide good measures of light-field quality, but require dense reference light- fields for optimal performance. For more complex tasks of comparing two distorted light fields, their performance drops significantly, which reveals the need for new, light-field-specific metrics.}, }

Endnote

%0 Report %A Adhikarla, Vamsi Kiran %A Vinkler, Marek %A Sumin, Denis %A Mantiuk, Rafał K. %A Myszkowski, Karol %A Seidel, Hans-Peter %A Didyk, Piotr %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Towards a Quality Metric for Dense Light Fields : %U http://hdl.handle.net/11858/00-001M-0000-002D-2C2C-1 %U http://arxiv.org/abs/1704.07576 %D 2017 %X Light fields become a popular representation of three dimensional scenes, and there is interest in their processing, resampling, and compression. As those operations often result in loss of quality, there is a need to quantify it. In this work, we collect a new dataset of dense reference and distorted light fields as well as the corresponding quality scores which are scaled in perceptual units. The scores were acquired in a subjective experiment using an interactive light-field viewing setup. The dataset contains typical artifacts that occur in light-field processing chain due to light-field reconstruction, multi-view compression, and limitations of automultiscopic displays. We test a number of existing objective quality metrics to determine how well they can predict the quality of light fields. We find that the existing image quality metrics provide good measures of light-field quality, but require dense reference light- fields for optimal performance. For more complex tasks of comparing two distorted light fields, their performance drops significantly, which reveals the need for new, light-field-specific metrics. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV

Adhikarla, V.K., Vinkler, M., Sumin, D., et al. 2017b. Towards a Quality Metric for Dense Light Fields. 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), IEEE Computer Society.

Links

Export

BibTeX

@inproceedings{Vamsi2017, TITLE = {Towards a Quality Metric for Dense Light Fields}, AUTHOR = {Adhikarla, Vamsi Kiran and Vinkler, Marek and Sumin, Denis and Mantiuk, Rafa{\l} and Myszkowski, Karol and Seidel, Hans-Peter and Didyk, Piotr}, LANGUAGE = {eng}, ISBN = {978-1-5386-0458-8}, DOI = {10.1109/CVPR.2017.396}, PUBLISHER = {IEEE Computer Society}, YEAR = {2017}, DATE = {2017}, BOOKTITLE = {30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)}, PAGES = {3720--3729}, ADDRESS = {Honolulu, HI, USA}, }

Endnote

%0 Conference Proceedings %A Adhikarla, Vamsi Kiran %A Vinkler, Marek %A Sumin, Denis %A Mantiuk, Rafał %A Myszkowski, Karol %A Seidel, Hans-Peter %A Didyk, Piotr %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Towards a Quality Metric for Dense Light Fields : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002D-E476-3 %R 10.1109/CVPR.2017.396 %D 2017 %B 30th IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2017-07-21 - 2017-07-26 %C Honolulu, HI, USA %B 30th IEEE Conference on Computer Vision and Pattern Recognition %P 3720 - 3729 %I IEEE Computer Society %@ 978-1-5386-0458-8

2016

Wang, Z., Seidel, H.-P., and Weinkauf, T. 2016. Multi-field Pattern Matching Based on Sparse Feature Sampling. IEEE Transactions on Visualization and Computer Graphics22, 1.

Links

Export

BibTeX

@article{Wang2015, TITLE = {Multi-field Pattern Matching Based on Sparse Feature Sampling}, AUTHOR = {Wang, Zhongjie and Seidel, Hans-Peter and Weinkauf, Tino}, LANGUAGE = {eng}, ISSN = {1077-2626}, DOI = {10.1109/TVCG.2015.2467292}, PUBLISHER = {IEEE Computer Society}, ADDRESS = {New York, NY}, YEAR = {2016}, DATE = {2016}, JOURNAL = {IEEE Transactions on Visualization and Computer Graphics}, VOLUME = {22}, NUMBER = {1}, PAGES = {807--816}, }

Endnote

%0 Journal Article %A Wang, Zhongjie %A Seidel, Hans-Peter %A Weinkauf, Tino %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Multi-field Pattern Matching Based on Sparse Feature Sampling : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0029-1A76-6 %R 10.1109/TVCG.2015.2467292 %7 2015 %D 2016 %J IEEE Transactions on Visualization and Computer Graphics %V 22 %N 1 %& 807 %P 807 - 816 %I IEEE Computer Society %C New York, NY %@ false

Von Radziewsky, P., Eisemann, E., Seidel, H.-P., and Hildebrandt, K. 2016. Optimized Subspaces for Deformation-based Modeling and Shape Interpolation. Computers and Graphics (Proc. SMI 2016)58.

Links

Export

BibTeX

@article{Radziewsky2016, TITLE = {Optimized Subspaces for Deformation-based Modeling and Shape Interpolation}, AUTHOR = {von Radziewsky, Philipp and Eisemann, Elmar and Seidel, Hans-Peter and Hildebrandt, Klaus}, LANGUAGE = {eng}, ISSN = {0097-8493}, DOI = {10.1016/j.cag.2016.05.016}, PUBLISHER = {Elsevier}, ADDRESS = {Amsterdam}, YEAR = {2016}, DATE = {2016}, JOURNAL = {Computers and Graphics (Proc. SMI)}, VOLUME = {58}, PAGES = {128--138}, BOOKTITLE = {Shape Modeling International 2016 (SMI 2016)}, }

Endnote

%0 Journal Article %A von Radziewsky, Philipp %A Eisemann, Elmar %A Seidel, Hans-Peter %A Hildebrandt, Klaus %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Optimized Subspaces for Deformation-based Modeling and Shape Interpolation : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-0144-0 %R 10.1016/j.cag.2016.05.016 %7 2016 %D 2016 %J Computers and Graphics %V 58 %& 128 %P 128 - 138 %I Elsevier %C Amsterdam %@ false %B Shape Modeling International 2016 %O SMI 2016

Templin, K., Didyk, P., Myszkowski, K., and Seidel, H.-P. 2016. Emulating Displays with Continuously Varying Frame Rates. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2016)35, 4.

Links

Export

BibTeX

@article{TemplinSIGGRAPH2016, TITLE = {Emulating Displays with Continuously Varying Frame Rates}, AUTHOR = {Templin, Krzysztof and Didyk, Piotr and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2897824.2925879}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2016}, DATE = {2016}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {35}, NUMBER = {4}, PAGES = {1--11}, EID = {67}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2016}, }

Endnote

%0 Journal Article %A Templin, Krzysztof %A Didyk, Piotr %A Myszkowski, Karol %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Emulating Displays with Continuously Varying Frame Rates : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-018D-E %R 10.1145/2897824.2925879 %7 2016 %D 2016 %J ACM Transactions on Graphics %V 35 %N 4 %& 1 %P 1 - 11 %Z sequence number: 67 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2016 %O ACM SIGGRAPH 2016 Anaheim, California

Steinberger, M., Derler, A., Zayer, R., and Seidel, H.-P. 2016. How Naive is Naive SpMV on the GPU? IEEE High Performance Extreme Computing Conference (HPEC 2016), IEEE.

Links

Export

BibTeX

@inproceedings{SteinbergerHPEC2016, TITLE = {How naive is naive {SpMV} on the {GPU}?}, AUTHOR = {Steinberger, Markus and Derler, Andreas and Zayer, Rhaleb and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-1-5090-3525-0}, DOI = {10.1109/HPEC.2016.7761634}, PUBLISHER = {IEEE}, YEAR = {2016}, DATE = {2016}, BOOKTITLE = {IEEE High Performance Extreme Computing Conference (HPEC 2016)}, PAGES = {1--8}, ADDRESS = {Waltham, MA, USA}, }

Endnote

%0 Conference Proceedings %A Steinberger, Markus %A Derler, Andreas %A Zayer, Rhaleb %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T How Naive is Naive SpMV on the GPU? : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-98A5-F %R 10.1109/HPEC.2016.7761634 %D 2016 %B IEEE High Performance Extreme Computing Conference %Z date of event: 2016-09-13 - 2016-09-15 %C Waltham, MA, USA %B IEEE High Performance Extreme Computing Conference %P 1 - 8 %I IEEE %@ 978-1-5090-3525-0

Serrano, A., Gutierrez, D., Myszkowski, K., Seidel, H.-P., and Masia, B. 2016a. Intuitive Editing of Material Appearance. ACM SIGGRAPH 2016 Posters.

Links

Export

BibTeX

@inproceedings{SerranoSIGGRAPH2016, TITLE = {Intuitive Editing of Material Appearance}, AUTHOR = {Serrano, Ana and Gutierrez, Diego and Myszkowski, Karol and Seidel, Hans-Peter and Masia, Belen}, LANGUAGE = {eng}, ISBN = {978-1-4503-4371-8}, DOI = {10.1145/2945078.2945141}, PUBLISHER = {ACM}, YEAR = {2016}, DATE = {2016}, BOOKTITLE = {ACM SIGGRAPH 2016 Posters}, PAGES = {1--2}, EID = {63}, ADDRESS = {Anaheim, CA, USA}, }

Endnote

%0 Generic %A Serrano, Ana %A Gutierrez, Diego %A Myszkowski, Karol %A Seidel, Hans-Peter %A Masia, Belen %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Intuitive Editing of Material Appearance : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-0170-C %R 10.1145/2945078.2945141 %D 2016 %Z name of event: 43rd International Conference and Exhibition on Computer Graphics & Interactive Techniques %Z date of event: 2016-07-24 - 2016-07-28 %Z place of event: Anaheim, CA, USA %B ACM SIGGRAPH 2016 Posters %P 1 - 2 %Z sequence number: 63 %@ 978-1-4503-4371-8

Serrano, A., Gutierrez, D., Myszkowski, K., Seidel, H.-P., and Masia, B. 2016b. An Intuitive Control Space for Material Appearance. ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia 2016)35, 6.

Links

Export

BibTeX

@article{Serrano_MaterialAppearance_2016, TITLE = {An Intuitive Control Space for Material Appearance}, AUTHOR = {Serrano, Ana and Gutierrez, Diego and Myszkowski, Karol and Seidel, Hans-Peter and Masia, Belen}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2980179.2980242}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2016}, DATE = {2016}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia)}, VOLUME = {35}, NUMBER = {6}, EID = {186}, BOOKTITLE = {Proceedings of ACM SIGGRAPH Asia 2016}, }

Endnote

%0 Journal Article %A Serrano, Ana %A Gutierrez, Diego %A Myszkowski, Karol %A Seidel, Hans-Peter %A Masia, Belen %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T An Intuitive Control Space for Material Appearance : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-82B8-9 %R 10.1145/2980179.2980242 %7 2016 %D 2016 %J ACM Transactions on Graphics %O TOG %V 35 %N 6 %Z sequence number: 186 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH Asia 2016 %O ACM SIGGRAPH Asia 2016

Robertini, N., Casas, D., Rhodin, H., Seidel, H.-P., and Theobalt, C. 2016. Model-Based Outdoor Performance Capture. Fourth International Conference on 3D Vision, IEEE Computer Society.

Links

Export

BibTeX

@inproceedings{Robertini:2016, TITLE = {Model-Based Outdoor Performance Capture}, AUTHOR = {Robertini, Nadia and Casas, Dan and Rhodin, Helge and Seidel, Hans-Peter and Theobalt, Christian}, LANGUAGE = {eng}, ISBN = {978-1-5090-5407-7}, URL = {http://gvv.mpi-inf.mpg.de/projects/OutdoorPerfcap/}, DOI = {10.1109/3DV.2016.25}, PUBLISHER = {IEEE Computer Society}, YEAR = {2016}, DATE = {2016}, BOOKTITLE = {Fourth International Conference on 3D Vision}, PAGES = {166--175}, ADDRESS = {Stanford, CA, USA}, }

Endnote

%0 Conference Proceedings %A Robertini, Nadia %A Casas, Dan %A Rhodin, Helge %A Seidel, Hans-Peter %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Model-Based Outdoor Performance Capture : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-4A6D-2 %R 10.1109/3DV.2016.25 %U http://gvv.mpi-inf.mpg.de/projects/OutdoorPerfcap/ %D 2016 %B Fourth International Conference on 3D Vision %Z date of event: 2016-10-25 - 2016-10-28 %C Stanford, CA, USA %B Fourth International Conference on 3D Vision %P 166 - 175 %I IEEE Computer Society %@ 978-1-5090-5407-7

Rhodin, H., Robertini, N., Richardt, C., Seidel, H.-P., and Theobalt, C. 2016a. A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation. http://arxiv.org/abs/1602.03725.

(arXiv: 1602.03725)

Abstract

Generative reconstruction methods compute the 3D configuration (such as pose and/or geometry) of a shape by optimizing the overlap of the projected 3D shape model with images. Proper handling of occlusions is a big challenge, since the visibility function that indicates if a surface point is seen from a camera can often not be formulated in closed form, and is in general discrete and non-differentiable at occlusion boundaries. We present a new scene representation that enables an analytically differentiable closed-form formulation of surface visibility. In contrast to previous methods, this yields smooth, analytically differentiable, and efficient to optimize pose similarity energies with rigorous occlusion handling, fewer local minima, and experimentally verified improved convergence of numerical optimization. The underlying idea is a new image formation model that represents opaque objects by a translucent medium with a smooth Gaussian density distribution which turns visibility into a smooth phenomenon. We demonstrate the advantages of our versatile scene model in several generative pose estimation problems, namely marker-less multi-object pose estimation, marker-less human motion capture with few cameras, and image-based 3D geometry estimation.

Links

Export

BibTeX

@online{Rhodin2016arXiv1602.03725, TITLE = {A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation}, AUTHOR = {Rhodin, Helge and Robertini, Nadia and Richardt, Christian and Seidel, Hans-Peter and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1602.03725}, EPRINT = {1602.03725}, EPRINTTYPE = {arXiv}, YEAR = {2016}, ABSTRACT = {Generative reconstruction methods compute the 3D configuration (such as pose and/or geometry) of a shape by optimizing the overlap of the projected 3D shape model with images. Proper handling of occlusions is a big challenge, since the visibility function that indicates if a surface point is seen from a camera can often not be formulated in closed form, and is in general discrete and non-differentiable at occlusion boundaries. We present a new scene representation that enables an analytically differentiable closed-form formulation of surface visibility. In contrast to previous methods, this yields smooth, analytically differentiable, and efficient to optimize pose similarity energies with rigorous occlusion handling, fewer local minima, and experimentally verified improved convergence of numerical optimization. The underlying idea is a new image formation model that represents opaque objects by a translucent medium with a smooth Gaussian density distribution which turns visibility into a smooth phenomenon. We demonstrate the advantages of our versatile scene model in several generative pose estimation problems, namely marker-less multi-object pose estimation, marker-less human motion capture with few cameras, and image-based 3D geometry estimation.}, }

Endnote

%0 Report %A Rhodin, Helge %A Robertini, Nadia %A Richardt, Christian %A Seidel, Hans-Peter %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Intel Visual Computing Institute Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-9875-C %U http://arxiv.org/abs/1602.03725 %D 2016 %X Generative reconstruction methods compute the 3D configuration (such as pose and/or geometry) of a shape by optimizing the overlap of the projected 3D shape model with images. Proper handling of occlusions is a big challenge, since the visibility function that indicates if a surface point is seen from a camera can often not be formulated in closed form, and is in general discrete and non-differentiable at occlusion boundaries. We present a new scene representation that enables an analytically differentiable closed-form formulation of surface visibility. In contrast to previous methods, this yields smooth, analytically differentiable, and efficient to optimize pose similarity energies with rigorous occlusion handling, fewer local minima, and experimentally verified improved convergence of numerical optimization. The underlying idea is a new image formation model that represents opaque objects by a translucent medium with a smooth Gaussian density distribution which turns visibility into a smooth phenomenon. We demonstrate the advantages of our versatile scene model in several generative pose estimation problems, namely marker-less multi-object pose estimation, marker-less human motion capture with few cameras, and image-based 3D geometry estimation. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV

Rhodin, H., Robertini, N., Casas, D., Richardt, C., Seidel, H.-P., and Theobalt, C. 2016b. General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues. http://arxiv.org/abs/1607.08659.

(arXiv: 1607.08659)

Abstract

Markerless motion capture algorithms require a 3D body with properly personalized skeleton dimension and/or body shape and appearance to successfully track a person. Unfortunately, many tracking methods consider model personalization a different problem and use manual or semi-automatic model initialization, which greatly reduces applicability. In this paper, we propose a fully automatic algorithm that jointly creates a rigged actor model commonly used for animation - skeleton, volumetric shape, appearance, and optionally a body surface - and estimates the actor's motion from multi-view video input only. The approach is rigorously designed to work on footage of general outdoor scenes recorded with very few cameras and without background subtraction. Our method uses a new image formation model with analytic visibility and analytically differentiable alignment energy. For reconstruction, 3D body shape is approximated as Gaussian density field. For pose and shape estimation, we minimize a new edge-based alignment energy inspired by volume raycasting in an absorbing medium. We further propose a new statistical human body model that represents the body surface, volumetric Gaussian density, as well as variability in skeleton shape. Given any multi-view sequence, our method jointly optimizes the pose and shape parameters of this model fully automatically in a spatiotemporal way.

Links

Export

BibTeX

@online{Rhodin2016arXiv1607.08659, TITLE = {General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues}, AUTHOR = {Rhodin, Helge and Robertini, Nadia and Casas, Dan and Richardt, Christian and Seidel, Hans-Peter and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1607.08659}, EPRINT = {1607.08659}, EPRINTTYPE = {arXiv}, YEAR = {2016}, ABSTRACT = {Markerless motion capture algorithms require a 3D body with properly personalized skeleton dimension and/or body shape and appearance to successfully track a person. Unfortunately, many tracking methods consider model personalization a different problem and use manual or semi-automatic model initialization, which greatly reduces applicability. In this paper, we propose a fully automatic algorithm that jointly creates a rigged actor model commonly used for animation -- skeleton, volumetric shape, appearance, and optionally a body surface -- and estimates the actor's motion from multi-view video input only. The approach is rigorously designed to work on footage of general outdoor scenes recorded with very few cameras and without background subtraction. Our method uses a new image formation model with analytic visibility and analytically differentiable alignment energy. For reconstruction, 3D body shape is approximated as Gaussian density field. For pose and shape estimation, we minimize a new edge-based alignment energy inspired by volume raycasting in an absorbing medium. We further propose a new statistical human body model that represents the body surface, volumetric Gaussian density, as well as variability in skeleton shape. Given any multi-view sequence, our method jointly optimizes the pose and shape parameters of this model fully automatically in a spatiotemporal way.}, }

Endnote

%0 Report %A Rhodin, Helge %A Robertini, Nadia %A Casas, Dan %A Richardt, Christian %A Seidel, Hans-Peter %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Intel Visual Computing Institute Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-9883-C %U http://arxiv.org/abs/1607.08659 %D 2016 %X Markerless motion capture algorithms require a 3D body with properly personalized skeleton dimension and/or body shape and appearance to successfully track a person. Unfortunately, many tracking methods consider model personalization a different problem and use manual or semi-automatic model initialization, which greatly reduces applicability. In this paper, we propose a fully automatic algorithm that jointly creates a rigged actor model commonly used for animation - skeleton, volumetric shape, appearance, and optionally a body surface - and estimates the actor's motion from multi-view video input only. The approach is rigorously designed to work on footage of general outdoor scenes recorded with very few cameras and without background subtraction. Our method uses a new image formation model with analytic visibility and analytically differentiable alignment energy. For reconstruction, 3D body shape is approximated as Gaussian density field. For pose and shape estimation, we minimize a new edge-based alignment energy inspired by volume raycasting in an absorbing medium. We further propose a new statistical human body model that represents the body surface, volumetric Gaussian density, as well as variability in skeleton shape. Given any multi-view sequence, our method jointly optimizes the pose and shape parameters of this model fully automatically in a spatiotemporal way. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV

Rhodin, H., Richardt, C., Casas, D., et al. 2016c. EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras (Extended Abstract). http://arxiv.org/abs/1701.00142.

(arXiv: 1701.00142)

Abstract

Marker-based and marker-less optical skeletal motion-capture methods use an outside-in arrangement of cameras placed around a scene, with viewpoints converging on the center. They often create discomfort by possibly needed marker suits, and their recording volume is severely restricted and often constrained to indoor scenes with controlled backgrounds. We therefore propose a new method for real-time, marker-less and egocentric motion capture which estimates the full-body skeleton pose from a lightweight stereo pair of fisheye cameras that are attached to a helmet or virtual-reality headset. It combines the strength of a new generative pose estimation framework for fisheye views with a ConvNet-based body-part detector trained on a new automatically annotated and augmented dataset. Our inside-in method captures full-body motion in general indoor and outdoor scenes, and also crowded scenes.

Links

Export

BibTeX

@online{DBLP:journals/corr/RhodinRCISSST17, TITLE = {{EgoCap}: Egocentric Marker-less Motion Capture with Two Fisheye Cameras (Extended Abstract)}, AUTHOR = {Rhodin, Helge and Richardt, Christian and Casas, Dan and Insafutdinov, Eldar and Shafiei, Mohammad and Seidel, Hans-Peter and Schiele, Bernt and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1701.00142}, EPRINT = {1701.00142}, EPRINTTYPE = {arXiv}, YEAR = {2016}, ABSTRACT = {Marker-based and marker-less optical skeletal motion-capture methods use an outside-in arrangement of cameras placed around a scene, with viewpoints converging on the center. They often create discomfort by possibly needed marker suits, and their recording volume is severely restricted and often constrained to indoor scenes with controlled backgrounds. We therefore propose a new method for real-time, marker-less and egocentric motion capture which estimates the full-body skeleton pose from a lightweight stereo pair of fisheye cameras that are attached to a helmet or virtual-reality headset. It combines the strength of a new generative pose estimation framework for fisheye views with a ConvNet-based body-part detector trained on a new automatically annotated and augmented dataset. Our inside-in method captures full-body motion in general indoor and outdoor scenes, and also crowded scenes.}, }

Endnote

%0 Report %A Rhodin, Helge %A Richardt, Christian %A Casas, Dan %A Insafutdinov, Eldar %A Shafiei, Mohammad %A Seidel, Hans-Peter %A Schiele, Bernt %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras (Extended Abstract) : %G eng %U http://hdl.handle.net/21.11116/0000-0000-3B3D-B %U http://arxiv.org/abs/1701.00142 %D 2016 %X Marker-based and marker-less optical skeletal motion-capture methods use an outside-in arrangement of cameras placed around a scene, with viewpoints converging on the center. They often create discomfort by possibly needed marker suits, and their recording volume is severely restricted and often constrained to indoor scenes with controlled backgrounds. We therefore propose a new method for real-time, marker-less and egocentric motion capture which estimates the full-body skeleton pose from a lightweight stereo pair of fisheye cameras that are attached to a helmet or virtual-reality headset. It combines the strength of a new generative pose estimation framework for fisheye views with a ConvNet-based body-part detector trained on a new automatically annotated and augmented dataset. Our inside-in method captures full-body motion in general indoor and outdoor scenes, and also crowded scenes. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV

Rhodin, H., Richardt, C., Casas, D., et al. 2016d. EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras. ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia 2016)35, 6.

Links

Export

BibTeX

@article{Rhodin2016SGA, TITLE = {{EgoCap}: {E}gocentric Marker-less Motion Capture with Two Fisheye Cameras}, AUTHOR = {Rhodin, Helge and Richardt, Christian and Casas, Dan and Insafutdinov, Eldar and Shafiei, Mohammad and Seidel, Hans-Peter and Schiele, Bernt and Theobalt, Christian}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2980179.2980235}, PUBLISHER = {Association for Computing Machinery}, ADDRESS = {New York, NY}, YEAR = {2016}, DATE = {2016}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia)}, VOLUME = {35}, NUMBER = {6}, PAGES = {1--11}, EID = {162}, BOOKTITLE = {Proceedings of ACM SIGGRAPH Asia 2016}, }

Endnote

%0 Journal Article %A Rhodin, Helge %A Richardt, Christian %A Casas, Dan %A Insafutdinov, Eldar %A Shafiei, Mohammad %A Seidel, Hans-Peter %A Schiele, Bernt %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Intel Visual Computing Institute University of Bath Computer Graphics, MPI for Informatics, Max Planck Society Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-8321-6 %R 10.1145/2980179.2980235 %7 2016 %D 2016 %J ACM Transactions on Graphics %V 35 %N 6 %& 1 %P 1 - 11 %Z sequence number: 162 %I Association for Computing Machinery %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH Asia 2016 %O ACM SIGGRAPH Asia 2016

Rhodin, H., Robertini, N., Casas, D., Richardt, C., Seidel, H.-P., and Theobalt, C. 2016e. General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues. Computer Vision -- ECCV 2016, Springer.

Links

Export

BibTeX

@inproceedings{RhodinECCV2016, TITLE = {General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues}, AUTHOR = {Rhodin, Helge and Robertini, Nadia and Casas, Dan and Richardt, Christian and Seidel, Hans-Peter and Theobalt, Christian}, LANGUAGE = {eng}, ISBN = {978-3-319-46453-4}, DOI = {10.1007/978-3-319-46454-1_31}, PUBLISHER = {Springer}, YEAR = {2016}, DATE = {2016}, BOOKTITLE = {Computer Vision -- ECCV 2016}, DEBUG = {author: Leibe, Bastian; author: Matas, Jiri; author: Sebe, Nicu; author: Welling, Max}, PAGES = {509--526}, SERIES = {Lecture Notes in Computer Science}, VOLUME = {9909}, ADDRESS = {Amsterdam, The Netherlands}, }

Endnote

%0 Conference Proceedings %A Rhodin, Helge %A Robertini, Nadia %A Casas, Dan %A Richardt, Christian %A Seidel, Hans-Peter %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Intel Visual Computing Institute Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-986D-F %R 10.1007/978-3-319-46454-1_31 %D 2016 %B 14th European Conference on Computer Vision %Z date of event: 2016-10-11 - 2016-10-14 %C Amsterdam, The Netherlands %B Computer Vision -- ECCV 2016 %E Leibe, Bastian; Matas, Jiri; Sebe, Nicu; Welling, Max %P 509 - 526 %I Springer %@ 978-3-319-46453-4 %B Lecture Notes in Computer Science %N 9909 %U https://rdcu.be/dLgG6

Reinert, B., Kopf, J., Ritschel, T., Cuervo, E., Chu, D., and Seidel, H.-P. 2016a. Proxy-guided Image-based Rendering for Mobile Devices. Computer Graphics Forum (Proc. Pacific Graphics 2016)35, 7.

Links

Export

BibTeX

@article{ReinertPG2016, TITLE = {Proxy-guided Image-based Rendering for Mobile Devices}, AUTHOR = {Reinert, Bernhard and Kopf, Johannes and Ritschel, Tobias and Cuervo, Eduardo and Chu, David and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.13032}, PUBLISHER = {Blackwell-Wiley}, ADDRESS = {Oxford}, YEAR = {2016}, DATE = {2016}, JOURNAL = {Computer Graphics Forum (Proc. Pacific Graphics)}, VOLUME = {35}, NUMBER = {7}, PAGES = {353--362}, BOOKTITLE = {The 24th Pacific Conference on Computer Graphics and Applications Short Papers Proceedings (Pacific Graphics 2016)}, }

Endnote

%0 Journal Article %A Reinert, Bernhard %A Kopf, Johannes %A Ritschel, Tobias %A Cuervo, Eduardo %A Chu, David %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Proxy-guided Image-based Rendering for Mobile Devices : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-2DD8-7 %R 10.1111/cgf.13032 %7 2016 %D 2016 %J Computer Graphics Forum %V 35 %N 7 %& 353 %P 353 - 362 %I Blackwell-Wiley %C Oxford %@ false %B The 24th Pacific Conference on Computer Graphics and Applications Short Papers Proceedings %O Pacific Graphics 2016 PG 2016

Reinert, B., Ritschel, T., Seidel, H.-P., and Georgiev, I. 2016b. Projective Blue-Noise Sampling. Computer Graphics Forum35, 1.

Links

Export

BibTeX

@article{ReinertCGF2016, TITLE = {Projective Blue-Noise Sampling}, AUTHOR = {Reinert, Bernhard and Ritschel, Tobias and Seidel, Hans-Peter and Georgiev, Iliyan}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12725}, PUBLISHER = {Wiley}, ADDRESS = {Chichester}, YEAR = {2016}, DATE = {2016}, JOURNAL = {Computer Graphics Forum}, VOLUME = {35}, NUMBER = {1}, PAGES = {285--295}, }

Endnote

%0 Journal Article %A Reinert, Bernhard %A Ritschel, Tobias %A Seidel, Hans-Peter %A Georgiev, Iliyan %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Projective Blue-Noise Sampling : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002A-1A31-D %R 10.1111/cgf.12725 %7 2016 %D 2016 %J Computer Graphics Forum %V 35 %N 1 %& 285 %P 285 - 295 %I Wiley %C Chichester %@ false

Reinert, B., Ritschel, T., and Seidel, H.-P. 2016c. Animated 3D Creatures from Single-view Video by Skeletal Sketching. Graphics Interface 2016, 42nd Graphics Interface Conference, Canadian Information Processing Society.

Links

Export

BibTeX

@inproceedings{Reinert:2016:AnimatedCreatures, TITLE = {Animated {3D} Creatures from Single-view Video by Skeletal Sketching}, AUTHOR = {Reinert, Bernhard and Ritschel, Tobias and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-0-9947868-1-4}, DOI = {10.20380/GI2016.17}, PUBLISHER = {Canadian Information Processing Society}, YEAR = {2016}, DATE = {2016}, BOOKTITLE = {Graphics Interface 2016, 42nd Graphics Interface Conference}, EDITOR = {Popa, Tiberiu and Moffatt, Karyn}, PAGES = {133--143}, ADDRESS = {Victoria, BC, Canada}, }

Endnote

%0 Conference Proceedings %A Reinert, Bernhard %A Ritschel, Tobias %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Animated 3D Creatures from Single-view Video by Skeletal Sketching : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-64EC-7 %R 10.20380/GI2016.17 %D 2016 %B 42nd Graphics Interface Conference %Z date of event: 2016-06-01 - 2016-06-03 %C Victoria, BC, Canada %B Graphics Interface 2016 %E Popa, Tiberiu; Moffatt, Karyn %P 133 - 143 %I Canadian Information Processing Society %@ 978-0-9947868-1-4

Nalbach, O., Arabadzhiyska, E., Mehta, D., Seidel, H.-P., and Ritschel, T. 2016. Deep Shading: Convolutional Neural Networks for Screen-Space Shading. http://arxiv.org/abs/1603.06078.

(arXiv: 1603.06078)

Abstract

In computer vision, Convolutional Neural Networks (CNNs) have recently achieved new levels of performance for several inverse problems where RGB pixel appearance is mapped to attributes such as positions, normals or reflectance. In computer graphics, screen-space shading has recently increased the visual quality in interactive image synthesis, where per-pixel attributes such as positions, normals or reflectance of a virtual 3D scene are converted into RGB pixel appearance, enabling effects like ambient occlusion, indirect light, scattering, depth-of-field, motion blur, or anti-aliasing. In this paper we consider the diagonal problem: synthesizing appearance from given per-pixel attributes using a CNN. The resulting Deep Shading simulates all screen-space effects as well as arbitrary combinations thereof at competitive quality and speed while not being programmed by human experts but learned from example images.

Links

Export

BibTeX

@online{NalbacharXiv2016, TITLE = {Deep Shading: Convolutional Neural Networks for Screen-Space Shading}, AUTHOR = {Nalbach, Oliver and Arabadzhiyska, Elena and Mehta, Dushyant and Seidel, Hans-Peter and Ritschel, Tobias}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1603.06078}, EPRINT = {1603.06078}, EPRINTTYPE = {arXiv}, YEAR = {2016}, ABSTRACT = {In computer vision, Convolutional Neural Networks (CNNs) have recently achieved new levels of performance for several inverse problems where RGB pixel appearance is mapped to attributes such as positions, normals or reflectance. In computer graphics, screen-space shading has recently increased the visual quality in interactive image synthesis, where per-pixel attributes such as positions, normals or reflectance of a virtual 3D scene are converted into RGB pixel appearance, enabling effects like ambient occlusion, indirect light, scattering, depth-of-field, motion blur, or anti-aliasing. In this paper we consider the diagonal problem: synthesizing appearance from given per-pixel attributes using a CNN. The resulting Deep Shading simulates all screen-space effects as well as arbitrary combinations thereof at competitive quality and speed while not being programmed by human experts but learned from example images.}, }

Endnote

%0 Report %A Nalbach, Oliver %A Arabadzhiyska, Elena %A Mehta, Dushyant %A Seidel, Hans-Peter %A Ritschel, Tobias %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Deep Shading: Convolutional Neural Networks for Screen-Space Shading : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-0174-4 %U http://arxiv.org/abs/1603.06078 %D 2016 %X In computer vision, Convolutional Neural Networks (CNNs) have recently achieved new levels of performance for several inverse problems where RGB pixel appearance is mapped to attributes such as positions, normals or reflectance. In computer graphics, screen-space shading has recently increased the visual quality in interactive image synthesis, where per-pixel attributes such as positions, normals or reflectance of a virtual 3D scene are converted into RGB pixel appearance, enabling effects like ambient occlusion, indirect light, scattering, depth-of-field, motion blur, or anti-aliasing. In this paper we consider the diagonal problem: synthesizing appearance from given per-pixel attributes using a CNN. The resulting Deep Shading simulates all screen-space effects as well as arbitrary combinations thereof at competitive quality and speed while not being programmed by human experts but learned from example images. %K Computer Science, Graphics, cs.GR,Computer Science, Learning, cs.LG

Leimkühler, T., Kellnhofer, P., Ritschel, T., Myszkowski, K., and Seidel, H.-P. 2016. Perceptual Real-Time 2D-to-3D Conversion Using Cue Fusion. Graphics Interface 2016, 42nd Graphics Interface Conference, Canadian Information Processing Society.

(Best Student Paper Award)

Links

Export

BibTeX

@inproceedings{LeimkuehlerGI2016, TITLE = {Perceptual real-time {2D}-to-{3D} conversion using cue fusion}, AUTHOR = {Leimk{\"u}hler, Thomas and Kellnhofer, Petr and Ritschel, Tobias and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-0-9947868-1-4}, DOI = {10.20380/GI2016.02}, PUBLISHER = {Canadian Information Processing Society}, YEAR = {2016}, DATE = {2016}, BOOKTITLE = {Graphics Interface 2016, 42nd Graphics Interface Conference}, EDITOR = {Popa, Tiberiu and Moffatt, Karyn}, PAGES = {5--12}, ADDRESS = {Victoria, Canada}, }

Endnote

%0 Conference Proceedings %A Leimkühler, Thomas %A Kellnhofer, Petr %A Ritschel, Tobias %A Myszkowski, Karol %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Perceptual Real-Time 2D-to-3D Conversion Using Cue Fusion : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-823D-1 %R 10.20380/GI2016.02 %D 2016 %B 42nd Graphics Interface Conference %Z date of event: 2016-06-01 - 2016-06-03 %C Victoria, Canada %B Graphics Interface 2016 %E Popa, Tiberiu; Moffatt, Karyn %P 5 - 12 %I Canadian Information Processing Society %@ 978-0-9947868-1-4

Kellnhofer, P., Didyk, P., Myszkowski, K., Hefeeda, M.M., Seidel, H.-P., and Matusik, W. 2016a. GazeStereo3D: Seamless Disparity Manipulations. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2016)35, 4.

Links

Export

BibTeX

@article{KellnhoferSIGGRAPH2016, TITLE = {{GazeStereo3D}: {S}eamless Disparity Manipulations}, AUTHOR = {Kellnhofer, Petr and Didyk, Piotr and Myszkowski, Karol and Hefeeda, Mohamed M. and Seidel, Hans-Peter and Matusik, Wojciech}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2897824.2925866}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2016}, DATE = {2016}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {35}, NUMBER = {4}, PAGES = {1--13}, EID = {68}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2016}, }

Endnote

%0 Journal Article %A Kellnhofer, Petr %A Didyk, Piotr %A Myszkowski, Karol %A Hefeeda, Mohamed M. %A Seidel, Hans-Peter %A Matusik, Wojciech %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T GazeStereo3D: Seamless Disparity Manipulations : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-0190-4 %R 10.1145/2897824.2925866 %7 2016 %D 2016 %J ACM Transactions on Graphics %V 35 %N 4 %& 1 %P 1 - 13 %Z sequence number: 68 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2016 %O ACM SIGGRAPH 2016 Anaheim, California

Kellnhofer, P., Ritschel, T., Myszkowski, K., and Seidel, H.-P. 2016b. Transformation-aware Perceptual Image Metric. Journal of Electronic Imaging25, 5.

Links

Export

BibTeX

@article{Kellnhofer2016jei, TITLE = {Transformation-aware Perceptual Image Metric}, AUTHOR = {Kellnhofer, Petr and Ritschel, Tobias and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {1017-9909}, DOI = {10.1117/1.JEI.25.5.053014}, PUBLISHER = {SPIE}, ADDRESS = {Bellingham, WA}, YEAR = {2016}, DATE = {2016}, JOURNAL = {Journal of Electronic Imaging}, VOLUME = {25}, NUMBER = {5}, PAGES = {1--16}, EID = {053014}, }

Endnote

%0 Journal Article %A Kellnhofer, Petr %A Ritschel, Tobias %A Myszkowski, Karol %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Transformation-aware Perceptual Image Metric : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-82B3-4 %R 10.1117/1.JEI.25.5.053014 %7 2016 %D 2016 %J Journal of Electronic Imaging %V 25 %N 5 %& 1 %P 1 - 16 %Z sequence number: 053014 %I SPIE %C Bellingham, WA %@ false

Kellnhofer, P., Didyk, P., Ritschel, T., Masia, B., Myszkowski, K., and Seidel, H.-P. 2016c. Motion Parallax in Stereo 3D: Model and Applications. ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia 2016)35, 6.

Links

Export

BibTeX

@article{Kellnhofer2016SGA, TITLE = {Motion Parallax in Stereo {3D}: {M}odel and Applications}, AUTHOR = {Kellnhofer, Petr and Didyk, Piotr and Ritschel, Tobias and Masia, Belen and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2980179.2980230}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2016}, DATE = {2016}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia)}, VOLUME = {35}, NUMBER = {6}, PAGES = {1--12}, EID = {176}, BOOKTITLE = {Proceedings of ACM SIGGRAPH Asia 2016}, }

Endnote

%0 Journal Article %A Kellnhofer, Petr %A Didyk, Piotr %A Ritschel, Tobias %A Masia, Belen %A Myszkowski, Karol %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Motion Parallax in Stereo 3D: Model and Applications : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-82B6-D %R 10.1145/2980179.2980230 %7 2016 %D 2016 %J ACM Transactions on Graphics %O TOG %V 35 %N 6 %& 1 %P 1 - 12 %Z sequence number: 176 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH Asia 2016 %O ACM SIGGRAPH Asia 2016

Gryaditskaya, Y., Masia, B., Didyk, P., Myszkowski, K., and Seidel, H.-P. 2016. Gloss Editing in Light Fields. VMV 2016 Vision, Modeling and Visualization, Eurographics Association.

Links

Export

BibTeX

@inproceedings{jgryadit2016, TITLE = {Gloss Editing in Light Fields}, AUTHOR = {Gryaditskaya, Yulia and Masia, Belen and Didyk, Piotr and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-3-03868-025-3}, DOI = {10.2312/vmv.20161351}, PUBLISHER = {Eurographics Association}, YEAR = {2016}, DATE = {2016}, BOOKTITLE = {VMV 2016 Vision, Modeling and Visualization}, EDITOR = {Hullin, Matthias and Stamminger, Marc and Weinkauf, Tino}, PAGES = {127--135}, ADDRESS = {Bayreuth, Germany}, }

Endnote

%0 Conference Proceedings %A Gryaditskaya, Yulia %A Masia, Belen %A Didyk, Piotr %A Myszkowski, Karol %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Gloss Editing in Light Fields : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-82C5-B %R 10.2312/vmv.20161351 %D 2016 %B 21st International Symposium on Vision, Modeling and Visualization %Z date of event: 2016-10-10 - 2016-10-12 %C Bayreuth, Germany %B VMV 2016 Vision, Modeling and Visualization %E Hullin, Matthias; Stamminger, Marc; Weinkauf, Tino %P 127 - 135 %I Eurographics Association %@ 978-3-03868-025-3

Dąbała, Ł., Ziegler, M., Didyk, P., et al. 2016. Efficient Multi-image Correspondences for On-line Light Field Video Processing. Computer Graphics Forum (Proc. Pacific Graphics 2016)35, 7.

Links

Export

BibTeX

@article{DabalaPG2016, TITLE = {Efficient Multi-image Correspondences for On-line Light Field Video Processing}, AUTHOR = {D{\k a}ba{\l}a, {\L}ukasz and Ziegler, Matthias and Didyk, Piotr and Zilly, Frederik and Keinert, Joachim and Myszkowski, Karol and Rokita, Przemyslaw and Ritschel, Tobias and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.13037}, PUBLISHER = {Blackwell-Wiley}, ADDRESS = {Oxford}, YEAR = {2016}, DATE = {2016}, JOURNAL = {Computer Graphics Forum (Proc. Pacific Graphics)}, VOLUME = {35}, NUMBER = {7}, PAGES = {401--410}, BOOKTITLE = {The 24th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2016)}, }

Endnote

%0 Journal Article %A Dąbała, Łukasz %A Ziegler, Matthias %A Didyk, Piotr %A Zilly, Frederik %A Keinert, Joachim %A Myszkowski, Karol %A Rokita, Przemyslaw %A Ritschel, Tobias %A Seidel, Hans-Peter %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Efficient Multi-image Correspondences for On-line Light Field Video Processing : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-82BA-5 %R 10.1111/cgf.13037 %7 2016 %D 2016 %J Computer Graphics Forum %O Computer Graphics Forum : journal of the European Association for Computer Graphics Comput. Graph. Forum %V 35 %N 7 %& 401 %P 401 - 410 %I Blackwell-Wiley %C Oxford %@ false %B The 24th Pacific Conference on Computer Graphics and Applications %O Pacific Graphics 2016 PG 2016

Boechat, P., Dokter, M., Kenzel, M., Seidel, H.-P., Schmalstieg, D., and Steinberger, M. 2016. Representing and Scheduling Procedural Generation using Operator Graphs. ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia 2016)35, 6.

Links

Export

BibTeX

@article{BoaechatSIGGRAPHAsia2016, TITLE = {Representing and Scheduling Procedural Generation using Operator Graphs}, AUTHOR = {Boechat, Pedro and Dokter, Mark and Kenzel, Michael and Seidel, Hans-Peter and Schmalstieg, Dieter and Steinberger, Markus}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2980179.2980227}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2016}, DATE = {2016}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia)}, VOLUME = {35}, NUMBER = {6}, PAGES = {1--12}, EID = {183}, BOOKTITLE = {Proceedings of ACM SIGGRAPH Asia 2016}, }

Endnote

%0 Journal Article %A Boechat, Pedro %A Dokter, Mark %A Kenzel, Michael %A Seidel, Hans-Peter %A Schmalstieg, Dieter %A Steinberger, Markus %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Representing and Scheduling Procedural Generation using Operator Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-98BB-0 %R 10.1145/2980179.2980227 %7 2016 %D 2016 %J ACM Transactions on Graphics %O TOG %V 35 %N 6 %& 1 %P 1 - 12 %Z sequence number: 183 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH Asia 2016 %O ACM SIGGRAPH Asia 2016

2015

Wang, Z., Seidel, H.-P., and Weinkauf, T. 2015. Hierarchical Hashing for Pattern Search in 3D Vector Fields. VMV 2015 Vision, Modeling and Visualization, Eurographics Association.

Links

Export

BibTeX

@inproceedings{WangVMV2015, TITLE = {Hierarchical Hashing for Pattern Search in {3D} Vector Fields}, AUTHOR = {Wang, Zhongjie and Seidel, Hans-Peter and Weinkauf, Tino}, LANGUAGE = {eng}, ISBN = {978-3-905674-95-8}, DOI = {10.2312/vmv.20151256}, PUBLISHER = {Eurographics Association}, YEAR = {2015}, DATE = {2015}, BOOKTITLE = {VMV 2015 Vision, Modeling and Visualization}, EDITOR = {Bommes, David and Ritschel, Tobias and Schultz, Thomas}, PAGES = {41--48}, ADDRESS = {Aachen, Germany}, }

Endnote

%0 Conference Proceedings %A Wang, Zhongjie %A Seidel, Hans-Peter %A Weinkauf, Tino %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Hierarchical Hashing for Pattern Search in 3D Vector Fields : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0028-F760-4 %R 10.2312/vmv.20151256 %D 2015 %B 20th International Symposium on Vision, Modeling and Visualization %Z date of event: 2015-10-07 - 2015-10-10 %C Aachen, Germany %B VMV 2015 Vision, Modeling and Visualization %E Bommes, David; Ritschel, Tobias; Schultz, Thomas %P 41 - 48 %I Eurographics Association %@ 978-3-905674-95-8

Von Tycowicz, C., Schulz, C., Seidel, H.-P., and Hildebrandt, K. 2015. Real-time Nonlinear Shape Interpolation. ACM Transactions on Graphics34, 3.

Links

Export

BibTeX

@article{Tycowicz2015, TITLE = {Real-time Nonlinear Shape Interpolation}, AUTHOR = {von Tycowicz, Christoph and Schulz, Christian and Seidel, Hans-Peter and Hildebrandt, Klaus}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2729972}, PUBLISHER = {Association for Computing Machinery}, ADDRESS = {New York, NY}, YEAR = {2015}, DATE = {2015}, JOURNAL = {ACM Transactions on Graphics}, VOLUME = {34}, NUMBER = {3}, PAGES = {1--10}, EID = {34}, }

Endnote

Schulz, C., von Tycowicz, C., Seidel, H.-P., and Hildebrandt, K. 2015. Animating Articulated Characters Using Wiggly Splines. Proceedings SCA 2015, ACM.

Links

Export

BibTeX

@inproceedings{SchulzSCA2015, TITLE = {Animating Articulated Characters Using Wiggly Splines}, AUTHOR = {Schulz, Christian and von Tycowicz, Christoph and Seidel, Hans-Peter and Hildebrandt, Klaus}, LANGUAGE = {eng}, ISBN = {978-1-4503-3496-9}, DOI = {10.1145/2786784.2786799}, PUBLISHER = {ACM}, YEAR = {2015}, DATE = {2015}, BOOKTITLE = {Proceedings SCA 2015}, PAGES = {101--109}, ADDRESS = {Los Angeles, CA, USA}, }

Endnote

%0 Conference Proceedings %A Schulz, Christian %A von Tycowicz, Christoph %A Seidel, Hans-Peter %A Hildebrandt, Klaus %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Animating Articulated Characters Using Wiggly Splines : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0028-8EA3-0 %R 10.1145/2786784.2786799 %D 2015 %B 14th ACM SIGGRAPH / Eurographics Symposium on Computer Animation %Z date of event: 2015-08-07 - 2015-08-09 %C Los Angeles, CA, USA %B Proceedings SCA 2015 %P 101 - 109 %I ACM %@ 978-1-4503-3496-9

Rhodin, H., Robertini, N., Richardt, C., Seidel, H.-P., and Theobalt, C. 2015a. A Versatile Scene Model With Differentiable Visibility Applied to Generative Pose Estimation. ICCV 2015, IEEE International Conference on Computer Vision, IEEE.

Links

Export

BibTeX

@inproceedings{RhodinICCV2015, TITLE = {A Versatile Scene Model With Differentiable Visibility Applied to Generative Pose Estimation}, AUTHOR = {Rhodin, Helge and Robertini, Nadia and Richardt, Christian and Seidel, Hans-Peter and Theobalt, Christian}, LANGUAGE = {eng}, ISBN = {978-1-4673-8390-5}, DOI = {10.1109/ICCV.2015.94}, PUBLISHER = {IEEE}, YEAR = {2015}, DATE = {2015}, BOOKTITLE = {ICCV 2015, IEEE International Conference on Computer Vision}, PAGES = {765--773}, ADDRESS = {Santiago, Chile}, }

Endnote

%0 Conference Proceedings %A Rhodin, Helge %A Robertini, Nadia %A Richardt, Christian %A Seidel, Hans-Peter %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T A Versatile Scene Model With Differentiable Visibility Applied to Generative Pose Estimation : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0029-52DC-4 %R 10.1109/ICCV.2015.94 %D 2015 %B IEEE International Conference on Computer Vision %Z date of event: 2015-12-07 - 2015-12-13 %C Santiago, Chile %B ICCV 2015 %P 765 - 773 %I IEEE %@ 978-1-4673-8390-5 %U http://www.cv-foundation.org/openaccess/content_iccv_2015/html/Rhodin_A_Versatile_Scene_ICCV_2015_paper.html

Rhodin, H., Tompkin, J., Kim, K.I., et al. 2015b. Generalizing Wave Gestures from Sparse Examples for Real-time Character Control. ACM Transactions on Graphics34, 6.

Links

Export

BibTeX

@article{DBLP:journals/tog/RhodinTKAPST15, TITLE = {Generalizing Wave Gestures from Sparse Examples for Real-time Character Control}, AUTHOR = {Rhodin, Helge and Tompkin, James and Kim, Kwang In and de Aguiar, Edilson and Pfister, Hanspeter and Seidel, Hans-Peter and Theobalt, Christian}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2816795.2818082}, PUBLISHER = {Association for Computing Machinery}, ADDRESS = {New York, NY}, YEAR = {2015}, DATE = {2015}, JOURNAL = {ACM Transactions on Graphics}, VOLUME = {34}, NUMBER = {6}, PAGES = {181:1--181:12}, }

Endnote

%0 Journal Article %A Rhodin, Helge %A Tompkin, James %A Kim, Kwang In %A de Aguiar, Edilson %A Pfister, Hanspeter %A Seidel, Hans-Peter %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Generalizing Wave Gestures from Sparse Examples for Real-time Character Control : %G eng %U http://hdl.handle.net/21.11116/0000-000F-7285-A %R 10.1145/2816795.2818082 %D 2015 %J ACM Transactions on Graphics %V 34 %N 6 %& 181:1 %P 181:1 - 181:12 %I Association for Computing Machinery %C New York, NY %@ false

Rhodin, H., Tompkin, J., Kim, K.I., et al. 2015c. Generalizing Wave Gestures from Sparse Examples for Real-time Character Control. ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia 2015)34, 6.

Links

Export

BibTeX

@article{RhodinSAP2015, TITLE = {Generalizing Wave Gestures from Sparse Examples for Real-time Character Control}, AUTHOR = {Rhodin, Helge and Tompkin, James and Kim, Kwang In and de Aguiar, Edilson and Pfister, Hanspeter and Seidel, Hans-Peter and Theobalt, Christian}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2816795.2818082}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2015}, DATE = {2015}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia)}, VOLUME = {34}, NUMBER = {6}, PAGES = {1--12}, EID = {181}, BOOKTITLE = {Proceedings of ACM SIGGRAPH Asia 2015}, }

Endnote

%0 Journal Article %A Rhodin, Helge %A Tompkin, James %A Kim, Kwang In %A de Aguiar, Edilson %A Pfister, Hanspeter %A Seidel, Hans-Peter %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Generalizing Wave Gestures from Sparse Examples for Real-time Character Control : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0029-2476-8 %R 10.1145/2816795.2818082 %7 2015 %D 2015 %J ACM Transactions on Graphics %O TOG %V 34 %N 6 %& 1 %P 1 - 12 %Z sequence number: 181 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH Asia 2015 %O ACM SIGGRAPH Asia 2015 Kobe, Japan

Nguyen, C., Ritschel, T., and Seidel, H.-P. 2015a. Data-driven Color Manifolds. ACM Transactions on Graphics34, 2.

Links

Export

BibTeX

@article{NguyenTOG2015, TITLE = {Data-driven Color Manifolds}, AUTHOR = {Nguyen, Chuong and Ritschel, Tobias and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2699645}, PUBLISHER = {Association for Computing Machinery}, ADDRESS = {New York, NY}, YEAR = {2015}, DATE = {2015}, JOURNAL = {ACM Transactions on Graphics}, VOLUME = {34}, NUMBER = {2}, PAGES = {1--9}, EID = {20}, }

Endnote

%0 Journal Article %A Nguyen, Chuong %A Ritschel, Tobias %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Data-driven Color Manifolds : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-680A-D %R 10.1145/2699645 %7 2015 %D 2015 %J ACM Transactions on Graphics %V 34 %N 2 %& 1 %P 1 - 9 %Z sequence number: 20 %I Association for Computing Machinery %C New York, NY %@ false

Nguyen, C., Nalbach, O., Ritschel, T., and Seidel, H.-P. 2015b. Guiding Image Manipulations Using Shape-appearance Subspaces from Co-alignment of Image Collections. Computer Graphics Forum (Proc. EUROGRAPHICS 2015)34, 2.

Links

Export

BibTeX

@article{NguyenEG2015, TITLE = {Guiding Image Manipulations Using Shape-appearance Subspaces from Co-alignment of Image Collections}, AUTHOR = {Nguyen, Chuong and Nalbach, Oliver and Ritschel, Tobias and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12548}, PUBLISHER = {Blackwell-Wiley}, ADDRESS = {Oxford}, YEAR = {2015}, DATE = {2015}, JOURNAL = {Computer Graphics Forum (Proc. EUROGRAPHICS)}, VOLUME = {34}, NUMBER = {2}, PAGES = {143--154}, BOOKTITLE = {The 36th Annual Conference of the European Association of Computer Graphics (EUROGRAPHICS 2015)}, }

Endnote

%0 Journal Article %A Nguyen, Chuong %A Nalbach, Oliver %A Ritschel, Tobias %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Guiding Image Manipulations Using Shape-appearance Subspaces from Co-alignment of Image Collections : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-5D6A-0 %R 10.1111/cgf.12548 %7 2015 %D 2015 %J Computer Graphics Forum %O Computer Graphics Forum : journal of the European Association for Computer Graphics Comput. Graph. Forum %V 34 %N 2 %& 143 %P 143 - 154 %I Blackwell-Wiley %C Oxford %@ false %B The 36th Annual Conference of the European Association of Computer Graphics %O EUROGRAPHICS 2015 4th – 8th May 2015, Kongresshaus in Zürich, Switzerland EG 2015

Nalbach, O., Ritschel, T., and Seidel, H.-P. 2015. The Bounced Z-buffer for Indirect Visibility. VMV 2015 Vision, Modeling and Visualization, Eurographics Association.

Links

Export

BibTeX

@inproceedings{NalbachVMV2015, TITLE = {The Bounced {Z}-buffer for Indirect Visibility}, AUTHOR = {Nalbach, Oliver and Ritschel, Tobias and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-3-905674-95-8}, DOI = {10.2312/vmv.20151261}, PUBLISHER = {Eurographics Association}, YEAR = {2015}, DATE = {2015}, BOOKTITLE = {VMV 2015 Vision, Modeling and Visualization}, EDITOR = {Bommes, David and Ritschel, Tobias and Schultz, Thomas}, PAGES = {79--86}, ADDRESS = {Aachen, Germany}, }

Endnote

%0 Conference Proceedings %A Nalbach, Oliver %A Ritschel, Tobias %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T The Bounced Z-buffer for Indirect Visibility : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0028-F762-F %R 10.2312/vmv.20151261 %D 2015 %B 20th International Symposium on Vision, Modeling and Visualization %Z date of event: 2015-10-07 - 2015-10-10 %C Aachen, Germany %B VMV 2015 Vision, Modeling and Visualization %E Bommes, David; Ritschel, Tobias; Schultz, Thomas %P 79 - 86 %I Eurographics Association %@ 978-3-905674-95-8

Mantiuk, R., Myszkowski, K., and Seidel, H.-P. 2015. High Dynamic Range Imaging. In: Wiley Encyclopedia of Electrical and Electronics Engineering. Wiley, New York, NY.

Links

Export

BibTeX

@incollection{MantiukEncyclopedia2015, TITLE = {High Dynamic Range Imaging}, AUTHOR = {Mantiuk, Rafa{\l} and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, DOI = {10.1002/047134608X.W8265}, PUBLISHER = {Wiley}, ADDRESS = {New York, NY}, YEAR = {2015}, BOOKTITLE = {Wiley Encyclopedia of Electrical and Electronics Engineering}, EDITOR = {Webster, John G.}, PAGES = {1--42}, }

Endnote

%0 Book Section %A Mantiuk, Rafał %A Myszkowski, Karol %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T High Dynamic Range Imaging : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-A376-B %R 10.1002/047134608X.W8265 %D 2015 %8 15.06.2015 %B Wiley Encyclopedia of Electrical and Electronics Engineering %E Webster, John G. %P 1 - 42 %I Wiley %C New York, NY

Li, C., Wand, M., Wu, X., and Seidel, H.-P. 2015. Approximate 3D Partial Symmetry Detection Using Co-occurrence Analysis. International Conference on 3D Vision, IEEE.

Links

Export

BibTeX

@inproceedings{Li3DV2015, TITLE = {Approximate {3D} Partial Symmetry Detection Using Co-occurrence Analysis}, AUTHOR = {Li, Chuan and Wand, Michael and Wu, Xiaokun and Seidel, Hans-Peter}, ISBN = {978-1-4673-8333-2}, DOI = {10.1109/3DV.2015.55}, PUBLISHER = {IEEE}, YEAR = {2015}, DATE = {2015}, BOOKTITLE = {International Conference on 3D Vision}, DEBUG = {author: Theobalt, Christian}, EDITOR = {Brown, Michael and Kosecka, Jana}, PAGES = {425--433}, ADDRESS = {Lyon, France}, }

Endnote

%0 Conference Proceedings %A Li, Chuan %A Wand, Michael %A Wu, Xiaokun %A Seidel, Hans-Peter %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Approximate 3D Partial Symmetry Detection Using Co-occurrence Analysis : %U http://hdl.handle.net/11858/00-001M-0000-002B-34D8-0 %R 10.1109/3DV.2015.55 %D 2015 %B International Conference on 3D Vision %Z date of event: 2015-10-19 - 2015-10-22 %C Lyon, France %B International Conference on 3D Vision %E Brown, Michael; Kosecka, Jana; Theobalt, Christian %P 425 - 433 %I IEEE %@ 978-1-4673-8333-2

Klehm, O., Kol, T.R., Seidel, H.-P., and Eisemann, E. 2015. Stylized Scattering via Transfer Functions and Occluder Manipulation. Graphics Interface 2015, Graphics Interface Conference 2015, Canadian Information Processing Society.

Links

Export

BibTeX

@inproceedings{KlehmGI2015, TITLE = {Stylized Scattering via Transfer Functions and Occluder Manipulation}, AUTHOR = {Klehm, Oliver and Kol, Timothy R. and Seidel, Hans-Peter and Eisemann, Elmar}, LANGUAGE = {eng}, ISBN = {978-0-9947868-0-7}, DOI = {10.20380/GI2015.15}, PUBLISHER = {Canadian Information Processing Society}, YEAR = {2015}, DATE = {2015}, BOOKTITLE = {Graphics Interface 2015, Graphics Interface Conference 2015}, EDITOR = {Zhang, Hao Richard and Tang, Tony}, PAGES = {115--121}, ADDRESS = {Halifax, Canada}, }

Endnote

%0 Conference Proceedings %A Klehm, Oliver %A Kol, Timothy R. %A Seidel, Hans-Peter %A Eisemann, Elmar %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Stylized Scattering via Transfer Functions and Occluder Manipulation : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0027-D415-8 %R 10.20380/GI2015.15 %D 2015 %B Graphics Interface Conference 2015 %Z date of event: 2015-06-03 - 2015-06-05 %C Halifax, Canada %B Graphics Interface 2015 %E Zhang, Hao Richard; Tang, Tony %P 115 - 121 %I Canadian Information Processing Society %@ 978-0-9947868-0-7

Kellnhofer, P., Ritschel, T., Myszkowski, K., and Seidel, H.-P. 2015a. A Transformation-aware Perceptual Image Metric. Human Vision and Electronic Imaging XX (HVEI 2015), SPIE/IS&T.

(Best Student Paper Award)

Abstract

Links

Export

BibTeX

@inproceedings{Kellnhofer2015, TITLE = {A Transformation-aware Perceptual Image Metric}, AUTHOR = {Kellnhofer, Petr and Ritschel, Tobias and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {9781628414844}, DOI = {10.1117/12.2076754}, PUBLISHER = {SPIE/IS\&T}, YEAR = {2015}, DATE = {2015}, ABSTRACT = {Predicting human visual perception of image differences has several applications such as compression, rendering, editing and retargeting. Current approaches however, ignore the fact that the human visual system compensates for geometric transformations, e.g. we see that an image and a rotated copy are identical. Instead, they will report a large, false-positive difference. At the same time, if the transformations become too strong or too spatially incoherent, comparing two images indeed gets increasingly difficult. Between these two extremes, we propose a system to quantify the effect of transformations, not only on the perception of image differences, but also on saliency and motion parallax. To this end, we first fit local homographies to a given optical flow field and then convert this field into a field of elementary transformations such as translation, rotation, scaling, and perspective. We conduct a perceptual experiment quantifying the increase of difficulty when compensating for elementary transformations. Transformation entropy is proposed as a novel measure of complexity in a flow field. This representation is then used for applications, such as comparison of non-aligned images, where transformations cause threshold elevation, and detection of salient transformations.}, BOOKTITLE = {Human Vision and Electronic Imaging XX (HVEI 2015)}, EDITOR = {Rogowitz, Bernice E. and Pappas, Thrasyvoulos N. and de Ridder, Huib}, EID = {939408}, SERIES = {Proceedings of SPIE}, VOLUME = {9394}, ADDRESS = {San Francisco, CA, USA}, }

Endnote

%0 Conference Proceedings %A Kellnhofer, Petr %A Ritschel, Tobias %A Myszkowski, Karol %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T A Transformation-aware Perceptual Image Metric : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-544A-4 %R 10.1117/12.2076754 %D 2015 %B Human Vision and Electronic Imaging XX %Z date of event: 2015-02-08 - 2015-02-12 %C San Francisco, CA, USA %X Predicting human visual perception of image differences has several applications such as compression, rendering, editing and retargeting. Current approaches however, ignore the fact that the human visual system compensates for geometric transformations, e.g. we see that an image and a rotated copy are identical. Instead, they will report a large, false-positive difference. At the same time, if the transformations become too strong or too spatially incoherent, comparing two images indeed gets increasingly difficult. Between these two extremes, we propose a system to quantify the effect of transformations, not only on the perception of image differences, but also on saliency and motion parallax. To this end, we first fit local homographies to a given optical flow field and then convert this field into a field of elementary transformations such as translation, rotation, scaling, and perspective. We conduct a perceptual experiment quantifying the increase of difficulty when compensating for elementary transformations. Transformation entropy is proposed as a novel measure of complexity in a flow field. This representation is then used for applications, such as comparison of non-aligned images, where transformations cause threshold elevation, and detection of salient transformations. %B Human Vision and Electronic Imaging XX %E Rogowitz, Bernice E.; Pappas, Thrasyvoulos N.; de Ridder, Huib %Z sequence number: 939408 %I SPIE/IS&T %@ 9781628414844 %B Proceedings of SPIE %N 9394

Kellnhofer, P., Leimkühler, T., Ritschel, T., Myszkowski, K., and Seidel, H.-P. 2015b. What Makes 2D-to-3D Stereo Conversion Perceptually Plausible? Proceedings SAP 2015, ACM.

(Best Presentation Award)

Links

Export

BibTeX

@inproceedings{Kellnhofer2015SAP, TITLE = {What Makes {2D}-to-{3D} Stereo Conversion Perceptually Plausible?}, AUTHOR = {Kellnhofer, Petr and Leimk{\"u}hler, Thomas and Ritschel, Tobias and Myszkowski, Karol and Seidel, Hans-Peter}, ISBN = {978-1-4503-3812-7}, DOI = {10.1145/2804408.2804409}, PUBLISHER = {ACM}, YEAR = {2015}, DATE = {2015}, BOOKTITLE = {Proceedings SAP 2015}, PAGES = {59--66}, ADDRESS = {T{\"u}bingen, Germany}, }

Endnote

%0 Conference Proceedings %A Kellnhofer, Petr %A Leimkühler, Thomas %A Ritschel, Tobias %A Myszkowski, Karol %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T What Makes 2D-to-3D Stereo Conversion Perceptually Plausible? : %U http://hdl.handle.net/11858/00-001M-0000-0029-2460-7 %R 10.1145/2804408.2804409 %D 2015 %B ACM SIGGRAPH Symposium on Applied Perception %Z date of event: 2015-09-13 - 2015-09-14 %C Tübingen, Germany %B Proceedings SAP 2015 %P 59 - 66 %I ACM %@ 978-1-4503-3812-7 %U http://resources.mpi-inf.mpg.de/StereoCueFusion/WhatMakes3D/

Kellnhofer, P., Ritschel, T., Myszkowski, K., Eisemann, E., and Seidel, H.-P. 2015c. Modeling Luminance Perception at Absolute Threshold. Computer Graphics Forum (Proc. Eurographics Symposium on Rendering 2015)34, 4.

Links

Export

BibTeX

@article{Kellnhofer2015a, TITLE = {Modeling Luminance Perception at Absolute Threshold}, AUTHOR = {Kellnhofer, Petr and Ritschel, Tobias and Myszkowski, Karol and Eisemann, Elmar and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12687}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2015}, DATE = {2015}, JOURNAL = {Computer Graphics Forum (Proc. Eurographics Symposium on Rendering)}, VOLUME = {34}, NUMBER = {4}, PAGES = {155--164}, BOOKTITLE = {Eurographics Symposium on Rendering 2014}, EDITOR = {Lehtinen, Jaakko and Nowrouzezahra, Derek}, }

Endnote

%0 Journal Article %A Kellnhofer, Petr %A Ritschel, Tobias %A Myszkowski, Karol %A Eisemann, Elmar %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Modeling Luminance Perception at Absolute Threshold : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0028-8E8D-4 %R 10.1111/cgf.12687 %7 2015 %D 2015 %J Computer Graphics Forum %V 34 %N 4 %& 155 %P 155 - 164 %I Wiley-Blackwell %C Oxford %@ false %B Eurographics Symposium on Rendering 2014 %O Eurographics Symposium on Rendering 2015 EGSR 2015 Darmstadt, Germany, June 24th - 26th, 2015

Jain, A., Chen, C., Thormählen, T., Metaxas, D., and Seidel, H.-P. 2015. Multi-layer Stencil Creation from Images. Computers and Graphics48.

Links

Export

BibTeX

@article{JainMulti-layer2015, TITLE = {Multi-layer Stencil Creation from Images}, AUTHOR = {Jain, Arjun and Chen, Chao and Thorm{\"a}hlen, Thorsten and Metaxas, Dimitris and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0097-8493}, DOI = {10.1016/j.cag.2015.02.003}, PUBLISHER = {Pergamon}, ADDRESS = {New York, NY}, YEAR = {2015}, DATE = {2015}, JOURNAL = {Computers and Graphics}, VOLUME = {48}, PAGES = {11--22}, }

Endnote

%0 Journal Article %A Jain, Arjun %A Chen, Chao %A Thormählen, Thorsten %A Metaxas, Dimitris %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Multi-layer Stencil Creation from Images : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0027-9C34-A %R 10.1016/j.cag.2015.02.003 %7 2015-02-26 %D 2015 %J Computers and Graphics %V 48 %& 11 %P 11 - 22 %I Pergamon %C New York, NY %@ false

Herzog, R., Mewes, D., Wand, M., Guibas, L., and Seidel, H.-P. 2015. LeSSS: Learned Shared Semantic Spaces for Relating Multi-modal Representations of 3D Shapes. Computer Graphics Forum (Proc. Eurographics Symposium on Geometric Processing 2015)34, 5.

Links

Export

BibTeX

@article{HerzogSGP2015, TITLE = {{LeSSS}: {L}earned {S}hared {S}emantic {S}paces for Relating Multi-Modal Representations of {3D} Shapes}, AUTHOR = {Herzog, Robert and Mewes, Daniel and Wand, Michael and Guibas, Leonidas and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12703}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Chichester}, YEAR = {2015}, DATE = {2015}, JOURNAL = {Computer Graphics Forum (Proc. Eurographics Symposium on Geometric Processing)}, VOLUME = {34}, NUMBER = {5}, PAGES = {141--151}, BOOKTITLE = {Symposium on Geometry Processing 2015 (Eurographics Symposium on Geometric Processing 2015)}, EDITOR = {Ben-Chen, Mirela and Liu, Ligang}, }

Endnote

%0 Journal Article %A Herzog, Robert %A Mewes, Daniel %A Wand, Michael %A Guibas, Leonidas %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T LeSSS: Learned Shared Semantic Spaces for Relating Multi-modal Representations of 3D Shapes : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0028-8E9A-6 %R 10.1111/cgf.12703 %7 2015 %D 2015 %J Computer Graphics Forum %V 34 %N 5 %& 141 %P 141 - 151 %I Wiley-Blackwell %C Chichester %@ false %B Symposium on Geometry Processing 2015 %O Graz, Austria, July 6 - 8, 2015 SGP 2015 Eurographics Symposium on Geometric Processing 2015

Gryaditskaya, Y., Pouli, T., Reinhard, E., Myszkowski, K., and Seidel, H.-P. 2015. Motion Aware Exposure Bracketing for HDR Video. Computer Graphics Forum (Proc. Eurographics Symposium on Rendering 2015)34, 4.

Links

Export

BibTeX

@article{Gryaditskaya2015, TITLE = {Motion Aware Exposure Bracketing for {HDR} Video}, AUTHOR = {Gryaditskaya, Yulia and Pouli, Tania and Reinhard, Erik and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12684}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2015}, DATE = {2015}, JOURNAL = {Computer Graphics Forum (Proc. Eurographics Symposium on Rendering)}, VOLUME = {34}, NUMBER = {4}, PAGES = {119--130}, BOOKTITLE = {Eurographics Symposium on Rendering 2015}, EDITOR = {Lehtinen, Jaakko and Nowrouzezahra, Derek}, }

Endnote

%0 Journal Article %A Gryaditskaya, Yulia %A Pouli, Tania %A Reinhard, Erik %A Myszkowski, Karol %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Motion Aware Exposure Bracketing for HDR Video : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0028-15D2-B %R 10.1111/cgf.12684 %7 2015 %D 2015 %J Computer Graphics Forum %V 34 %N 4 %& 119 %P 119 - 130 %I Wiley-Blackwell %C Oxford %@ false %B Eurographics Symposium on Rendering 2015 %O Eurographics Symposium on Rendering 2015 EGSR 2015 Darmstadt, Germany, June 24th - 26th, 2015

Brandt, C., Seidel, H.-P., and Hildebrandt, K. 2015. Optimal Spline Approximation via ℓ₀-Minimization. Computer Graphics Forum (Proc. EUROGRAPHICS 2015)34, 2.

Links

Export

BibTeX

@article{Brandt2015, TITLE = {Optimal Spline Approximation via $\ell_0$-Minimization}, AUTHOR = {Brandt, Christopher and Seidel, Hans-Peter and Hildebrandt, Klaus}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12589}, PUBLISHER = {Blackwell-Wiley}, ADDRESS = {Oxford}, YEAR = {2015}, DATE = {2015}, JOURNAL = {Computer Graphics Forum (Proc. EUROGRAPHICS)}, VOLUME = {34}, NUMBER = {2}, PAGES = {617--626}, BOOKTITLE = {The 36th Annual Conference of the European Association of Computer Graphics (EUROGRAPHICS 2015)}, }

Endnote

%0 Journal Article %A Brandt, Christopher %A Seidel, Hans-Peter %A Hildebrandt, Klaus %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Optimal Spline Approximation via ℓ₀-Minimization : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-5D67-5 %R 10.1111/cgf.12589 %7 2015 %D 2015 %J Computer Graphics Forum %O Computer Graphics Forum : journal of the European Association for Computer Graphics Comput. Graph. Forum %V 34 %N 2 %& 617 %P 617 - 626 %I Blackwell-Wiley %C Oxford %@ false %B The 36th Annual Conference of the European Association of Computer Graphics %O EUROGRAPHICS 2015 4th - 8th May 2015, Kongresshaus in Zürich, Switzerland

Arpa, S., Ritschel, T., Myszkowski, K., Çapin, T., and Seidel, H.-P. 2015. Purkinje Images: Conveying Different Content for Different Luminance Adaptations in a Single Image. Computer Graphics Forum34, 1.

Links

Export

BibTeX

@article{arpa2014purkinje, TITLE = {Purkinje Images: {Conveying} Different Content for Different Luminance Adaptations in a Single Image}, AUTHOR = {Arpa, Sami and Ritschel, Tobias and Myszkowski, Karol and {\c C}apin, Tolga and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12463}, PUBLISHER = {Blackwell-Wiley}, ADDRESS = {Oxford}, YEAR = {2015}, DATE = {2015}, JOURNAL = {Computer Graphics Forum}, VOLUME = {34}, NUMBER = {1}, PAGES = {116--126}, }

Endnote

%0 Journal Article %A Arpa, Sami %A Ritschel, Tobias %A Myszkowski, Karol %A Çapin, Tolga %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Purkinje Images: Conveying Different Content for Different Luminance Adaptations in a Single Image : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-5D0B-6 %R 10.1111/cgf.12463 %7 2014-10-18 %D 2015 %J Computer Graphics Forum %O Computer Graphics Forum : journal of the European Association for Computer Graphics Comput. Graph. Forum %V 34 %N 1 %& 116 %P 116 - 126 %I Blackwell-Wiley %C Oxford %@ false

2014

Wu, X., Li, C., Wand, M., Hildebrandt, K., Jansen, S., and Seidel, H.-P. 2014a. 3D Model Retargeting Using Offset Statistics. 2nd International Conference on 3D Vision, IEEE.

Links

Export

BibTeX

@inproceedings{Wu2014a, TITLE = {{3D} Model Retargeting Using Offset Statistics}, AUTHOR = {Wu, Xiaokun and Li, Chuan and Wand, Michael and Hildebrandt, Klaus and Jansen, Silke and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-1-4799-7000-1}, DOI = {10.1109/3DV.2014.74}, PUBLISHER = {IEEE}, YEAR = {2014}, DATE = {2014}, BOOKTITLE = {2nd International Conference on 3D Vision}, PAGES = {353--360}, ADDRESS = {Tokyo, Japan}, }

Endnote

%0 Conference Proceedings %A Wu, Xiaokun %A Li, Chuan %A Wand, Michael %A Hildebrandt, Klaus %A Jansen, Silke %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T 3D Model Retargeting Using Offset Statistics : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-5D63-D %R 10.1109/3DV.2014.74 %D 2014 %B 2nd International Conference on 3D Vision %Z date of event: 2014-12-08 - 2014-12-11 %C Tokyo, Japan %B 2nd International Conference on 3D Vision %P 353 - 360 %I IEEE %@ 978-1-4799-7000-1

Wu, X., Wand, M., Hildebrandt, K., Kohli, P., and Seidel, H.-P. 2014b. Real-time Symmetry-preserving Deformation. Computer Graphics Forum (Proc. Pacific Graphics 2014)33, 7.

Links

Export

BibTeX

@article{Wu2014, TITLE = {Real-time Symmetry-preserving Deformation}, AUTHOR = {Wu, Xiaokun and Wand, Michael and Hildebrandt, Klaus and Kohli, Pushmeet and Seidel, Hans-Peter}, LANGUAGE = {eng}, DOI = {10.1111/cgf.12491}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2014}, DATE = {2014}, JOURNAL = {Computer Graphics Forum (Proc. Pacific Graphics)}, VOLUME = {33}, NUMBER = {7}, PAGES = {229--238}, BOOKTITLE = {22nd Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2014)}, }

Endnote

%0 Journal Article %A Wu, Xiaokun %A Wand, Michael %A Hildebrandt, Klaus %A Kohli, Pushmeet %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Real-time Symmetry-preserving Deformation : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0015-3D08-5 %R 10.1111/cgf.12491 %7 2014-10-28 %D 2014 %J Computer Graphics Forum %V 33 %N 7 %& 229 %P 229 - 238 %I Wiley-Blackwell %C Oxford %B 22nd Pacific Conference on Computer Graphics and Applications %O Pacific Graphics 2014 PG 2014 8 to 10 Oct 2014, Seoul, South Korea

Wang, Z., Martinez Esturo, J., Seidel, H.-P., and Weinkauf, T. 2014. Pattern Search in Flows based on Similarity of Stream Line Segments. VMV 2014 Vision, Modeling and Visualization, Eurographics Association.

Abstract

We propose a method that allows users to define flow features in form of patterns represented as sparse sets of stream line segments. Our approach finds similar occurrences in the same or other time steps. Related approaches define patterns using dense, local stencils or support only single segments. Our patterns are defined sparsely and can have a significant extent, i.e., they are integration-based and not local. This allows for a greater flexibility in defining features of interest. Similarity is measured using intrinsic curve properties only, which enables invariance to location, orientation, and scale. Our method starts with splitting stream lines using globally-consistent segmentation criteria. It strives to maintain the visually apparent features of the flow as a collection of stream line segments. Most importantly, it provides similar segmentations for similar flow structures. For user-defined patterns of curve segments, our algorithm finds similar ones that are invariant to similarity transformations. We showcase the utility of our method using different 2D and 3D flow fields.

Links

Export

BibTeX

@inproceedings{wang14, TITLE = {Pattern Search in Flows based on Similarity of Stream Line Segments}, AUTHOR = {Wang, Zhongjie and Martinez Esturo, Janick and Seidel, Hans-Peter and Weinkauf, Tino}, LANGUAGE = {eng}, DOI = {10.2312/vmv.20141272}, PUBLISHER = {Eurographics Association}, YEAR = {2014}, DATE = {2014-10}, ABSTRACT = {We propose a method that allows users to define flow features in form of patterns represented as sparse sets of stream line segments. Our approach finds similar occurrences in the same or other time steps. Related approaches define patterns using dense, local stencils or support only single segments. Our patterns are defined sparsely and can have a significant extent, i.e., they are integration-based and not local. This allows for a greater flexibility in defining features of interest. Similarity is measured using intrinsic curve properties only, which enables invariance to location, orientation, and scale. Our method starts with splitting stream lines using globally-consistent segmentation criteria. It strives to maintain the visually apparent features of the flow as a collection of stream line segments. Most importantly, it provides similar segmentations for similar flow structures. For user-defined patterns of curve segments, our algorithm finds similar ones that are invariant to similarity transformations. We showcase the utility of our method using different 2D and 3D flow fields.}, BOOKTITLE = {VMV 2014 Vision, Modeling and Visualization}, DEBUG = {author: von Landesberger, Tatiana; author: Theisel, Holger; author: Urban, Philipp}, EDITOR = {Bender, Jan and Kuijper, Arjan}, PAGES = {23--30}, ADDRESS = {Darmstadt, Germany}, }

Endnote

%0 Conference Proceedings %A Wang, Zhongjie %A Martinez Esturo, Janick %A Seidel, Hans-Peter %A Weinkauf, Tino %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Pattern Search in Flows based on Similarity of Stream Line Segments : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-5337-3 %R 10.2312/vmv.20141272 %D 2014 %B 19th International Workshop on Vision, Modeling and Visualization %Z date of event: 2014-10-08 - 2014-10-10 %C Darmstadt, Germany %X We propose a method that allows users to define flow features in form of patterns represented as sparse sets of stream line segments. Our approach finds similar occurrences in the same or other time steps. Related approaches define patterns using dense, local stencils or support only single segments. Our patterns are defined sparsely and can have a significant extent, i.e., they are integration-based and not local. This allows for a greater flexibility in defining features of interest. Similarity is measured using intrinsic curve properties only, which enables invariance to location, orientation, and scale. Our method starts with splitting stream lines using globally-consistent segmentation criteria. It strives to maintain the visually apparent features of the flow as a collection of stream line segments. Most importantly, it provides similar segmentations for similar flow structures. For user-defined patterns of curve segments, our algorithm finds similar ones that are invariant to similarity transformations. We showcase the utility of our method using different 2D and 3D flow fields. %B VMV 2014 Vision, Modeling and Visualization %E Bender, Jan; Kuijper, Arjan; von Landesberger, Tatiana; Theisel, Holger; Urban, Philipp %P 23 - 30 %I Eurographics Association %U http://tinoweinkauf.net/

Vangorp, P., Mantiuk, R., Bazyluk, B., et al. 2014. Depth from HDR: Depth Induction or Increased Realism? SAP 2014, ACM Symposium on Applied Perception, ACM.

Links

Export

BibTeX

@inproceedings{Vangorp2014, TITLE = {Depth from {HDR}: {Depth} Induction or Increased Realism?}, AUTHOR = {Vangorp, Peter and Mantiuk, Rafal and Bazyluk, Bartosz and Myszkowski, Karol and Mantiuk, Rados{\textbackslash}law and Watt, Simon J. and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-1-4503-3009-1}, DOI = {10.1145/2628257.2628258}, PUBLISHER = {ACM}, YEAR = {2014}, DATE = {2014}, BOOKTITLE = {SAP 2014, ACM Symposium on Applied Perception}, EDITOR = {Bailey, Reynold and Kuhl, Scott}, PAGES = {71--78}, ADDRESS = {Vancouver, Canada}, }

Endnote

%0 Conference Proceedings %A Vangorp, Peter %A Mantiuk, Rafal %A Bazyluk, Bartosz %A Myszkowski, Karol %A Mantiuk, Rados\law %A Watt, Simon J. %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Depth from HDR: Depth Induction or Increased Realism? : %G eng %U http://hdl.handle.net/11858/00-001M-0000-001A-34DB-5 %R 10.1145/2628257.2628258 %D 2014 %B ACM Symposium on Applied Perception %Z date of event: 2014-08-08 - 2014-08-09 %C Vancouver, Canada %K binocular disparity, contrast, luminance, stereo 3D %B SAP 2014 %E Bailey, Reynold; Kuhl, Scott %P 71 - 78 %I ACM %@ 978-1-4503-3009-1

Tevs, A., Huang, Q., Wand, M., Seidel, H.-P., and Guibas, L. 2014. Relating Shapes via Geometric Symmetries and Regularities. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2014)33, 4.

Links

Export

BibTeX

@article{TevsSIGGRAPH2014, TITLE = {Relating Shapes via Geometric Symmetries and Regularities}, AUTHOR = {Tevs, Art and Huang, Qixing and Wand, Michael and Seidel, Hans-Peter and Guibas, Leonidas}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2601097.2601220}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2014}, DATE = {2014}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {33}, NUMBER = {4}, PAGES = {1--12}, EID = {119}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2014}, }

Endnote

%0 Journal Article %A Tevs, Art %A Huang, Qixing %A Wand, Michael %A Seidel, Hans-Peter %A Guibas, Leonidas %+ External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Relating Shapes via Geometric Symmetries and Regularities : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-8052-F %F ISI: 000340000100086 %R 10.1145/2601097.2601220 %7 2014-07 %D 2014 %J ACM Transactions on Graphics %V 33 %N 4 %& 1 %P 1 - 12 %Z sequence number: 119 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2014 %O Vancouver, BC, Canada ACM SIGGRAPH 2014

Templin, K., Didyk, P., Myszkowski, K., Hefeeda, M.M., Seidel, H.-P., and Matusik, W. 2014a. Modeling and Optimizing Eye Vergence Response to Stereoscopic Cuts. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2014)33, 4.

Links

Export

BibTeX

@article{Templin:2014:MOE:2601097.2601148, TITLE = {Modeling and Optimizing Eye Vergence Response to Stereoscopic Cuts}, AUTHOR = {Templin, Krzysztof and Didyk, Piotr and Myszkowski, Karol and Hefeeda, Mohamed M. and Seidel, Hans-Peter and Matusik, Wojciech}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2601097.2601148}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2014}, DATE = {2014}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {33}, NUMBER = {4}, PAGES = {1--8}, EID = {145}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2014}, }

Endnote

%0 Journal Article %A Templin, Krzysztof %A Didyk, Piotr %A Myszkowski, Karol %A Hefeeda, Mohamed M. %A Seidel, Hans-Peter %A Matusik, Wojciech %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Modeling and Optimizing Eye Vergence Response to Stereoscopic Cuts : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0023-EE16-9 %R 10.1145/2601097.2601148 %7 2014 %D 2014 %K S3D, binocular, eye‐tracking %J ACM Transactions on Graphics %V 33 %N 4 %& 1 %P 1 - 8 %Z sequence number: 145 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2014 %O ACM SIGGRAPH 2014 Vancouver, BC, Canada

Templin, K., Didyk, P., Myszkowski, K., and Seidel, H.-P. 2014b. Perceptually-motivated Stereoscopic Film Grain. Computer Graphics Forum (Proc. Pacific Graphics 2014)33, 7.

Links

Export

BibTeX

@article{Templin2014b, TITLE = {Perceptually-motivated Stereoscopic Film Grain}, AUTHOR = {Templin, Krzysztof and Didyk, Piotr and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, DOI = {10.1111/cgf.12503}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2014}, DATE = {2014}, JOURNAL = {Computer Graphics Forum (Proc. Pacific Graphics)}, VOLUME = {33}, NUMBER = {7}, PAGES = {349--358}, BOOKTITLE = {22nd Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2014)}, }

Endnote

%0 Journal Article %A Templin, Krzysztof %A Didyk, Piotr %A Myszkowski, Karol %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Perceptually-motivated Stereoscopic Film Grain : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-5DF2-B %R 10.1111/cgf.12503 %7 2014-10-28 %D 2014 %J Computer Graphics Forum %V 33 %N 7 %& 349 %P 349 - 358 %I Wiley-Blackwell %C Oxford %B 22nd Pacific Conference on Computer Graphics and Applications %O Pacific Graphics 2014 PG 2014 8 to 10 Oct 2014, Seoul, South Korea

Sridhar, S., Rhodin, H., Seidel, H.-P., Oulasvirta, A., and Theobalt, C. 2014a. Real-time Hand Tracking Using a Sum of Anisotropic Gaussians Model. Proceedings of the 2nd International Conference on 3D Vision, IEEE explore.

(arXiv: 1602.03860)

Abstract

Real-time marker-less hand tracking is of increasing importance in human-computer interaction. Robust and accurate tracking of arbitrary hand motion is a challenging problem due to the many degrees of freedom, frequent self-occlusions, fast motions, and uniform skin color. In this paper, we propose a new approach that tracks the full skeleton motion of the hand from multiple RGB cameras in real-time. The main contributions include a new generative tracking method which employs an implicit hand shape representation based on Sum of Anisotropic Gaussians (SAG), and a pose fitting energy that is smooth and analytically differentiable making fast gradient based pose optimization possible. This shape representation, together with a full perspective projection model, enables more accurate hand modeling than a related baseline method from literature. Our method achieves better accuracy than previous methods and runs at 25 fps. We show these improvements both qualitatively and quantitatively on publicly available datasets.

Links

Export

BibTeX

@inproceedings{Sridhar2016arXiv1602.03860, TITLE = {Real-time Hand Tracking Using a Sum of Anisotropic {Gaussians} Model}, AUTHOR = {Sridhar, Srinath and Rhodin, Helge and Seidel, Hans-Peter and Oulasvirta, Antti and Theobalt, Christian}, LANGUAGE = {eng}, ISBN = {978-1-4799-7000-1}, URL = {http://arxiv.org/abs/1602.03860}, DOI = {10.1109/3DV.2014.37}, EPRINT = {1602.03860}, EPRINTTYPE = {arXiv}, PUBLISHER = {IEEE explore}, YEAR = {2014}, DATE = {2014}, ABSTRACT = {Real-time marker-less hand tracking is of increasing importance in human-computer interaction. Robust and accurate tracking of arbitrary hand motion is a challenging problem due to the many degrees of freedom, frequent self-occlusions, fast motions, and uniform skin color. In this paper, we propose a new approach that tracks the full skeleton motion of the hand from multiple RGB cameras in real-time. The main contributions include a new generative tracking method which employs an implicit hand shape representation based on Sum of Anisotropic Gaussians (SAG), and a pose fitting energy that is smooth and analytically differentiable making fast gradient based pose optimization possible. This shape representation, together with a full perspective projection model, enables more accurate hand modeling than a related baseline method from literature. Our method achieves better accuracy than previous methods and runs at 25 fps. We show these improvements both qualitatively and quantitatively on publicly available datasets. }, BOOKTITLE = {Proceedings of the 2nd International Conference on 3D Vision}, PAGES = {319--326}, ADDRESS = {Tokyo, Japan}, }

Endnote

%0 Conference Proceedings %A Sridhar, Srinath %A Rhodin, Helge %A Seidel, Hans-Peter %A Oulasvirta, Antti %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Real-time Hand Tracking Using a Sum of Anisotropic Gaussians Model : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-9878-6 %U http://arxiv.org/abs/1602.03860 %R 10.1109/3DV.2014.37 %D 2014 %B 2nd International Conference on 3D Vision %Z date of event: 2014-12-08 - 2014-12-11 %C Tokyo, Japan %X Real-time marker-less hand tracking is of increasing importance in human-computer interaction. Robust and accurate tracking of arbitrary hand motion is a challenging problem due to the many degrees of freedom, frequent self-occlusions, fast motions, and uniform skin color. In this paper, we propose a new approach that tracks the full skeleton motion of the hand from multiple RGB cameras in real-time. The main contributions include a new generative tracking method which employs an implicit hand shape representation based on Sum of Anisotropic Gaussians (SAG), and a pose fitting energy that is smooth and analytically differentiable making fast gradient based pose optimization possible. This shape representation, together with a full perspective projection model, enables more accurate hand modeling than a related baseline method from literature. Our method achieves better accuracy than previous methods and runs at 25 fps. We show these improvements both qualitatively and quantitatively on publicly available datasets. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV %B Proceedings of the 2nd International Conference on 3D Vision %P 319 - 326 %I IEEE explore %@ 978-1-4799-7000-1

Sridhar, S., Rhodin, H., Seidel, H.-P., Oulasvirta, A., and Theobalt, C. 2014b. Real-time Hand Tracking Using a Sum of Anisotropic Gaussians Model. 3DV 2014, International Conference on 3D Vision, IEEE Computer Society.

Links

Export

BibTeX

@inproceedings{sridhar2014real, TITLE = {Real-time Hand Tracking Using a Sum of Anisotropic {Gaussians} Model}, AUTHOR = {Sridhar, Srinath and Rhodin, Helge and Seidel, Hans-Peter and Oulasvirta, Antti and Theobalt, Christian}, LANGUAGE = {eng}, ISBN = {978-1-4799-7001-8}, DOI = {10.1109/3DV.2014.37}, PUBLISHER = {IEEE Computer Society}, YEAR = {2014}, DATE = {2014}, BOOKTITLE = {3DV 2014, International Conference on 3D Vision}, PAGES = {319--326}, ADDRESS = {Tokyo, Japan}, }

Endnote

Schulze, M., Martinez Esturo, J., Günther, T., et al. 2014. Sets of Globally Optimal Stream Surfaces for Flow Visualization. Computer Graphics Forum (Proc. EuroVis 2014)33, 3.

Links

Export

BibTeX

@article{Schulze2014, TITLE = {Sets of Globally Optimal Stream Surfaces for Flow Visualization}, AUTHOR = {Schulze, Maik and Martinez Esturo, Janick and G{\"u}nther, T. and R{\"o}ssl, Christian and Seidel, Hans-Peter and Weinkauf, Tino and Theisel, Holger}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12356}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2014}, DATE = {2014}, JOURNAL = {Computer Graphics Forum (Proc. EuroVis)}, VOLUME = {33}, NUMBER = {3}, PAGES = {1--10}, BOOKTITLE = {Eurographics Conference on Visualization (EuroVis 2014)}, EDITOR = {Carr, Hamish and Rheingans, Penny and Schumann, Heidrun}, }

Endnote

%0 Journal Article %A Schulze, Maik %A Martinez Esturo, Janick %A Günther, T. %A Rössl, Christian %A Seidel, Hans-Peter %A Weinkauf, Tino %A Theisel, Holger %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Sets of Globally Optimal Stream Surfaces for Flow Visualization : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0023-F518-1 %R 10.1111/cgf.12356 %7 2014-07-12 %D 2014 %K Categories and Subject Descriptors (according to ACM CCS), I.3.5 [Computer Graphics]: Computational Geometry and Object Modeling—Geometric algorithms, languages, and systems %J Computer Graphics Forum %V 33 %N 3 %& 1 %P 1 - 10 %I Wiley-Blackwell %C Oxford %@ false %B Eurographics Conference on Visualization %O EuroVis 2014 Swansea, Wales, UK, June 9 – 13, 2014

Schulz, C., von Tycowicz, C., Seidel, H.-P., and Hildebrandt, K. 2014a. Animating Deformable Objects Using Sparse Spacetime Constraints. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2014)33, 4.

Links

Export

BibTeX

@article{Schulz2014, TITLE = {Animating Deformable Objects Using Sparse Spacetime Constraints}, AUTHOR = {Schulz, Christian and von Tycowicz, Christoph and Seidel, Hans-Peter and Hildebrandt, Klaus}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2601097.2601156}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2014}, DATE = {2014}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {33}, NUMBER = {4}, PAGES = {1--10}, EID = {109}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2014}, }

Endnote

%0 Journal Article %A Schulz, Christian %A von Tycowicz, Christoph %A Seidel, Hans-Peter %A Hildebrandt, Klaus %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Animating Deformable Objects Using Sparse Spacetime Constraints : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0023-EE18-5 %R 10.1145/2601097.2601156 %7 2014 %D 2014 %K model reduction, optimal control, physically‐based animation, spacetime constraints, wiggly splines %J ACM Transactions on Graphics %V 33 %N 4 %& 1 %P 1 - 10 %Z sequence number: 109 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2014 %O ACM SIGGRAPH 2014 Vancouver, BC, Canada

Schulz, C., von Tycowicz, C., Seidel, H.-P., and Hildebrandt, K. 2014b. Proofs of two Theorems concerning Sparse Spacetime Constraints. https://arxiv.org/abs/1405.1902v1.

(arXiv: 1405.1902)

Abstract

In the SIGGRAPH 2014 paper [SvTSH14] an approach for animating deformable objects using sparse spacetime constraints is introduced. This report contains the proofs of two theorems presented in the paper.

Links

Export

BibTeX

@online{Schulz-et-al_2014, TITLE = {Proofs of two Theorems concerning Sparse Spacetime Constraints}, AUTHOR = {Schulz, Christian and von Tycowicz, Christoph and Seidel, Hans-Peter and Hildebrandt, Klaus}, LANGUAGE = {eng}, URL = {https://arxiv.org/abs/1405.1902v1}, DOI = {10.48550/arXiv.1405.1902}, EPRINT = {1405.1902}, EPRINTTYPE = {arXiv}, YEAR = {2014}, DATE = {2014}, ABSTRACT = {In the SIGGRAPH 2014 paper [SvTSH14] an approach for animating deformable objects using sparse spacetime constraints is introduced. This report contains the proofs of two theorems presented in the paper. }, }

Endnote

%0 Report %A Schulz, Christian %A von Tycowicz, Christoph %A Seidel, Hans-Peter %A Hildebrandt, Klaus %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Proofs of two Theorems concerning Sparse Spacetime Constraints : %G eng %U http://hdl.handle.net/21.11116/0000-000F-7066-0 %U https://arxiv.org/abs/1405.1902v1 %R 10.48550/arXiv.1405.1902 %D 2014 %X In the SIGGRAPH 2014 paper [SvTSH14] an approach for animating deformable objects using sparse spacetime constraints is introduced. This report contains the proofs of two theorems presented in the paper. %K Computer Science, Graphics, cs.GR,Mathematics, Numerical Analysis, math.NA

Saikia, H., Seidel, H.-P., and Weinkauf, T. 2014. Extended Branch Decomposition Graphs: Structural Comparison of Scalar Data. Computer Graphics Forum (Proc. EuroVis 2014)33, 3.

Abstract

We present a method to find repeating topological structures in scalar data sets. More precisely, we compare all subtrees of two merge trees against each other - in an efficient manner exploiting redundancy. This provides pair-wise distances between the topological structures defined by sub/superlevel sets, which can be exploited in several applications such as finding similar structures in the same data set, assessing periodic behavior in time-dependent data, and comparing the topology of two different data sets. To do so, we introduce a novel data structure called the extended branch decomposition graph, which is composed of the branch decompositions of all subtrees of the merge tree. Based on dynamic programming, we provide two highly efficient algorithms for computing and comparing extended branch decomposition graphs. Several applications attest to the utility of our method and its robustness against noise.

Links

Export

BibTeX

@article{saikia14a, TITLE = {Extended Branch Decomposition Graphs: {Structural} Comparison of Scalar Data}, AUTHOR = {Saikia, Himangshu and Seidel, Hans-Peter and Weinkauf, Tino}, LANGUAGE = {eng}, DOI = {10.1111/cgf.12360}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2014}, DATE = {2014}, ABSTRACT = {We present a method to find repeating topological structures in scalar data sets. More precisely, we compare all subtrees of two merge trees against each other -- in an efficient manner exploiting redundancy. This provides pair-wise distances between the topological structures defined by sub/superlevel sets, which can be exploited in several applications such as finding similar structures in the same data set, assessing periodic behavior in time-dependent data, and comparing the topology of two different data sets. To do so, we introduce a novel data structure called the extended branch decomposition graph, which is composed of the branch decompositions of all subtrees of the merge tree. Based on dynamic programming, we provide two highly efficient algorithms for computing and comparing extended branch decomposition graphs. Several applications attest to the utility of our method and its robustness against noise.}, JOURNAL = {Computer Graphics Forum (Proc. EuroVis)}, VOLUME = {33}, NUMBER = {3}, PAGES = {41--50}, BOOKTITLE = {Eurographics Conference on Visualization 2014 (EuroVis 2014)}, EDITOR = {Carr, Hamish and Rheingans, Penny and Schumann, Heidrun}, }

Endnote

%0 Journal Article %A Saikia, Himangshu %A Seidel, Hans-Peter %A Weinkauf, Tino %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Extended Branch Decomposition Graphs: Structural Comparison of Scalar Data : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-4FFB-A %R 10.1111/cgf.12360 %7 2014 %D 2014 %X We present a method to find repeating topological structures in scalar data sets. More precisely, we compare all subtrees of two merge trees against each other - in an efficient manner exploiting redundancy. This provides pair-wise distances between the topological structures defined by sub/superlevel sets, which can be exploited in several applications such as finding similar structures in the same data set, assessing periodic behavior in time-dependent data, and comparing the topology of two different data sets. To do so, we introduce a novel data structure called the extended branch decomposition graph, which is composed of the branch decompositions of all subtrees of the merge tree. Based on dynamic programming, we provide two highly efficient algorithms for computing and comparing extended branch decomposition graphs. Several applications attest to the utility of our method and its robustness against noise. %J Computer Graphics Forum %V 33 %N 3 %& 41 %P 41 - 50 %I Wiley-Blackwell %C Oxford %B Eurographics Conference on Visualization 2014 %O EuroVis 2014 Swansea, Wales, UK, June 9 – 13, 2014

Rhodin, H., Tompkin, J., Kim, K.I., Varanasi, K., Seidel, H.-P., and Theobalt, C. 2014. Interactive Motion Mapping for Real-time Character Control. Computer Graphics Forum (Proc. EUROGRAPHICS 2014)33, 2.

Links

Export

BibTeX

@article{RhodinCGF2014, TITLE = {Interactive Motion Mapping for Real-time Character Control}, AUTHOR = {Rhodin, Helge and Tompkin, James and Kim, Kwang In and Varanasi, Kiran and Seidel, Hans-Peter and Theobalt, Christian}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12325}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford, UK}, YEAR = {2014}, DATE = {2014-05}, JOURNAL = {Computer Graphics Forum (Proc. EUROGRAPHICS)}, VOLUME = {33}, NUMBER = {2}, PAGES = {273--282}, BOOKTITLE = {EUROGRAPHICS 2014}, EDITOR = {L{\'e}vy, Bruno and Kautz, Jan}, }

Endnote

%0 Journal Article %A Rhodin, Helge %A Tompkin, James %A Kim, Kwang In %A Varanasi, Kiran %A Seidel, Hans-Peter %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Interactive Motion Mapping for Real-time Character Control : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-8096-6 %F ISI: 000337543000028 %R 10.1111/cgf.12325 %7 2014 %D 2014 %J Computer Graphics Forum %V 33 %N 2 %& 273 %P 273 - 282 %I Wiley-Blackwell %C Oxford, UK %@ false %B EUROGRAPHICS 2014 %O The European Association for Computer Graphics 35th Annual Conference ; Strasbourg, France, April 7th – 11th, 2014 EUROGRAPHICS 2014 EG 2014

Palmas, G., Bachynskyi, M., Oulasvirta, A., Seidel, H.-P., and Weinkauf, T. 2014a. MovExp: A Versatile Visualization Tool for Human-Computer Interaction Studies with 3D Performance and Biomechanical Data. IEEE Transactions on Visualization and Computer Graphics (Proc. IEEE VIS 2014)20, 12.

Abstract

In Human-Computer Interaction (HCI), experts seek to evaluate and compare the performance and ergonomics of user interfaces. Recently, a novel cost-efficient method for estimating physical ergonomics and performance has been introduced to HCI. It is based on optical motion capture and biomechanical simulation. It provides a rich source for analyzing human movements summarized in a multidimensional data set. Existing visualization tools do not sufficiently support the HCI experts in analyzing this data. We identified two shortcomings. First, appropriate visual encodings are missing particularly for the biomechanical aspects of the data. Second, the physical setup of the user interface cannot be incorporated explicitly into existing tools. We present MovExp, a versatile visualization tool that supports the evaluation of user interfaces. In particular, it can be easily adapted by the HCI experts to include the physical setup that is being evaluated, and visualize the data on top of it. Furthermore, it provides a variety of visual encodings to communicate muscular loads, movement directions, and other specifics of HCI studies that employ motion capture and biomechanical simulation. In this design study, we follow a problem-driven research approach. Based on a formalization of the visualization needs and the data structure, we formulate technical requirements for the visualization tool and present novel solutions to the analysis needs of the HCI experts. We show the utility of our tool with four case studies from the daily work of our HCI experts.

Links

Export

BibTeX

@article{palmas14b, TITLE = {{MovExp}: A Versatile Visualization Tool for Human-Computer Interaction Studies with {3D} Performance and Biomechanical Data}, AUTHOR = {Palmas, Gregorio and Bachynskyi, Myroslav and Oulasvirta, Antti and Seidel, Hans-Peter and Weinkauf, Tino}, LANGUAGE = {eng}, ISSN = {1077-2626}, DOI = {10.1109/TVCG.2014.2346311}, PUBLISHER = {IEEE Computer Society}, ADDRESS = {Los Alamitos, CA}, YEAR = {2014}, DATE = {2014-12}, ABSTRACT = {In Human-Computer Interaction (HCI), experts seek to evaluate and compare the performance and ergonomics of user interfaces. Recently, a novel cost-efficient method for estimating physical ergonomics and performance has been introduced to HCI. It is based on optical motion capture and biomechanical simulation. It provides a rich source for analyzing human movements summarized in a multidimensional data set. Existing visualization tools do not sufficiently support the HCI experts in analyzing this data. We identified two shortcomings. First, appropriate visual encodings are missing particularly for the biomechanical aspects of the data. Second, the physical setup of the user interface cannot be incorporated explicitly into existing tools. We present MovExp, a versatile visualization tool that supports the evaluation of user interfaces. In particular, it can be easily adapted by the HCI experts to include the physical setup that is being evaluated, and visualize the data on top of it. Furthermore, it provides a variety of visual encodings to communicate muscular loads, movement directions, and other specifics of HCI studies that employ motion capture and biomechanical simulation. In this design study, we follow a problem-driven research approach. Based on a formalization of the visualization needs and the data structure, we formulate technical requirements for the visualization tool and present novel solutions to the analysis needs of the HCI experts. We show the utility of our tool with four case studies from the daily work of our HCI experts.}, JOURNAL = {IEEE Transactions on Visualization and Computer Graphics (Proc. IEEE VIS)}, VOLUME = {20}, NUMBER = {12}, PAGES = {2359--2368}, BOOKTITLE = {IEEE Visual Analytics Science \& Technology Conference, IEEE Information Visualization Conference, and IEEE Scientific Visualization Conference Proceedings 2014}, DEBUG = {author: Ebert, David; author: Hauser, Helwig; author: Heer, Jeffrey; author: North, Chris; author: Tory, Melanie; author: Qu, Huamin; author: Shen, Han-Wei; author: Ynnerman, Anders}, EDITOR = {Chen, Min}, }

Endnote

%0 Journal Article %A Palmas, Gregorio %A Bachynskyi, Myroslav %A Oulasvirta, Antti %A Seidel, Hans-Peter %A Weinkauf, Tino %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T MovExp: A Versatile Visualization Tool for Human-Computer Interaction Studies with 3D Performance and Biomechanical Data : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-4D4C-4 %R 10.1109/TVCG.2014.2346311 %7 2014 %D 2014 %X In Human-Computer Interaction (HCI), experts seek to evaluate and compare the performance and ergonomics of user interfaces. Recently, a novel cost-efficient method for estimating physical ergonomics and performance has been introduced to HCI. It is based on optical motion capture and biomechanical simulation. It provides a rich source for analyzing human movements summarized in a multidimensional data set. Existing visualization tools do not sufficiently support the HCI experts in analyzing this data. We identified two shortcomings. First, appropriate visual encodings are missing particularly for the biomechanical aspects of the data. Second, the physical setup of the user interface cannot be incorporated explicitly into existing tools. We present MovExp, a versatile visualization tool that supports the evaluation of user interfaces. In particular, it can be easily adapted by the HCI experts to include the physical setup that is being evaluated, and visualize the data on top of it. Furthermore, it provides a variety of visual encodings to communicate muscular loads, movement directions, and other specifics of HCI studies that employ motion capture and biomechanical simulation. In this design study, we follow a problem-driven research approach. Based on a formalization of the visualization needs and the data structure, we formulate technical requirements for the visualization tool and present novel solutions to the analysis needs of the HCI experts. We show the utility of our tool with four case studies from the daily work of our HCI experts. %J IEEE Transactions on Visualization and Computer Graphics %V 20 %N 12 %& 2359 %P 2359 - 2368 %I IEEE Computer Society %C Los Alamitos, CA %@ false %B IEEE Visual Analytics Science & Technology Conference, IEEE Information Visualization Conference, and IEEE Scientific Visualization Conference Proceedings 2014 %O Proceedings 2014 ; Paris, France, 9–14 November 2014 IEEE VIS 2014

Palmas, G., Bachynskyi, M., Oulasvirta, A., Seidel, H.-P., and Weinkauf, T. 2014b. An Edge-bundling Layout for Interactive Parallel Coordinates. PacificVis 2014, IEEE Pacific Visualization Symposium, IEEE Computer Society.

Abstract

Parallel Coordinates is an often used visualization method for multidimensional data sets. Its main challenges for large data sets are visual clutter and overplotting which hamper the recognition of patterns in the data. We present an edge-bundling method using density-based clustering for each dimension. This reduces clutter and provides a faster overview of clusters and trends. Moreover, it allows rendering the clustered lines using polygons, decreasing rendering time remarkably. In addition, we design interactions to support multidimensional clustering with this method. A user study shows improvements over the classic parallel coordinates plot in two user tasks: correlation estimation and subset tracing.

Links

Export

BibTeX

@inproceedings{palmas14a, TITLE = {An Edge-bundling Layout for Interactive Parallel Coordinates}, AUTHOR = {Palmas, Gregorio and Bachynskyi, Myroslav and Oulasvirta, Antti and Seidel, Hans-Peter and Weinkauf, Tino}, LANGUAGE = {eng}, DOI = {10.1109/PacificVis.2014.40}, PUBLISHER = {IEEE Computer Society}, YEAR = {2014}, DATE = {2014-03}, ABSTRACT = {Parallel Coordinates is an often used visualization method for multidimensional data sets. Its main challenges for large data sets are visual clutter and overplotting which hamper the recognition of patterns in the data. We present an edge-bundling method using density-based clustering for each dimension. This reduces clutter and provides a faster overview of clusters and trends. Moreover, it allows rendering the clustered lines using polygons, decreasing rendering time remarkably. In addition, we design interactions to support multidimensional clustering with this method. A user study shows improvements over the classic parallel coordinates plot in two user tasks: correlation estimation and subset tracing.}, BOOKTITLE = {PacificVis 2014, IEEE Pacific Visualization Symposium}, PAGES = {57--64}, ADDRESS = {Yokohama, Japan}, }

Endnote

%0 Conference Proceedings %A Palmas, Gregorio %A Bachynskyi, Myroslav %A Oulasvirta, Antti %A Seidel, Hans-Peter %A Weinkauf, Tino %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T An Edge-bundling Layout for Interactive Parallel Coordinates : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-4D29-0 %R 10.1109/PacificVis.2014.40 %D 2014 %B IEEE Pacific Visualization Symposium %Z date of event: 2014-03-04 - 2014-03-07 %C Yokohama, Japan %X Parallel Coordinates is an often used visualization method for multidimensional data sets. Its main challenges for large data sets are visual clutter and overplotting which hamper the recognition of patterns in the data. We present an edge-bundling method using density-based clustering for each dimension. This reduces clutter and provides a faster overview of clusters and trends. Moreover, it allows rendering the clustered lines using polygons, decreasing rendering time remarkably. In addition, we design interactions to support multidimensional clustering with this method. A user study shows improvements over the classic parallel coordinates plot in two user tasks: correlation estimation and subset tracing. %B PacificVis 2014 %P 57 - 64 %I IEEE Computer Society

Nalbach, O., Ritschel, T., and Seidel, H.-P. 2014a. Deep Screen Space for Indirect Lighting of Volumes. VMV 2014 Vision, Modeling and Visualization, Eurographics Association.

Links

Export

BibTeX

@inproceedings{DBLP:conf/vmv/NalbachRS14, TITLE = {Deep Screen Space for Indirect Lighting of Volumes}, AUTHOR = {Nalbach, Oliver and Ritschel, Tobias and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-3-905674-74-3}, DOI = {10.2312/vmv.20141287}, PUBLISHER = {Eurographics Association}, YEAR = {2014}, DATE = {2014}, BOOKTITLE = {VMV 2014 Vision, Modeling and Visualization}, EDITOR = {Bender, Jan and Kuijper, Arjan and von Landesberger, Tatiana and Theisel, Holger and Urban, Philipp}, PAGES = {143--150}, ADDRESS = {Darmstadt, Germany}, }

Endnote

%0 Conference Proceedings %A Nalbach, Oliver %A Ritschel, Tobias %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Deep Screen Space for Indirect Lighting of Volumes : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-4D6C-B %R 10.2312/vmv.20141287 %D 2014 %B 19th International Workshop on Vision, Modeling and Visualization %Z date of event: 2014-10-08 - 2014-10-10 %C Darmstadt, Germany %B VMV 2014 Vision, Modeling and Visualization %E Bender, Jan; Kuijper, Arjan; von Landesberger, Tatiana; Theisel, Holger; Urban, Philipp %P 143 - 150 %I Eurographics Association %@ 978-3-905674-74-3 %U http://dx.doi.org/10.2312/vmv.20141287

Nalbach, O., Ritschel, T., and Seidel, H.-P. 2014b. Deep Screen Space. Proceedings I3D 2014, ACM.

Links

Export

BibTeX

@inproceedings{Nalbach:2014:DSS:2556700.2556708, TITLE = {Deep Screen Space}, AUTHOR = {Nalbach, Oliver and Ritschel, Tobias and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-1-4503-2717-6}, URL = {http://doi.acm.org/10.1145/2556700.2556708}, DOI = {10.1145/2556700.2556708}, PUBLISHER = {ACM}, YEAR = {2014}, DATE = {2014}, BOOKTITLE = {Proceedings I3D 2014}, EDITOR = {Keyser, John and Sander, Pedro}, PAGES = {79--86}, ADDRESS = {San Francisco, CA, USA}, }

Endnote

%0 Conference Proceedings %A Nalbach, Oliver %A Ritschel, Tobias %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Deep Screen Space : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-4D74-8 %R 10.1145/2556700.2556708 %U http://doi.acm.org/10.1145/2556700.2556708 %D 2014 %B 18th Meeting of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games %Z date of event: 2014-03-14 - 2014-03-16 %C San Francisco, CA, USA %B Proceedings I3D 2014 %E Keyser, John; Sander, Pedro %P 79 - 86 %I ACM %@ 978-1-4503-2717-6

Lochmann, G., Reinert, B., Ritschel, T., Müller, S., and Seidel, H.-P. 2014. Real‐time Reflective and Refractive Novel‐view Synthesis. VMV 2014 Vision, Modeling and Visualization, Eurographics Association.

Links

Export

BibTeX

@inproceedings{LochmannVMV2014, TITLE = {Real-time Reflective and Refractive Novel-view Synthesis}, AUTHOR = {Lochmann, Gerrit and Reinert, Bernhard and Ritschel, Tobias and M{\"u}ller, Stefan and Seidel, Hans-Peter}, LANGUAGE = {eng}, DOI = {10.2312/vmv.20141270}, PUBLISHER = {Eurographics Association}, YEAR = {2014}, DATE = {2014}, BOOKTITLE = {VMV 2014 Vision, Modeling and Visualization}, EDITOR = {Bender, Jan and Kuijper, Arjan and Landesberger, Tatiana and Theisel, Holger and Urban, Philipp}, PAGES = {9--16}, ADDRESS = {Darmstadt, Germany}, }

Endnote

%0 Conference Proceedings %A Lochmann, Gerrit %A Reinert, Bernhard %A Ritschel, Tobias %A Müller, Stefan %A Seidel, Hans-Peter %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Real‐time Reflective and Refractive Novel‐view Synthesis : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-533E-6 %R 10.2312/vmv.20141270 %D 2014 %B 19th International Workshop on Vision, Modeling and Visualization %Z date of event: 2014-10-08 - 2014-10-10 %C Darmstadt, Germany %B VMV 2014 Vision, Modeling and Visualization %E Bender, Jan; Kuijper, Arjan; Landesberger, Tatiana; Theisel, Holger; Urban, Philipp %P 9 - 16 %I Eurographics Association %U http://dx.doi.org/10.2312/vmv.20141270

Kurz, C., Wu, X., Wand, M., Thormählen, T., Kohli, P., and Seidel, H.-P. 2014. Symmetry-aware Template Deformation and Fitting. Computer Graphics Forum33, 6.

Links

Export

BibTeX

@article{Kurz2014, TITLE = {Symmetry-aware Template Deformation and Fitting}, AUTHOR = {Kurz, Christian and Wu, Xiaokun and Wand, Michael and Thorm{\"a}hlen, Thorsten and Kohli, P. and Seidel, Hans-Peter}, LANGUAGE = {eng}, DOI = {10.1111/cgf.12344}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2014}, DATE = {2014}, JOURNAL = {Computer Graphics Forum}, VOLUME = {33}, NUMBER = {6}, PAGES = {205--219}, }

Endnote

%0 Journal Article %A Kurz, Christian %A Wu, Xiaokun %A Wand, Michael %A Thormählen, Thorsten %A Kohli, P. %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Symmetry-aware Template Deformation and Fitting : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-5D2B-D %R 10.1111/cgf.12344 %7 2014-03-20 %D 2014 %J Computer Graphics Forum %V 33 %N 6 %& 205 %P 205 - 219 %I Wiley-Blackwell %C Oxford

Kozlov, Y., Esturo, J.M., Seidel, H.-P., and Weinkauf, T. 2014. Regularized Harmonic Surface Deformation. http://arxiv.org/abs/1408.3326.

(arXiv: 1408.3326)

Abstract

Harmonic surface deformation is a well-known geometric modeling method that creates plausible deformations in an interactive manner. However, this method is susceptible to artifacts, in particular close to the deformation handles. These artifacts often correlate with strong gradients of the deformation energy.In this work, we propose a novel formulation of harmonic surface deformation, which incorporates a regularization of the deformation energy. To do so, we build on and extend a recently introduced generic linear regularization approach. It can be expressed as a change of norm for the linear optimization problem, i.e., the regularization is baked into the optimization. This minimizes the implementation complexity and has only a small impact on runtime. Our results show that a moderate use of regularization suppresses many deformation artifacts common to the well-known harmonic surface deformation method, without introducing new artifacts.

Links

Export

BibTeX

@online{kozlov14, TITLE = {Regularized Harmonic Surface Deformation}, AUTHOR = {Kozlov, Yeara and Esturo, Janick Martinez and Seidel, Hans-Peter and Weinkauf, Tino}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1408.3326}, EPRINT = {1408.3326}, EPRINTTYPE = {arXiv}, YEAR = {2014}, ABSTRACT = {Harmonic surface deformation is a well-known geometric modeling method that creates plausible deformations in an interactive manner. However, this method is susceptible to artifacts, in particular close to the deformation handles. These artifacts often correlate with strong gradients of the deformation energy.In this work, we propose a novel formulation of harmonic surface deformation, which incorporates a regularization of the deformation energy. To do so, we build on and extend a recently introduced generic linear regularization approach. It can be expressed as a change of norm for the linear optimization problem, i.e., the regularization is baked into the optimization. This minimizes the implementation complexity and has only a small impact on runtime. Our results show that a moderate use of regularization suppresses many deformation artifacts common to the well-known harmonic surface deformation method, without introducing new artifacts.}, }

Endnote

%0 Report %A Kozlov, Yeara %A Esturo, Janick Martinez %A Seidel, Hans-Peter %A Weinkauf, Tino %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Regularized Harmonic Surface Deformation : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-49F5-A %U http://arxiv.org/abs/1408.3326 %D 2014 %X Harmonic surface deformation is a well-known geometric modeling method that creates plausible deformations in an interactive manner. However, this method is susceptible to artifacts, in particular close to the deformation handles. These artifacts often correlate with strong gradients of the deformation energy.In this work, we propose a novel formulation of harmonic surface deformation, which incorporates a regularization of the deformation energy. To do so, we build on and extend a recently introduced generic linear regularization approach. It can be expressed as a change of norm for the linear optimization problem, i.e., the regularization is baked into the optimization. This minimizes the implementation complexity and has only a small impact on runtime. Our results show that a moderate use of regularization suppresses many deformation artifacts common to the well-known harmonic surface deformation method, without introducing new artifacts. %K Computer Science, Graphics, cs.GR

Klehm, O., Seidel, H.-P., and Eisemann, E. 2014a. Filter-based Real-time Single Scattering using Rectified Shadow Maps. Journal of Computer Graphics Techniques3, 3.

Links

Export

BibTeX

@article{fbss_jcgtKlehm2014, TITLE = {Filter-based Real-time Single Scattering using Rectified Shadow Maps}, AUTHOR = {Klehm, Oliver and Seidel, Hans-Peter and Eisemann, Elmar}, LANGUAGE = {eng}, ISSN = {2331-7418}, URL = {http://jcgt.org/published/0003/03/02/}, PUBLISHER = {Williams College}, ADDRESS = {Williamstown, MA}, YEAR = {2014}, DATE = {2014-08}, JOURNAL = {Journal of Computer Graphics Techniques}, VOLUME = {3}, NUMBER = {3}, PAGES = {7--34}, }

Endnote

%0 Journal Article %A Klehm, Oliver %A Seidel, Hans-Peter %A Eisemann, Elmar %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Filter-based Real-time Single Scattering using Rectified Shadow Maps : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-51B3-E %U http://jcgt.org/published/0003/03/02/ %7 2014 %D 2014 %J Journal of Computer Graphics Techniques %O JCGT %V 3 %N 3 %& 7 %P 7 - 34 %I Williams College %C Williamstown, MA %@ false %U http://jcgt.org/published/0003/03/02/

Klehm, O., Seidel, H.-P., and Eisemann, E. 2014b. Prefiltered Single Scattering. Proceedings I3D 2014, ACM.

Links

Export

BibTeX

@inproceedings{Klehm:2014:PSS:2556700.2556704, TITLE = {Prefiltered Single Scattering}, AUTHOR = {Klehm, Oliver and Seidel, Hans-Peter and Eisemann, Elmar}, LANGUAGE = {eng}, ISBN = {978-1-4503-2717-6}, DOI = {10.1145/2556700.2556704}, PUBLISHER = {ACM}, YEAR = {2014}, DATE = {2014}, BOOKTITLE = {Proceedings I3D 2014}, EDITOR = {Keyser, John and Sander, Pedro}, PAGES = {71--78}, ADDRESS = {San Francisco, CA, USA}, }

Endnote

%0 Conference Proceedings %A Klehm, Oliver %A Seidel, Hans-Peter %A Eisemann, Elmar %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Prefiltered Single Scattering : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-51C5-6 %R 10.1145/2556700.2556704 %D 2014 %B 18th Meeting of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games %Z date of event: 2014-03-14 - 2014-03-16 %C San Francisco, CA, USA %K participating media, scattering, shadow test %B Proceedings I3D 2014 %E Keyser, John; Sander, Pedro %P 71 - 78 %I ACM %@ 978-1-4503-2717-6

Klehm, O., Ihrke, I., Seidel, H.-P., and Eisemann, E. 2014c. Property and Lighting Manipulations for Static Volume Stylization Using a Painting Metaphor. IEEE Transactions on Visualization and Computer Graphics20, 7.

Links

Export

BibTeX

@article{PLM-tvcg_Klehm2014, TITLE = {Property and Lighting Manipulations for Static Volume Stylization Using a Painting Metaphor}, AUTHOR = {Klehm, Oliver and Ihrke, Ivo and Seidel, Hans-Peter and Eisemann, Elmar}, LANGUAGE = {eng}, ISSN = {1077-2626}, DOI = {10.1109/TVCG.2014.13}, PUBLISHER = {IEEE Computer Society}, ADDRESS = {Los Alamitos, CA}, YEAR = {2014}, DATE = {2014-07}, JOURNAL = {IEEE Transactions on Visualization and Computer Graphics}, VOLUME = {20}, NUMBER = {7}, PAGES = {983--995}, }

Endnote

%0 Journal Article %A Klehm, Oliver %A Ihrke, Ivo %A Seidel, Hans-Peter %A Eisemann, Elmar %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Property and Lighting Manipulations for Static Volume Stylization Using a Painting Metaphor : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-51CA-B %R 10.1109/TVCG.2014.13 %7 2014 %D 2014 %K rendering (computer graphics);artistic control;environmental lighting;image component;lighting manipulations;noise function parameters;painting metaphor;property manipulations;realistic rendering;static volume stylization;static volumes;tomographic reconstruction;volume appearance;volume properties;volumetric rendering equation;Equations;Image reconstruction;Lighting;Mathematical model;Optimization;Rendering (computer graphics);Scattering;Artist control;optimization;participating media %J IEEE Transactions on Visualization and Computer Graphics %V 20 %N 7 %& 983 %P 983 - 995 %I IEEE Computer Society %C Los Alamitos, CA %@ false

Kellnhofer, P., Ritschel, T., Myszkowski, K., and Seidel, H.-P. 2014a. Improving Perception of Binocular Stereo Motion on 3D Display Devices. Stereoscopic Displays and Applications XXV, SPIE.

Abstract

This paper studies the presentation of moving stereo images on different display devices. We address three representative issues. First, we propose temporal compensation for the Pulfrich effect found when using anaglyph glasses. Second, we describe, how content-adaptive capture protocols can reduce false motion-in-depth sensation for time-multiplexing based displays. Third, we conclude with a recommendation how to improve rendering of synthetic stereo animations.

Links

Export

BibTeX

@inproceedings{Kellnhofer2014a, TITLE = {Improving Perception of Binocular Stereo Motion on {3D} Display Devices}, AUTHOR = {Kellnhofer, Petr and Ritschel, Tobias and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0277-786X}, ISBN = {9780819499288}, DOI = {10.1117/12.2032389}, PUBLISHER = {SPIE}, YEAR = {2014}, DATE = {2014}, ABSTRACT = {This paper studies the presentation of moving stereo images on different display devices. We address three representative issues. First, we propose temporal compensation for the Pulfrich effect found when using anaglyph glasses. Second, we describe, how content-adaptive capture protocols can reduce false motion-in-depth sensation for time-multiplexing based displays. Third, we conclude with a recommendation how to improve rendering of synthetic stereo animations.}, BOOKTITLE = {Stereoscopic Displays and Applications XXV}, EDITOR = {Woods, Andrew J. and Holliman, Nicolas S. and Favalora, Gregg E.}, PAGES = {1--11}, EID = {901116}, SERIES = {Proceedings of SPIE-IS\&T Electronic Imaging}, VOLUME = {9011}, ADDRESS = {San Francisco, CA, USA}, }

Endnote

Kellnhofer, P., Ritschel, T., Vangorp, P., Myszkowski, K., and Seidel, H.-P. 2014b. Stereo Day-for-Night: Retargeting Disparity for Scotopic Vision. ACM Transactions on Applied Perception11, 3.

Links

Export

BibTeX

@article{kellnhofer:2014c:DarkStereo, TITLE = {Stereo Day-for-Night: Retargeting Disparity for Scotopic Vision}, AUTHOR = {Kellnhofer, Petr and Ritschel, Tobias and Vangorp, Peter and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {1544-3558}, DOI = {10.1145/2644813}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2014}, DATE = {2014}, JOURNAL = {ACM Transactions on Applied Perception}, VOLUME = {11}, NUMBER = {3}, EID = {15}, }

Endnote

%0 Journal Article %A Kellnhofer, Petr %A Ritschel, Tobias %A Vangorp, Peter %A Myszkowski, Karol %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Stereo Day-for-Night: Retargeting Disparity for Scotopic Vision : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0023-EE0E-E %R 10.1145/2644813 %7 2014 %D 2014 %J ACM Transactions on Applied Perception %V 11 %N 3 %Z sequence number: 15 %I ACM %C New York, NY %@ false

Günther, D., Jacobson, A., Reininghaus, J., Seidel, H.-P., Sorkine-Hornung, O., and Weinkauf, T. 2014. Fast and Memory-efficient Topological Denoising of 2D and 3D Scalar Fields. IEEE Transactions on Visualization and Computer Graphics (Proc. IEEE VIS 2014)20, 12.

Links

Export

BibTeX

@article{guenther14c, TITLE = {Fast and Memory-efficient Topological Denoising of {2D} and {3D} Scalar Fields}, AUTHOR = {G{\"u}nther, David and Jacobson, Alec and Reininghaus, Jan and Seidel, Hans-Peter and Sorkine-Hornung, Olga and Weinkauf, Tino}, LANGUAGE = {eng}, ISSN = {1077-2626}, DOI = {10.1109/TVCG.2014.2346432}, PUBLISHER = {IEEE Computer Society}, ADDRESS = {Los Alamitos, CA}, YEAR = {2014}, DATE = {2014-12}, JOURNAL = {IEEE Transactions on Visualization and Computer Graphics (Proc. IEEE VIS)}, VOLUME = {20}, NUMBER = {12}, PAGES = {2585--2594}, BOOKTITLE = {IEEE Visual Analytics Science \& Technology Conference, IEEE Information Visualization Conference, and IEEE Scientific Visualization Conference Proceedings 2014}, DEBUG = {author: Ebert, David; author: Hauser, Helwig; author: Heer, Jeffrey; author: North, Chris; author: Tory, Melanie; author: Qu, Huamin; author: Shen, Han-Wei; author: Ynnerman, Anders}, EDITOR = {Chen, Min}, }

Endnote

%0 Journal Article %A Günther, David %A Jacobson, Alec %A Reininghaus, Jan %A Seidel, Hans-Peter %A Sorkine-Hornung, Olga %A Weinkauf, Tino %+ External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Fast and Memory-efficient Topological Denoising of 2D and 3D Scalar Fields : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-5349-E %R 10.1109/TVCG.2014.2346432 %7 2014 %D 2014 %J IEEE Transactions on Visualization and Computer Graphics %V 20 %N 12 %& 2585 %P 2585 - 2594 %I IEEE Computer Society %C Los Alamitos, CA %@ false %B IEEE Visual Analytics Science & Technology Conference, IEEE Information Visualization Conference, and IEEE Scientific Visualization Conference Proceedings 2014 %O Proceedings 2014 ; Paris, France, 9–14 November 2014 IEEE VIS 2014

Guenther, D., Reininghaus, J., Seidel, H.-P., and Weinkauf, T. 2014. Notes on the Simplification of the Morse-Smale Complex. Topological Methods in Data Analysis and Visualization III (TopoInVis 2013), Springer.

Abstract

The Morse-Smale complex can be either explicitly or implicitly represented. Depending on the type of representation, the simplification of the Morse-Smale complex works differently. In the explicit representation, the Morse-Smale complex is directly simplified by explicitly reconnecting the critical points during the simplification. In the implicit representation, on the other hand, the Morse-Smale complex is given by a combinatorial gradient field. In this setting, the simplification changes the combinatorial flow, which yields an indirect simplification of the Morse-Smale complex. The topological complexity of the Morse-Smale complex is reduced in both representations. However, the simplifications generally yield different results. In this paper, we emphasize the differences between these two representations, and provide a high-level discussion about their advantages and limitations.

Links

Export

BibTeX

@inproceedings{guenther13a, TITLE = {Notes on the Simplification of the {Morse}-{Smale} Complex}, AUTHOR = {Guenther, David and Reininghaus, Jan and Seidel, Hans-Peter and Weinkauf, Tino}, LANGUAGE = {eng}, ISBN = {978-3-319-04098-1}, DOI = {10.1007/978-3-319-04099-8_9}, PUBLISHER = {Springer}, YEAR = {2013}, DATE = {2014}, ABSTRACT = {The Morse-Smale complex can be either explicitly or implicitly represented. Depending on the type of representation, the simplification of the Morse-Smale complex works differently. In the explicit representation, the Morse-Smale complex is directly simplified by explicitly reconnecting the critical points during the simplification. In the implicit representation, on the other hand, the Morse-Smale complex is given by a combinatorial gradient field. In this setting, the simplification changes the combinatorial flow, which yields an indirect simplification of the Morse-Smale complex. The topological complexity of the Morse-Smale complex is reduced in both representations. However, the simplifications generally yield different results. In this paper, we emphasize the differences between these two representations, and provide a high-level discussion about their advantages and limitations.}, BOOKTITLE = {Topological Methods in Data Analysis and Visualization III (TopoInVis 2013)}, EDITOR = {Bremer, Peer-Timo and Hotz, Ingrid and Pascucci, Valerio and Peikert, Ronald}, PAGES = {135--150}, SERIES = {Mathematics and Visualization}, ADDRESS = {Davis, CA, USA}, }

Endnote

%0 Conference Proceedings %A Guenther, David %A Reininghaus, Jan %A Seidel, Hans-Peter %A Weinkauf, Tino %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Notes on the Simplification of the Morse-Smale Complex : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-52F3-3 %R 10.1007/978-3-319-04099-8_9 %D 2014 %B TopoInVis %Z date of event: 2013-03-04 - 2013-03-06 %C Davis, CA, USA %X The Morse-Smale complex can be either explicitly or implicitly represented. Depending on the type of representation, the simplification of the Morse-Smale complex works differently. In the explicit representation, the Morse-Smale complex is directly simplified by explicitly reconnecting the critical points during the simplification. In the implicit representation, on the other hand, the Morse-Smale complex is given by a combinatorial gradient field. In this setting, the simplification changes the combinatorial flow, which yields an indirect simplification of the Morse-Smale complex. The topological complexity of the Morse-Smale complex is reduced in both representations. However, the simplifications generally yield different results. In this paper, we emphasize the differences between these two representations, and provide a high-level discussion about their advantages and limitations. %B Topological Methods in Data Analysis and Visualization III %E Bremer, Peer-Timo; Hotz, Ingrid; Pascucci, Valerio; Peikert, Ronald %P 135 - 150 %I Springer %@ 978-3-319-04098-1 %B Mathematics and Visualization %U https://rdcu.be/dK3QD

Gryaditskaya, Y., Pouli, T., Reinhard, E., and Seidel, H.-P. 2014. Sky Based Light Metering for High Dynamic Range Images. Computer Graphics Forum (Proc. Pacific Graphics 2014)33, 7.

Abstract

Image calibration requires both linearization of pixel values and scaling so that values in the image correspond to real-world luminances. In this paper we focus on the latter and rather than rely on camera characterization, we calibrate images by analysing their content and metadata, obviating the need for expensive measuring devices or modeling of lens and camera combinations. Our analysis correlates sky pixel values to luminances that would be expected based on geographical metadata. Combined with high dynamic range (HDR) imaging, which gives us linear pixel data, our algorithm allows us to find absolute luminance values for each pixel—effectively turning digital cameras into absolute light meters. To validate our algorithm we have collected and annotated a calibrated set of HDR images and compared our estimation with several other approaches, showing that our approach is able to more accurately recover absolute luminance. We discuss various applications and demonstrate the utility of our method in the context of calibrated color appearance reproduction and lighting design.

Links

Export

BibTeX

@article{CGF:Gryad:14, TITLE = {Sky Based Light Metering for High Dynamic Range Images}, AUTHOR = {Gryaditskaya, Yulia and Pouli, Tania and Reinhard, Erik and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {1467-8659}, DOI = {10.1111/cgf.12474}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford, UK}, YEAR = {2014}, DATE = {2014}, ABSTRACT = {Image calibration requires both linearization of pixel values and scaling so that values in the image correspond to real-world luminances. In this paper we focus on the latter and rather than rely on camera characterization, we calibrate images by analysing their content and metadata, obviating the need for expensive measuring devices or modeling of lens and camera combinations. Our analysis correlates sky pixel values to luminances that would be expected based on geographical metadata. Combined with high dynamic range (HDR) imaging, which gives us linear pixel data, our algorithm allows us to find absolute luminance values for each pixel---effectively turning digital cameras into absolute light meters. To validate our algorithm we have collected and annotated a calibrated set of HDR images and compared our estimation with several other approaches, showing that our approach is able to more accurately recover absolute luminance. We discuss various applications and demonstrate the utility of our method in the context of calibrated color appearance reproduction and lighting design.}, JOURNAL = {Computer Graphics Forum (Proc. Pacific Graphics)}, VOLUME = {33}, NUMBER = {7}, PAGES = {61--69}, BOOKTITLE = {22nd Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2014)}, }

Endnote

%0 Journal Article %A Gryaditskaya, Yulia %A Pouli, Tania %A Reinhard, Erik %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Sky Based Light Metering for High Dynamic Range Images : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-6C64-1 %R 10.1111/cgf.12474 %7 2014 %D 2014 %X Image calibration requires both linearization of pixel values and scaling so that values in the image correspond to real-world luminances. In this paper we focus on the latter and rather than rely on camera characterization, we calibrate images by analysing their content and metadata, obviating the need for expensive measuring devices or modeling of lens and camera combinations. Our analysis correlates sky pixel values to luminances that would be expected based on geographical metadata. Combined with high dynamic range (HDR) imaging, which gives us linear pixel data, our algorithm allows us to find absolute luminance values for each pixel—effectively turning digital cameras into absolute light meters. To validate our algorithm we have collected and annotated a calibrated set of HDR images and compared our estimation with several other approaches, showing that our approach is able to more accurately recover absolute luminance. We discuss various applications and demonstrate the utility of our method in the context of calibrated color appearance reproduction and lighting design. %J Computer Graphics Forum %V 33 %N 7 %& 61 %P 61 - 69 %I Wiley-Blackwell %C Oxford, UK %@ false %B 22nd Pacific Conference on Computer Graphics and Applications %O Pacific Graphics 2014 PG 2014 8 to 10 Oct 2014, Seoul, South Korea

Elek, O., Ritschel, T., Dachsbacher, C., and Seidel, H.-P. 2014a. Interactive Light Scattering with Principal-ordinate Propagation. Graphics Interface 2014, Canadian Information Processing Society.

Links

Export

BibTeX

@inproceedings{ElekGI2014, TITLE = {Interactive Light Scattering with Principal-ordinate Propagation}, AUTHOR = {Elek, Oskar and Ritschel, Tobias and Dachsbacher, Carsten and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-1-4822-6003-8}, URL = {https://graphicsinterface.org/proceedings/gi2014/gi2014-11/}, PUBLISHER = {Canadian Information Processing Society}, YEAR = {2014}, DATE = {2014}, BOOKTITLE = {Graphics Interface 2014}, EDITOR = {Kry, Paul G. and Bunt, Andrea}, PAGES = {87--94}, ADDRESS = {Montreal, Canada}, }

Endnote

%0 Conference Proceedings %A Elek, Oskar %A Ritschel, Tobias %A Dachsbacher, Carsten %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Interactive Light Scattering with Principal-ordinate Propagation : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-5181-D %U https://graphicsinterface.org/proceedings/gi2014/gi2014-11/ %D 2014 %B Graphics Interface %Z date of event: 2014-05-07 - 2014-05-09 %C Montreal, Canada %B Graphics Interface 2014 %E Kry, Paul G.; Bunt, Andrea %P 87 - 94 %I Canadian Information Processing Society %@ 978-1-4822-6003-8

Elek, O., Bauszat, P., Ritschel, T., Magnor, M., and Seidel, H.-P. 2014b. Progressive Spectral Ray Differentials. VMV 2014 Vision, Modeling and Visualization, Eurographics Association.

Links

Export

BibTeX

@inproceedings{ElekVMV2014, TITLE = {Progressive Spectral Ray Differentials}, AUTHOR = {Elek, Oskar and Bauszat, Pablo and Ritschel, Tobias and Magnor, Marcus and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-3-905674-74-3}, DOI = {10.2312/vmv.20141288}, PUBLISHER = {Eurographics Association}, YEAR = {2014}, DATE = {2014}, BOOKTITLE = {VMV 2014 Vision, Modeling and Visualization}, PAGES = {151--158}, ADDRESS = {Darmstadt, Germany}, }

Endnote

%0 Conference Proceedings %A Elek, Oskar %A Bauszat, Pablo %A Ritschel, Tobias %A Magnor, Marcus %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Progressive Spectral Ray Differentials : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-5176-5 %R 10.2312/vmv.20141288 %D 2014 %B 19th International Workshop on Vision, Modeling and Visualization %Z date of event: 2014-10-08 - 2014-10-10 %C Darmstadt, Germany %B VMV 2014 Vision, Modeling and Visualization %P 151 - 158 %I Eurographics Association %@ 978-3-905674-74-3

Elek, O., Ritschel, T., Dachsbacher, C., and Seidel, H.-P. 2014c. Principal-ordinates Propagation for Real-time Rendering of Participating Media. Computers & Graphics45.

Links

Export

BibTeX

@article{ElekCAG2014, TITLE = {Principal-ordinates Propagation for Real-time Rendering of Participating Media}, AUTHOR = {Elek, Oskar and Ritschel, Tobias and Dachsbacher, Carsten and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0097-8493}, DOI = {10.1016/j.cag.2014.08.003}, PUBLISHER = {Elsevier}, ADDRESS = {Amsterdam}, YEAR = {2014}, DATE = {2014}, JOURNAL = {Computers \& Graphics}, VOLUME = {45}, PAGES = {28--39}, }

Endnote

%0 Journal Article %A Elek, Oskar %A Ritschel, Tobias %A Dachsbacher, Carsten %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Principal-ordinates Propagation for Real-time Rendering of Participating Media : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-516D-C %R 10.1016/j.cag.2014.08.003 %7 2014-09-06 %D 2014 %J Computers & Graphics %V 45 %& 28 %P 28 - 39 %I Elsevier %C Amsterdam %@ false

Elek, O., Bauszat, P., Ritschel, T., Magnor, M., and Seidel, H.-P. 2014d. Spectral Ray Differentials. Computer Graphics Forum (Proc. Eurographics Symposium on Rendering 2014)33, 4.

Links

Export

BibTeX

@article{Elek2014EGSR, TITLE = {Spectral Ray Differentials}, AUTHOR = {Elek, Oskar and Bauszat, Pablo and Ritschel, Tobias and Magnor, Marcus and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12418}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2014}, DATE = {2014}, JOURNAL = {Computer Graphics Forum (Proc. Eurographics Symposium on Rendering)}, VOLUME = {33}, NUMBER = {4}, PAGES = {113--122}, BOOKTITLE = {Eurographics Symposium on Rendering 2014}, EDITOR = {Wojciech, Jarosz and Peers, Pieter}, }

Endnote

%0 Journal Article %A Elek, Oskar %A Bauszat, Pablo %A Ritschel, Tobias %A Magnor, Marcus %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Spectral Ray Differentials : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-4A77-B %R 10.1111/cgf.12418 %7 2014 %D 2014 %J Computer Graphics Forum %V 33 %N 4 %& 113 %P 113 - 122 %I Wiley-Blackwell %C Oxford %@ false %B Eurographics Symposium on Rendering 2014 %O Eurographics Symposium on Rendering 2014 EGSR 2014 Lyon, France, June 25th - 27th, 2014

Dabala, L., Kellnhofer, P., Ritschel, T., et al. 2014. Manipulating Refractive and Reflective Binocular Disparity. Computer Graphics Forum (Proc. EUROGRAPHICS 2014)33, 2.

Abstract

Presenting stereoscopic content on 3D displays is a challenging task, usually requiring manual adjustments. A number of techniques have been developed to aid this process, but they account for binocular disparity of surfaces that are diffuse and opaque only. However, combinations of transparent as well as specular materials are common in the real and virtual worlds, and pose a significant problem. For example, excessive disparities can be created which cannot be fused by the observer. Also, multiple stereo interpretations become possible, e. g., for glass, that both reflects and refracts, which may confuse the observer and result in poor 3D experience. In this work, we propose an efficient method for analyzing and controlling disparities in computer-generated images of such scenes where surface positions and a layer decomposition are available. Instead of assuming a single per-pixel disparity value, we estimate all possibly perceived disparities at each image location. Based on this representation, we define an optimization to find the best per-pixel camera parameters, assuring that all disparities can be easily fused by a human. A preliminary perceptual study indicates, that our approach combines comfortable viewing with realistic depiction of typical specular scenes.

Links

Export

BibTeX

@article{Kellnhofer2014b, TITLE = {Manipulating Refractive and Reflective Binocular Disparity}, AUTHOR = {Dabala, Lukasz and Kellnhofer, Petr and Ritschel, Tobias and Didyk, Piotr and Templin, Krzysztof and Rokita, Przemyslaw and Myszkowski, Karol and Seidel, Hans-Peter}, LANGUAGE = {eng}, DOI = {10.1111/cgf.12290}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford, UK}, YEAR = {2014}, DATE = {2014}, ABSTRACT = {Presenting stereoscopic content on 3D displays is a challenging task, usually requiring manual adjustments. A number of techniques have been developed to aid this process, but they account for binocular disparity of surfaces that are diffuse and opaque only. However, combinations of transparent as well as specular materials are common in the real and virtual worlds, and pose a significant problem. For example, excessive disparities can be created which cannot be fused by the observer. Also, multiple stereo interpretations become possible, e. g., for glass, that both reflects and refracts, which may confuse the observer and result in poor 3D experience. In this work, we propose an efficient method for analyzing and controlling disparities in computer-generated images of such scenes where surface positions and a layer decomposition are available. Instead of assuming a single per-pixel disparity value, we estimate all possibly perceived disparities at each image location. Based on this representation, we define an optimization to find the best per-pixel camera parameters, assuring that all disparities can be easily fused by a human. A preliminary perceptual study indicates, that our approach combines comfortable viewing with realistic depiction of typical specular scenes.}, JOURNAL = {Computer Graphics Forum (Proc. EUROGRAPHICS)}, VOLUME = {33}, NUMBER = {2}, PAGES = {53--62}, BOOKTITLE = {EUROGRAPHICS 2014}, EDITOR = {L{\'e}vy, Bruno and Kautz, Jan}, }

Endnote

%0 Journal Article %A Dabala, Lukasz %A Kellnhofer, Petr %A Ritschel, Tobias %A Didyk, Piotr %A Templin, Krzysztof %A Rokita, Przemyslaw %A Myszkowski, Karol %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Manipulating Refractive and Reflective Binocular Disparity : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0019-EEF9-6 %R 10.1111/cgf.12290 %7 2014-06-01 %D 2014 %X Presenting stereoscopic content on 3D displays is a challenging task, usually requiring manual adjustments. A number of techniques have been developed to aid this process, but they account for binocular disparity of surfaces that are diffuse and opaque only. However, combinations of transparent as well as specular materials are common in the real and virtual worlds, and pose a significant problem. For example, excessive disparities can be created which cannot be fused by the observer. Also, multiple stereo interpretations become possible, e. g., for glass, that both reflects and refracts, which may confuse the observer and result in poor 3D experience. In this work, we propose an efficient method for analyzing and controlling disparities in computer-generated images of such scenes where surface positions and a layer decomposition are available. Instead of assuming a single per-pixel disparity value, we estimate all possibly perceived disparities at each image location. Based on this representation, we define an optimization to find the best per-pixel camera parameters, assuring that all disparities can be easily fused by a human. A preliminary perceptual study indicates, that our approach combines comfortable viewing with realistic depiction of typical specular scenes. %J Computer Graphics Forum %V 33 %N 2 %& 53 %P 53 - 62 %I Wiley-Blackwell %C Oxford, UK %B EUROGRAPHICS 2014 %O The European Association for Computer Graphics 35th Annual Conference ; Strasbourg, France, April 7th – 11th, 2014 EUROGRAPHICS 2014 EG 2014

Brunton, A., Wand, M., Wuhrer, S., Seidel, H.-P., and Weinkauf, T. 2014. A Low-dimensional Representation for Robust Partial Isometric Correspondences Computation. Graphical Models76, 2.

Abstract

Intrinsic shape matching has become the standard approach for pose invariant correspondence estimation among deformable shapes. Most existing approaches assume global consistency. While global isometric matching is well understood, only a few heuristic solutions are known for partial matching. Partial matching is particularly important for robustness to topological noise, which is a common problem in real-world scanner data. We introduce a new approach to partial isometric matching based on the observation that isometries are fully determined by local information: a map of a single point and its tangent space fixes an isometry. We develop a new representation for partial isometric maps based on equivalence classes of correspondences between pairs of points and their tangent-spaces. We apply our approach to register partial point clouds and compare it to the state-of-the-art methods, where we obtain significant improvements over global methods for real-world data and stronger guarantees than previous partial matching algorithms.

Links

Export

BibTeX

@article{brunton13, TITLE = {A Low-dimensional Representation for Robust Partial Isometric Correspondences Computation}, AUTHOR = {Brunton, Alan and Wand, Michael and Wuhrer, Stefanie and Seidel, Hans-Peter and Weinkauf, Tino}, LANGUAGE = {eng}, ISSN = {1524-0703}, DOI = {10.1016/j.gmod.2013.11.003}, PUBLISHER = {Academic Press}, ADDRESS = {San Diego, CA}, YEAR = {2014}, DATE = {2014}, ABSTRACT = {Intrinsic shape matching has become the standard approach for pose invariant correspondence estimation among deformable shapes. Most existing approaches assume global consistency. While global isometric matching is well understood, only a few heuristic solutions are known for partial matching. Partial matching is particularly important for robustness to topological noise, which is a common problem in real-world scanner data. We introduce a new approach to partial isometric matching based on the observation that isometries are fully determined by local information: a map of a single point and its tangent space fixes an isometry. We develop a new representation for partial isometric maps based on equivalence classes of correspondences between pairs of points and their tangent-spaces. We apply our approach to register partial point clouds and compare it to the state-of-the-art methods, where we obtain significant improvements over global methods for real-world data and stronger guarantees than previous partial matching algorithms.}, JOURNAL = {Graphical Models}, VOLUME = {76}, NUMBER = {2}, PAGES = {70--85}, }

Endnote

%0 Journal Article %A Brunton, Alan %A Wand, Michael %A Wuhrer, Stefanie %A Seidel, Hans-Peter %A Weinkauf, Tino %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T A Low-dimensional Representation for Robust Partial Isometric Correspondences Computation : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0014-F6E9-5 %R 10.1016/j.gmod.2013.11.003 %7 2013-12-15 %D 2014 %X Intrinsic shape matching has become the standard approach for pose invariant correspondence estimation among deformable shapes. Most existing approaches assume global consistency. While global isometric matching is well understood, only a few heuristic solutions are known for partial matching. Partial matching is particularly important for robustness to topological noise, which is a common problem in real-world scanner data. We introduce a new approach to partial isometric matching based on the observation that isometries are fully determined by local information: a map of a single point and its tangent space fixes an isometry. We develop a new representation for partial isometric maps based on equivalence classes of correspondences between pairs of points and their tangent-spaces. We apply our approach to register partial point clouds and compare it to the state-of-the-art methods, where we obtain significant improvements over global methods for real-world data and stronger guarantees than previous partial matching algorithms. %J Graphical Models %V 76 %N 2 %& 70 %P 70 - 85 %I Academic Press %C San Diego, CA %@ false

2013

Wang, Z., Grochulla, M.P., Thormählen, T., and Seidel, H.-P. 2013. 3D Face Template Registration Using Normal Maps. 3DV 2013, International Conference on 3D Vision, IEEE Computer Society.

Links

Export

BibTeX

@inproceedings{Wang2013, TITLE = {{3D} Face Template Registration Using Normal Maps}, AUTHOR = {Wang, Zhongjie and Grochulla, Martin Peter and Thorm{\"a}hlen, Thorsten and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISBN = {978-0-7695-5067-1}, DOI = {10.1109/3DV.2013.46}, LOCALID = {Local-ID: 220FFD3372EB9C04C1257C6000528BF3-Wang2013}, PUBLISHER = {IEEE Computer Society}, YEAR = {2013}, DATE = {2013}, BOOKTITLE = {3DV 2013, International Conference on 3D Vision}, EDITOR = {Guerrero, Juan E.}, PAGES = {295--302}, ADDRESS = {Seattle, WA, USA}, }

Endnote

%0 Conference Proceedings %A Wang, Zhongjie %A Grochulla, Martin Peter %A Thormählen, Thorsten %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T 3D Face Template Registration Using Normal Maps : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0015-1CEC-B %R 10.1109/3DV.2013.46 %F OTHER: Local-ID: 220FFD3372EB9C04C1257C6000528BF3-Wang2013 %D 2013 %B International Conference on 3D Vision %Z date of event: 2013-06-29 - 2013-07-01 %C Seattle, WA, USA %B 3DV 2013 %E Guerrero, Juan E. %P 295 - 302 %I IEEE Computer Society %@ 978-0-7695-5067-1

Von Tycowicz, C., Schulz, C., Seidel, H.-P., and Hildebrandt, K. 2013. An Efficient Construction of Reduced Deformable Objects. ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia 2013)32, 6.

Abstract

Many efficient computational methods for physical simulation are based on model reduction. We propose new model reduction techniques for the \emphapproximation of reduced forces} and for the \emph{construction of reduced shape spaces of deformable objects that accelerate the construction of a reduced dynamical system, increase the accuracy of the approximation, and simplify the implementation of model reduction. Based on the techniques, we introduce schemes for real-time simulation of deformable objects and interactive deformation-based editing of triangle or tet meshes. We demonstrate the effectiveness of the new techniques in different experiments with elastic solids and shells and compare them to alternative approaches.

Links

Export

BibTeX

@article{Hildebrandt2013, TITLE = {An Efficient Construction of Reduced Deformable Objects}, AUTHOR = {von Tycowicz, Christoph and Schulz, Christian and Seidel, Hans-Peter and Hildebrandt, Klaus}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2508363.2508392}, LOCALID = {Local-ID: CBFBAC90E4E008EDC1257C240031E997-Hildebrandt2013}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2013}, DATE = {2013}, ABSTRACT = {Many efficient computational methods for physical simulation are based on model reduction. We propose new model reduction techniques for the \emphapproximation of reduced forces} and for the \emph{construction of reduced shape spaces of deformable objects that accelerate the construction of a reduced dynamical system, increase the accuracy of the approximation, and simplify the implementation of model reduction. Based on the techniques, we introduce schemes for real-time simulation of deformable objects and interactive deformation-based editing of triangle or tet meshes. We demonstrate the effectiveness of the new techniques in different experiments with elastic solids and shells and compare them to alternative approaches.}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia)}, VOLUME = {32}, NUMBER = {6}, PAGES = {1--10}, EID = {213}, BOOKTITLE = {Proceedings of ACM SIGGRAPH Asia 2013}, }

Endnote

%0 Journal Article %A von Tycowicz, Christoph %A Schulz, Christian %A Seidel, Hans-Peter %A Hildebrandt, Klaus %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T An Efficient Construction of Reduced Deformable Objects : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0015-3A34-A %R 10.1145/2508363.2508392 %F OTHER: Local-ID: CBFBAC90E4E008EDC1257C240031E997-Hildebrandt2013 %7 2013 %D 2013 %X Many efficient computational methods for physical simulation are based on model reduction. We propose new model reduction techniques for the \emphapproximation of reduced forces} and for the \emph{construction of reduced shape spaces of deformable objects that accelerate the construction of a reduced dynamical system, increase the accuracy of the approximation, and simplify the implementation of model reduction. Based on the techniques, we introduce schemes for real-time simulation of deformable objects and interactive deformation-based editing of triangle or tet meshes. We demonstrate the effectiveness of the new techniques in different experiments with elastic solids and shells and compare them to alternative approaches. %J ACM Transactions on Graphics %V 32 %N 6 %& 1 %P 1 - 10 %Z sequence number: 213 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH Asia 2013 %O ACM SIGGRAPH Asia 2013 Hong Kong, 19 - 22 November 2013

Sunkel, M., Jansen, S., Wand, M., and Seidel, H.-P. 2013. A Correlated Parts Model for Object Detection in Large 3D Scans. Computer Graphics Forum (Proc. EUROGRAPHICS 2013)32, 2.

Abstract

This paper addresses the problem of detecting objects in 3D scans according to object classes learned from sparse user annotation. We model objects belonging to a class by a set of fully correlated parts, encoding dependencies between local shapes of different parts as well as their relative spatial arrangement. For an efficient and comprehensive retrieval of instances belonging to a class of interest, we introduce a new approximate inference scheme and a corresponding planning procedure. We extend our technique to hierarchical composite structures, reducing training effort and modeling spatial relations between detected instances. We evaluate our method on a number of real-world 3D scans and demonstrate its benefits as well as the performance of the new inference algorithm.

Links

Export

BibTeX

@article{Sunkel2013, TITLE = {A Correlated Parts Model for Object Detection in Large {3D} Scans}, AUTHOR = {Sunkel, Martin and Jansen, Silke and Wand, Michael and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12040}, LOCALID = {Local-ID: 71E3D133D260E612C1257B0400475765-Sunkel2013}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford, UK}, YEAR = {2013}, DATE = {2013}, ABSTRACT = {This paper addresses the problem of detecting objects in 3D scans according to object classes learned from sparse user annotation. We model objects belonging to a class by a set of fully correlated parts, encoding dependencies between local shapes of different parts as well as their relative spatial arrangement. For an efficient and comprehensive retrieval of instances belonging to a class of interest, we introduce a new approximate inference scheme and a corresponding planning procedure. We extend our technique to hierarchical composite structures, reducing training effort and modeling spatial relations between detected instances. We evaluate our method on a number of real-world 3D scans and demonstrate its benefits as well as the performance of the new inference algorithm.}, JOURNAL = {Computer Graphics Forum (Proc. EUROGRAPHICS)}, VOLUME = {32}, NUMBER = {2}, PAGES = {205--214}, BOOKTITLE = {EUROGRAPHICS 2013}, EDITOR = {Poulin, P. and Navazo, I.}, }

Endnote

%0 Journal Article %A Sunkel, Martin %A Jansen, Silke %A Wand, Michael %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T A Correlated Parts Model for Object Detection in Large 3D Scans : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0015-1CE6-8 %R 10.1111/cgf.12040 %F OTHER: Local-ID: 71E3D133D260E612C1257B0400475765-Sunkel2013 %7 2013-05-06 %D 2013 %X This paper addresses the problem of detecting objects in 3D scans according to object classes learned from sparse user annotation. We model objects belonging to a class by a set of fully correlated parts, encoding dependencies between local shapes of different parts as well as their relative spatial arrangement. For an efficient and comprehensive retrieval of instances belonging to a class of interest, we introduce a new approximate inference scheme and a corresponding planning procedure. We extend our technique to hierarchical composite structures, reducing training effort and modeling spatial relations between detected instances. We evaluate our method on a number of real-world 3D scans and demonstrate its benefits as well as the performance of the new inference algorithm. %J Computer Graphics Forum %V 32 %N 2 %& 205 %P 205 - 214 %I Wiley-Blackwell %C Oxford, UK %@ false %B EUROGRAPHICS 2013 %O EG 2013 EUROGRAPHICS 2013 The European Association for Computer Graphics 34th Annual Conference ; Girona, Spain, May 6th – 10th, 2013

Scherbaum, K., Petterson, J., Feris, R.S., Blanz, V., and Seidel, H.-P. 2013. Fast Face Detector Training Using Tailored Views. ICCV 2013, IEEE International Conference on Computer Vision, IEEE Computer Society.

Links

Export

BibTeX

@inproceedings{Scherbaum2013, TITLE = {Fast Face Detector Training Using Tailored Views}, AUTHOR = {Scherbaum, Kristina and Petterson, James and Feris, Rogerio S. and Blanz, Volker and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {1550-5499}, ISBN = {978-1-4799-2839-2}, DOI = {10.1109/ICCV.2013.354}, LOCALID = {Local-ID: BBE1AD1B44792B41C1257C600050C266-Scherbaum2013}, PUBLISHER = {IEEE Computer Society}, YEAR = {2013}, DATE = {2013}, BOOKTITLE = {ICCV 2013, IEEE International Conference on Computer Vision}, PAGES = {2848--2855}, ADDRESS = {Sydney, Australia}, }

Endnote

%0 Conference Proceedings %A Scherbaum, Kristina %A Petterson, James %A Feris, Rogerio S. %A Blanz, Volker %A Seidel, Hans-Peter %+ Cluster of Excellence Multimodal Computing and Interaction External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Fast Face Detector Training Using Tailored Views : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0019-7AC0-9 %R 10.1109/ICCV.2013.354 %F OTHER: Local-ID: BBE1AD1B44792B41C1257C600050C266-Scherbaum2013 %D 2013 %B IEEE International Conference on Computer Vision %Z date of event: 2013-12-01 - 2013-12-08 %C Sydney, Australia %B ICCV 2013 %P 2848 - 2855 %I IEEE Computer Society %@ false

Reshetouski, I., Manakov, A., Bhandari, A., Raskar, R., Seidel, H.-P., and Ihrke, I. 2013. Discovering the Structure of a Planar Mirror System from Multiple Observations of a Single Point. 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2013), IEEE Computer Society.

Links

Export

BibTeX

@inproceedings{DBLP:conf/cvpr/ReshetouskiMBRSI13, TITLE = {Discovering the Structure of a Planar Mirror System from Multiple Observations of a Single Point}, AUTHOR = {Reshetouski, Ilya and Manakov, Alkhazur and Bhandari, Ayush and Raskar, Ramesh and Seidel, Hans-Peter and Ihrke, Ivo}, LANGUAGE = {eng}, ISBN = {978-1-5386-5672-3}, DOI = {10.1109/CVPR.2013.19}, PUBLISHER = {IEEE Computer Society}, YEAR = {2013}, DATE = {2013}, BOOKTITLE = {2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2013)}, PAGES = {89--96}, ADDRESS = {Portland, OR, USA}, }

Endnote

%0 Conference Proceedings %A Reshetouski, Ilya %A Manakov, Alkhazur %A Bhandari, Ayush %A Raskar, Ramesh %A Seidel, Hans-Peter %A Ihrke, Ivo %+ External Organizations External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Discovering the Structure of a Planar Mirror System from Multiple Observations of a Single Point : %G eng %U http://hdl.handle.net/21.11116/0000-000F-6BFF-B %R 10.1109/CVPR.2013.19 %D 2013 %B 2013 IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2013-06-23 - 2013-06-28 %C Portland, OR, USA %B 2013 IEEE Conference on Computer Vision and Pattern Recognition %P 89 - 96 %I IEEE Computer Society %@ 978-1-5386-5672-3

Reinhard, E., Efros, A., Kautz, J., and Seidel, H.-P. 2013. On Visual Realism of Synthesized Imagery. Proceedings of the IEEE101, 9.

Links

Export

BibTeX

@article{Reinhard2013a, TITLE = {On Visual Realism of Synthesized Imagery}, AUTHOR = {Reinhard, Erik and Efros, Alexei and Kautz, Jan and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0018-9219}, DOI = {10.1109/JPROC.2013.2260711}, LOCALID = {Local-ID: 87D8785C8741C366C1257B820045FF96-Reinhard2013a}, PUBLISHER = {IEEE}, ADDRESS = {Piscataway, NJ}, YEAR = {2013}, DATE = {2013}, JOURNAL = {Proceedings of the IEEE}, VOLUME = {101}, NUMBER = {9}, PAGES = {1998--2007}, }

Endnote

%0 Journal Article %A Reinhard, Erik %A Efros, Alexei %A Kautz, Jan %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T On Visual Realism of Synthesized Imagery : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0015-3E31-1 %R 10.1109/JPROC.2013.2260711 %F OTHER: Local-ID: 87D8785C8741C366C1257B820045FF96-Reinhard2013a %7 2013-07-25 %D 2013 %J Proceedings of the IEEE %O Proc. IEEE %V 101 %N 9 %& 1998 %P 1998 - 2007 %I IEEE %C Piscataway, NJ %@ false

Reinert, B., Ritschel, T., and Seidel, H.-P. 2013. Interactive By-example Design of Artistic Packing Layouts. ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia 2013)32, 6.

Abstract

We propose an approach to �pack� a set of two-dimensional graphical primitives into a spatial layout that follows artistic goals. We formalize this process as projecting from a high-dimensional feature space into a 2D layout. Our system does not expose the control of this projection to the user in form of sliders or similar interfaces. Instead, we infer the desired layout of all primitives from interactive placement of a small subset of example primitives. To produce a pleasant distribution of primitives with spatial extend, we produce a pleasant distribution of primitives with spatial extend, we propose a novel generalization of Centroidal Voronoi Tesselation which equalizes the distances between boundaries of nearby primitives. Compared to previous primitive distribution approaches our GPU implementation achieves both better fidelity and asymptotically higher speed. A user study evaluates the system�s usability.

Links

Export

BibTeX

@article{Reinert2013, TITLE = {Interactive By-example Design of Artistic Packing Layouts}, AUTHOR = {Reinert, Bernhard and Ritschel, Tobias and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2508363.2508409}, LOCALID = {Local-ID: 7A381077C9181F50C1257C6F004CC475-Reinert2013}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2013}, DATE = {2013}, ABSTRACT = {We propose an approach to {\diamond}pack{\diamond} a set of two-dimensional graphical primitives into a spatial layout that follows artistic goals. We formalize this process as projecting from a high-dimensional feature space into a 2D layout. Our system does not expose the control of this projection to the user in form of sliders or similar interfaces. Instead, we infer the desired layout of all primitives from interactive placement of a small subset of example primitives. To produce a pleasant distribution of primitives with spatial extend, we produce a pleasant distribution of primitives with spatial extend, we propose a novel generalization of Centroidal Voronoi Tesselation which equalizes the distances between boundaries of nearby primitives. Compared to previous primitive distribution approaches our GPU implementation achieves both better fidelity and asymptotically higher speed. A user study evaluates the system{\diamond}s usability.}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia)}, VOLUME = {32}, NUMBER = {6}, PAGES = {1--7}, EID = {218}, BOOKTITLE = {Proceedings of ACM SIGGRAPH Asia 2013}, }

Endnote

%0 Journal Article %A Reinert, Bernhard %A Ritschel, Tobias %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Interactive By-example Design of Artistic Packing Layouts : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0015-18D8-6 %R 10.1145/2508363.2508409 %F OTHER: Local-ID: 7A381077C9181F50C1257C6F004CC475-Reinert2013 %D 2013 %X We propose an approach to �pack� a set of two-dimensional graphical primitives into a spatial layout that follows artistic goals. We formalize this process as projecting from a high-dimensional feature space into a 2D layout. Our system does not expose the control of this projection to the user in form of sliders or similar interfaces. Instead, we infer the desired layout of all primitives from interactive placement of a small subset of example primitives. To produce a pleasant distribution of primitives with spatial extend, we produce a pleasant distribution of primitives with spatial extend, we propose a novel generalization of Centroidal Voronoi Tesselation which equalizes the distances between boundaries of nearby primitives. Compared to previous primitive distribution approaches our GPU implementation achieves both better fidelity and asymptotically higher speed. A user study evaluates the system�s usability. %J ACM Transactions on Graphics %V 32 %N 6 %& 1 %P 1 - 7 %Z sequence number: 218 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH Asia 2013 %O ACM SIGGRAPH Asia 2013 Hong Kong, 19 - 22 November 2013

Pouli, T., Artusi, A., Banterle, F., Akyüz, A.O., Seidel, H.-P., and Reinhard, E. 2013. Color Correction for Tone Reproduction. 21st Color and Imaging Conference Final Program and Proceedings (CIC 2013), IS&T.

Links

Export

BibTeX

@inproceedings{PouliCIC21, TITLE = {Color Correction for Tone Reproduction}, AUTHOR = {Pouli, Tania and Artusi, Alessandro and Banterle, Francesco and Aky{\"u}z, Ahmet O. and Seidel, Hans-Peter and Reinhard, Erik}, LANGUAGE = {eng}, DOI = {10.2352/CIC.2013.21.1.art00039}, PUBLISHER = {IS\&T}, YEAR = {2013}, DATE = {2013}, BOOKTITLE = {21st Color and Imaging Conference Final Program and Proceedings (CIC 2013)}, PAGES = {215--220}, ADDRESS = {Albuquerque, NM, USA}, }

Endnote

%0 Conference Proceedings %A Pouli, Tania %A Artusi, Alessandro %A Banterle, Francesco %A Akyüz, Ahmet O. %A Seidel, Hans-Peter %A Reinhard, Erik %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Color Correction for Tone Reproduction : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-A2C6-E %R 10.2352/CIC.2013.21.1.art00039 %D 2013 %B 21st Color and Imaging Conference %Z date of event: 2013-11-04 - 2013-11-08 %C Albuquerque, NM, USA %B 21st Color and Imaging Conference Final Program and Proceedings %P 215 - 220 %I IS&T

Nguyen, C., Scherzer, D., Ritschel, T., and Seidel, H.-P. 2013. Material Editing in Complex Scenes by Surface Light Field Manipulation and Reflectance Optimization. Computer Graphics Forum (Proc. EUROGRAPHICS 2013)32, 2.

Abstract

This work addresses the challenge of intuitive appearance editing in scenes with complex geometric layout and complex, spatially-varying indirect lighting. In contrast to previous work, that aimed to edit surface reflectance, our system allows a user to freely manipulate the surface light field. It then finds the best surface reflectance that ``explains'' the surface light field manipulation. Instead of classic \mathcal L_2 fitting of reflectance to a combination of incoming and exitant illumination, our system infers a sparse \mathcal L_0 change of shading parameters instead. Consequently, our system does not require ``diffuse'' or ``glossiness'' brushes or any such understanding of the underlying reflectance parametrization. Instead, it infers reflectance changes from scribbles made by a single simple color brush tool alone: Drawing a highlight will increase Phong specular; blurring a mirror reflection will decrease glossiness; etc. A sparse-solver framework operating on a novel point-based, pre-convolved lighting representation in combination with screen-space edit upsampling allows to perform editing interactively on a GPU.

Links

Export

BibTeX

@article{Nguyen2013, TITLE = {Material Editing in Complex Scenes by Surface Light Field Manipulation and Reflectance Optimization}, AUTHOR = {Nguyen, Chuong and Scherzer, Daniel and Ritschel, Tobias and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12038}, LOCALID = {Local-ID: 4CD3871C310E2855C1257B010065285A-Nguyen2013}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford, UK}, YEAR = {2013}, DATE = {2013}, ABSTRACT = {This work addresses the challenge of intuitive appearance editing in scenes with complex geometric layout and complex, spatially-varying indirect lighting. In contrast to previous work, that aimed to edit surface reflectance, our system allows a user to freely manipulate the surface light field. It then finds the best surface reflectance that ``explains'' the surface light field manipulation. Instead of classic \mathcal L_2 fitting of reflectance to a combination of incoming and exitant illumination, our system infers a sparse \mathcal L_0 change of shading parameters instead. Consequently, our system does not require ``diffuse'' or ``glossiness'' brushes or any such understanding of the underlying reflectance parametrization. Instead, it infers reflectance changes from scribbles made by a single simple color brush tool alone: Drawing a highlight will increase Phong specular; blurring a mirror reflection will decrease glossiness; etc. A sparse-solver framework operating on a novel point-based, pre-convolved lighting representation in combination with screen-space edit upsampling allows to perform editing interactively on a GPU.}, JOURNAL = {Computer Graphics Forum (Proc. EUROGRAPHICS)}, VOLUME = {32}, NUMBER = {2}, PAGES = {185--194}, BOOKTITLE = {EUROGRAPHICS 2013}, EDITOR = {Poulin, P. and Navazo, I.}, }

Endnote

%0 Journal Article %A Nguyen, Chuong %A Scherzer, Daniel %A Ritschel, Tobias %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Material Editing in Complex Scenes by Surface Light Field Manipulation and Reflectance Optimization : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0015-3810-8 %R 10.1111/cgf.12038 %F OTHER: Local-ID: 4CD3871C310E2855C1257B010065285A-Nguyen2013 %7 2013-05-06 %D 2013 %X This work addresses the challenge of intuitive appearance editing in scenes with complex geometric layout and complex, spatially-varying indirect lighting. In contrast to previous work, that aimed to edit surface reflectance, our system allows a user to freely manipulate the surface light field. It then finds the best surface reflectance that ``explains'' the surface light field manipulation. Instead of classic \mathcal L_2 fitting of reflectance to a combination of incoming and exitant illumination, our system infers a sparse \mathcal L_0 change of shading parameters instead. Consequently, our system does not require ``diffuse'' or ``glossiness'' brushes or any such understanding of the underlying reflectance parametrization. Instead, it infers reflectance changes from scribbles made by a single simple color brush tool alone: Drawing a highlight will increase Phong specular; blurring a mirror reflection will decrease glossiness; etc. A sparse-solver framework operating on a novel point-based, pre-convolved lighting representation in combination with screen-space edit upsampling allows to perform editing interactively on a GPU. %J Computer Graphics Forum %V 32 %N 2 %& 185 %P 185 - 194 %I Wiley-Blackwell %C Oxford, UK %@ false %B EUROGRAPHICS 2013 %O EUROGRAPHICS 2013 EG 2013 The European Association for Computer Graphics 34th Annual Conference ; Girona, Spain, May 6th - 10th, 2013

Milliez, A., Wand, M., Cani, M.-P., and Seidel, H.-P. 2013. Mutable Elastic Models for Sculpting Structured Shapes. Computer Graphics Forum (Proc. EUROGRAPHICS 2013)32, 2.

Links

Export

BibTeX

@article{Milliez2013, TITLE = {Mutable Elastic Models for Sculpting Structured Shapes}, AUTHOR = {Milliez, Antoine and Wand, Michael and Cani, Marie-Paule and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.12022}, LOCALID = {Local-ID: 54D78E6C8E10AB4CC1257C130048CEEA-Milliez2013}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford, UK}, YEAR = {2013}, DATE = {2013}, JOURNAL = {Computer Graphics Forum (Proc. EUROGRAPHICS)}, VOLUME = {32}, NUMBER = {2}, PAGES = {21--30}, BOOKTITLE = {EUROGRAPHICS 2013}, EDITOR = {Poulin, Pierre and Navazo, Isabel}, }

Endnote

%0 Journal Article %A Milliez, Antoine %A Wand, Michael %A Cani, Marie-Paule %A Seidel, Hans-Peter %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Mutable Elastic Models for Sculpting Structured Shapes : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0015-3CCE-2 %R 10.1111/cgf.12022 %F OTHER: Local-ID: 54D78E6C8E10AB4CC1257C130048CEEA-Milliez2013 %7 2013-05-06 %D 2013 %J Computer Graphics Forum %V 32 %N 2 %& 21 %P 21 - 30 %I Wiley-Blackwell %C Oxford, UK %@ false %B EUROGRAPHICS 2013 %O EUROGRAPHICS 2013 The European Association for Computer Graphics 34th Annual Conference ; Girona, Spain, May 6th - 10th, 2013 EG 2013

Manakov, A., Restrepo, J.F., Klehm, O., et al. 2013. A Reconfigurable Camera Add-on for High Dynamic Range, Multi-spectral, Polarization, and Light-field Imaging. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2013)32, 4.

Abstract

We propose a non-permanent add-on that enables plenoptic imaging with standard cameras. Our design is based on a physical copying mechanism that multiplies a sensor image into a number of identical copies that still carry the plenoptic information of interest. Via different optical filters, we can then recover the desired information. A minor modification of the design also allows for aperture sub-sampling and, hence, light-field imaging. As the filters in our design are exchangeable, a reconfiguration for different imaging purposes is possible. We show in a prototype setup that high dynamic range, multispectral, polarization, and light-field imaging can be achieved with our design.

Links

Export

BibTeX

@article{Manakov2013, TITLE = {A Reconfigurable Camera Add-on for High Dynamic Range, Multi-spectral, Polarization, and Light-field Imaging}, AUTHOR = {Manakov, Alkhazur and Restrepo, John F. and Klehm, Oliver and Heged{\"u}s, Ramon and Eisemann, Elmar and Seidel, Hans-Peter and Ihrke, Ivo}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/2461912.2461937}, LOCALID = {Local-ID: 2AF094BD6240B2D2C1257C13003B6CBD-Manakov2013}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2013}, DATE = {2013}, ABSTRACT = {We propose a non-permanent add-on that enables plenoptic imaging with standard cameras. Our design is based on a physical copying mechanism that multiplies a sensor image into a number of identical copies that still carry the plenoptic information of interest. Via different optical filters, we can then recover the desired information. A minor modification of the design also allows for aperture sub-sampling and, hence, light-field imaging. As the filters in our design are exchangeable, a reconfiguration for different imaging purposes is possible. We show in a prototype setup that high dynamic range, multispectral, polarization, and light-field imaging can be achieved with our design.}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {32}, NUMBER = {4}, PAGES = {1--14}, EID = {47}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2013}, }

Endnote

%0 Journal Article %A Manakov, Alkhazur %A Restrepo, John F. %A Klehm, Oliver %A Hegedüs, Ramon %A Eisemann, Elmar %A Seidel, Hans-Peter %A Ihrke, Ivo %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T A Reconfigurable Camera Add-on for High Dynamic Range, Multi-spectral, Polarization, and Light-field Imaging : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0015-3CDD-F %R 10.1145/2461912.2461937 %F OTHER: Local-ID: 2AF094BD6240B2D2C1257C13003B6CBD-Manakov2013 %7 2013 %D 2013 %X We propose a non-permanent add-on that enables plenoptic imaging with standard cameras. Our design is based on a physical copying mechanism that multiplies a sensor image into a number of identical copies that still carry the plenoptic information of interest. Via different optical filters, we can then recover the desired information. A minor modification of the design also allows for aperture sub-sampling and, hence, light-field imaging. As the filters in our design are exchangeable, a reconfiguration for different imaging purposes is possible. We show in a prototype setup that high dynamic range, multispectral, polarization, and light-field imaging can be achieved with our design. %J ACM Transactions on Graphics %V 32 %N 4 %& 1 %P 1 - 14 %Z sequence number: 47 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2013 %O ACM SIGGRAPH 2013 Anaheim, California, 21 - 25 July 2013

Liu, Y., Gall, J., Stoll, C., Dai, Q., Seidel, H.-P., and Theobalt, C. 2013. Markerless Motion Capture of Multiple Characters Using Multiview Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence35, 11.

Links

Export

BibTeX

@article{LiuPami2013, TITLE = {Markerless Motion Capture of Multiple Characters Using Multiview Image Segmentation}, AUTHOR = {Liu, Yebin and Gall, J{\"u}rgen and Stoll, Carsten and Dai, Qionghai and Seidel, Hans-Peter and Theobalt, Christian}, LANGUAGE = {eng}, ISSN = {0162-8828}, DOI = {10.1109/TPAMI.2013.47}, LOCALID = {Local-ID: 3A056CE707FBCCD9C1257C6000533A6F-LiuPami2013}, PUBLISHER = {IEEE Computer Society}, ADDRESS = {Los Alamitos, CA}, YEAR = {2013}, DATE = {2013}, JOURNAL = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, VOLUME = {35}, NUMBER = {11}, PAGES = {2720--2735}, }

Endnote

%0 Journal Article %A Liu, Yebin %A Gall, Jürgen %A Stoll, Carsten %A Dai, Qionghai %A Seidel, Hans-Peter %A Theobalt, Christian %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Markerless Motion Capture of Multiple Characters Using Multiview Image Segmentation : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0015-3937-8 %R 10.1109/TPAMI.2013.47 %F OTHER: Local-ID: 3A056CE707FBCCD9C1257C6000533A6F-LiuPami2013 %7 2013-02-21 %D 2013 %J IEEE Transactions on Pattern Analysis and Machine Intelligence %O IEEE Trans. Pattern Anal. Mach. Intell. %V 35 %N 11 %& 2720 %P 2720 - 2735 %I IEEE Computer Society %C Los Alamitos, CA %@ false

Lee, S., Sips, M., and Seidel, H.-P. 2013. Perceptually Driven Visibility Optimization for Categorical Data Visualization. IEEE Transactions on Visualization and Computer Graphics19, 10.

Links

Export

BibTeX

@article{Seidel2013, TITLE = {Perceptually Driven Visibility Optimization for Categorical Data Visualization}, AUTHOR = {Lee, Sungkil and Sips, Mike and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {1077-2626}, DOI = {10.1109/TVCG.2012.315}, PUBLISHER = {IEEE Computer Society}, ADDRESS = {Los Alamitos, CA}, YEAR = {2013}, DATE = {2013}, JOURNAL = {IEEE Transactions on Visualization and Computer Graphics}, VOLUME = {19}, NUMBER = {10}, PAGES = {1746--1757}, }

Endnote

%0 Journal Article %A Lee, Sungkil %A Sips, Mike %A Seidel, Hans-Peter %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Perceptually Driven Visibility Optimization for Categorical Data Visualization : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0018-A9FB-0 %R 10.1109/TVCG.2012.315 %7 2012-11-30 %D 2013 %J IEEE Transactions on Visualization and Computer Graphics %V 19 %N 10 %& 1746 %P 1746 - 1757 %I IEEE Computer Society %C Los Alamitos, CA %@ false

Kurz, C., Ritschel, T., Eisemann, E., Thormählen, T., and Seidel, H.-P. 2013. Generating Realistic Camera Shake for Virtual Scenes. Journal of Virtual Reality and Broadcasting10, 7.

[publisher version]

Abstract

When depicting both virtual and physical worlds, the viewer's impression of presence in these worlds is strongly linked to camera motion. Plausible and artist-controlled camera movement can substantially increase scene immersion. While physical camera motion exhibits subtle details of position, rotation, and acceleration, these details are often missing for virtual camera motion. In this work, we analyze camera movement using signal theory. Our system allows us to stylize a smooth user-defined virtual base camera motion by enriching it with plausible details. A key component of our system is a database of videos filmed by physical cameras. These videos are analyzed with a camera-motion estimation algorithm (structure-from-motion) and labeled manually with a specific style. By considering spectral properties of location, orientation and acceleration, our solution learns camera motion details. Consequently, an arbitrary virtual base motion, defined in any conventional animation package, can be automatically modified according to a user-selected style. In an animation package the camera motion base path is typically defined by the user via function curves. Another possibility is to obtain the camera path by using a mixed reality camera in motion capturing studio. As shown in our experiments, the resulting shots are still fully artist-controlled, but appear richer and more physically plausible.

Links

[publisher version]

Export

BibTeX

@article{Kurz2013, TITLE = {Generating Realistic Camera Shake for Virtual Scenes}, AUTHOR = {Kurz, Christian and Ritschel, Tobias and Eisemann, Elmar and Thorm{\"a}hlen, Thorsten and Seidel, Hans-Peter}, LANGUAGE = {eng}, ISSN = {1860-2037}, URL = {urn:nbn:de:0009-6-38335}, LOCALID = {Local-ID: 43DB142DAE2CF97AC1257C69005B2D67-Kurz2013}, PUBLISHER = {Hochschulbibliothekszentrum des Landes Nordrhein-Westfalen, K{\"o}ln (HBZ)}, ADDRESS = {K{\"o}ln}, YEAR = {2013}, ABSTRACT = {When depicting both virtual and physical worlds, the viewer's impression of presence in these worlds is strongly linked to camera motion. Plausible and artist-controlled camera movement can substantially increase scene immersion. While physical camera motion exhibits subtle details of position, rotation, and acceleration, these details are often missing for virtual camera motion. In this work, we analyze camera movement using signal theory. Our system allows us to stylize a smooth user-defined virtual base camera motion by enriching it with plausible details. A key component of our system is a database of videos filmed by physical cameras. These videos are analyzed with a camera-motion estimation algorithm (structure-from-motion) and labeled manually with a specific style. By considering spectral properties of location, orientation and acceleration, our solution learns camera motion details. Consequently, an arbitrary virtual base motion, defined in any conventional animation package, can be automatically modified according to a user-selected style. In an animation package the camera motion base path is typically defined by the user via function curves. Another possibility is to obtain the camera path by using a mixed reality camera in motion capturing studio. As shown in our experiments, the resulting shots are still fully artist-controlled, but appear richer and more physically plausible.}, JOURNAL = {Journal of Virtual Reality and Broadcasting}, VOLUME = {10}, NUMBER = {7}, PAGES = {1--13}, }

Endnote

%0 Journal Article %A Kurz, Christian %A Ritschel, Tobias %A Eisemann, Elmar %A Thormählen, Thorsten %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Generating Realistic Camera Shake for Virtual Scenes : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0015-196D-1 %F OTHER: Local-ID: 43DB142DAE2CF97AC1257C69005B2D67-Kurz2013 %U urn:nbn:de:0009-6-38335 %7 2013 %D 2013 %X When depicting both virtual and physical worlds, the viewer's impression of presence in these worlds is strongly linked to camera motion. Plausible and artist-controlled camera movement can substantially increase scene immersion. While physical camera motion exhibits subtle details of position, rotation, and acceleration, these details are often missing for virtual camera motion. In this work, we analyze camera movement using signal theory. Our system allows us to stylize a smooth user-defined virtual base camera motion by enriching it with plausible details. A key component of our system is a database of videos filmed by physical cameras. These videos are analyzed with a camera-motion estimation algorithm (structure-from-motion) and labeled manually with a specific style. By considering spectral properties of location, orientation and acceleration, our solution learns camera motion details. Consequently, an arbitrary virtual base motion, defined in any conventional animation package, can be automatically modified according to a user-selected style. In an animation package the camera motion base path is typically defined by the user via function curves. Another possibility is to obtain the camera path by using a mixed reality camera in motion capturing studio. As shown in our experiments, the resulting shots are still fully artist-controlled, but appear richer and more physically plausible. %J Journal of Virtual Reality and Broadcasting %V 10 %N 7 %& 1 %P 1 - 13 %I Hochschulbibliothekszentrum des Landes Nordrhein-Westfalen, Köln (HBZ) %C Köln %@ false %U http://www.jvrb.org/past-issues/10.2013/3833/1020137.pdf

Klehm, O., Ihrke, I., Seidel, H.-P., and Eisemann, E. 2013. Volume Stylizer: Tomography-based Volume Painting. Proceedings I3D 2013, ACM.

Abstract

Volumetric phenomena are an integral part of standard rendering, yet, no suitable tools to edit characteristic properties are available so far. Either simulation results are used directly, or modifications are high-level, e.g., noise functions to influence appearance. Intuitive artistic control is not possible. We propose a solution to stylize single-scattering volumetric effects. Emission, scattering and extinction become amenable to artistic control while preserving a smooth and coherent appearance when changing the viewpoint. Our approach lets the user define a number of target views to be matched when observing the volume from this perspective. Via an analysis of the volumetric rendering equation, we can show how to link this problem to tomographic reconstruction.

Links

Export

BibTeX

@inproceedings{i3dKlehm2013, TITLE = {Volume Stylizer: {Tomography-based} Volume Painting}, AUTHOR = {Klehm, Oliver and Ihrke, Ivo and Seidel, Hans-Peter and Eisemann, Elmar}, LANGUAGE = {eng}, ISBN = {978-1-4503-1956-0}, DOI = {10.1145/2448196.2448222}, LOCALID = {Local-ID: A0B42A95204F2B1EC1257B03005B313A-i3dKlehm2013}, PUBLISHER = {ACM}, YEAR = {2013}, DATE = {2013}, ABSTRACT = {Volumetric phenomena are an integral part of standard rendering, yet, no suitable tools to edit characteristic properties are available so far. Either simulation results are used directly, or modifications are high-level, e.g., noise functions to influence appearance. Intuitive artistic control is not possible. We propose a solution to stylize single-scattering volumetric effects. Emission, scattering and extinction become amenable to artistic control while preserving a smooth and coherent appearance when changing the viewpoint. Our approach lets the user define a number of target views to be matched when observing the volume from this perspective. Via an analysis of the volumetric rendering equation, we can show how to link this problem to tomographic reconstruction.}, BOOKTITLE = {Proceedings I3D 2013}, EDITOR = {Olano, Marc and Otaduy, Miguel A. and Meenakshisundaram, Gopi and Yoon, Sung-Eui and Spencer, Stephen N.}, PAGES = {161--168}, ADDRESS = {Orlando, FL, USA}, }

Endnote

%0 Conference Proceedings %A Klehm, Oliver %A Ihrke, Ivo %A Seidel, Hans-Peter %A Eisemann, Elmar %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Volume Stylizer: Tomography-based Volume Painting : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0015-3817-9 %R 10.1145/2448196.2448222 %F OTHER: Local-ID: A0B42A95204F2B1EC1257B03005B313A-i3dKlehm2013 %D 2013 %B ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games %Z date of event: 2013-03-21 - 2013-03-23 %C Orlando, FL, USA %X Volumetric phenomena are an integral part of standard rendering, yet, no suitable tools to edit characteristic properties are available so far. Either simulation results are used directly, or modifications are high-level, e.g., noise functions to influence appearance. Intuitive artistic control is not possible. We propose a solution to stylize single-scattering volumetric effects. Emission, scattering and extinction become amenable to artistic control while preserving a smooth and coherent appearance when changing the viewpoint. Our approach lets the user define a number of target views to be matched when observing the volume from this perspective. Via an analysis of the volumetric rendering equation, we can show how to link this problem to tomographic reconstruction. %B Proceedings I3D 2013 %E Olano, Marc; Otaduy, Miguel A.; Meenakshisundaram, Gopi; Yoon, Sung-Eui; Spencer, Stephen N. %P 161 - 168 %I ACM %@ 978-1-4503-1956-0

Kerber, J., Bokeloh, M., Wand, M., and Seidel, H.-P. 2013. Scalable Symmetry Detection for Urban Scenes. Computer Graphics Forum32, 1.

Links

Export

BibTeX

@article{Kerber2013_1, TITLE = {Scalable Symmetry Detection for Urban Scenes}, AUTHOR = {Kerber, Jens and Bokeloh, Martin and Wand, Michael and Seidel, Hans-Peter}, LANGUAGE = {eng}, DOI = {10.1111/j.1467-8659.2012.03226.x}, LOCALID = {Local-ID: FC00BBDD131C5BC2C1257AED003BCDC9-Kerber2013_1}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford, UK}, YEAR = {2013}, DATE = {2013}, JOURNAL = {Computer Graphics Forum}, VOLUME = {32}, NUMBER = {1}, PAGES = {3--15}, }

Endnote

%0 Journal Article %A Kerber, Jens %A Bokeloh, Martin %A Wand, Michael %A Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Scalable Symmetry Detection for Urban Scenes : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0015-17F3-0 %R 10.1111/j.1467-8659.2012.03226.x %F OTHER: Local-ID: FC00BBDD131C5BC2C1257AED003BCDC9-Kerber2013_1 %7 2012-10-09 %D 2013 %J Computer Graphics Forum %V 32 %N 1 %& 3 %P 3 - 15 %I Wiley-Blackwell %C Oxford, UK

Kellnhofer, P., Ritschel, T., Myszkowski, K., and Seidel, H.-P. 2013. Optimizing Disparity for Motion in Depth. Computer Graphics Forum (Proc. Eurographics Symposium on Rendering 2013)32, 4.

Abstract

Beyond the careful design of stereo acquisition equipment and rendering algorithms, disparity post-processing has recently received much attention, where one of the key tasks is to compress the originally large disparity range to avoid viewing discomfort. The perception of dynamic stereo content however, relies on reproducing the full disparity-time volume that a scene point undergoes in motion. This volume can be strongly distorted in manipulation, which is only concerned with changing disparity at one instant in time, even if the temporal coherence of that change is maintained. We propose an optimization to preserve stereo motion of content that was subject to an arbitrary disparity manipulation, based on a perceptual model of temporal disparity changes. Furthermore, we introduce a novel 3D warping technique to create stereo image pairs that conform to this optimized disparity map. The paper concludes with perceptual studies of motion reproduction quality and task performance in a simple game, showing how our optimization can achieve both viewing comfort and faithful stereo motion.

Links