Last Year

Article
Bemana, M., Keinert, J., Myszkowski, K., et al. 2019a. Learning to Predict Image-based Rendering Artifacts with Respect to a Hidden Reference Image. Computer Graphics Forum (Proc. Pacific Graphics 2019)38, 7.
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}, MARGINALMARK = {$\bullet$}, 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
Bernard, F., Thunberg, J., Goncalves, J., and Theobalt, C. 2019. Synchronisation of Partial Multi-Matchings via Non-negative Factorisations. Pattern Recognition92.
Export
BibTeX
@article{Bernard2019, TITLE = {Synchronisation of Partial Multi-Matchings via Non-negative Factorisations}, AUTHOR = {Bernard, Florian and Thunberg, Johan and Goncalves, Jorge and Theobalt, Christian}, LANGUAGE = {eng}, ISSN = {0031-3203}, DOI = {10.1016/j.patcog.2019.03.021}, PUBLISHER = {Pergamon}, ADDRESS = {Oxford}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {Pattern Recognition}, VOLUME = {92}, PAGES = {146--155}, }
Endnote
%0 Journal Article %A Bernard, Florian %A Thunberg, Johan %A Goncalves, Jorge %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Synchronisation of Partial Multi-Matchings via Non-negative Factorisations : %G eng %U http://hdl.handle.net/21.11116/0000-0003-B2EC-A %R 10.1016/j.patcog.2019.03.021 %7 2019 %D 2019 %J Pattern Recognition %O Pattern Recognit. %V 92 %& 146 %P 146 - 155 %I Pergamon %C Oxford %@ false
Dokter, M., Hladký, J., Parger, M., Schmalstieg, D., Seidel, H.-P., and Steinberger, M. 2019. Hierarchical Rasterization of Curved Primitives for Vector Graphics Rendering on the GPU. Computer Graphics Forum (Proc. EUROGRAPHICS 2019)38, 2.
Export
BibTeX
@article{Dokter_EG2019, TITLE = {Hierarchical Rasterization of Curved Primitives for Vector Graphics Rendering on the {GPU}}, AUTHOR = {Dokter, Mark and Hladk{\'y}, Jozef and Parger, Mathias and Schmalstieg, Dieter and Seidel, Hans-Peter and Steinberger, Markus}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.13622}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {Computer Graphics Forum (Proc. EUROGRAPHICS)}, VOLUME = {38}, NUMBER = {2}, PAGES = {93--103}, BOOKTITLE = {EUROGRAPHICS 2019 STAR -- State of The Art Reports}, }
Endnote
%0 Journal Article %A Dokter, Mark %A Hladký, Jozef %A Parger, Mathias %A Schmalstieg, Dieter %A Seidel, Hans-Peter %A Steinberger, Markus %+ 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 Hierarchical Rasterization of Curved Primitives for Vector Graphics Rendering on the GPU : %G eng %U http://hdl.handle.net/21.11116/0000-0002-FC80-1 %R 10.1111/cgf.13622 %7 2019 %D 2019 %J Computer Graphics Forum %V 38 %N 2 %& 93 %P 93 - 103 %I Wiley-Blackwell %C Oxford %@ false %B EUROGRAPHICS 2019 STAR – State of The Art Reports %O EUROGRAPHICS 2019 The 40th Annual Conference of the European Association for Computer Graphics ; Genova, Italy, May 6-10, 2019 EG 2019
Fried, O., Tewari, A., Zollhöfer, M., et al. 2019a. Text-based Editing of Talking-head Video. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2019)38, 4.
Export
BibTeX
@article{Fried_SIGGRAPH2019, TITLE = {Text-based Editing of Talking-head Video}, AUTHOR = {Fried, Ohad and Tewari, Ayush and Zollh{\"o}fer, Michael and Finkelstein, Adam and Shechtman, Eli and Goldman, Dan B. and Genova, Kyle and Jin, Zeyu and Theobalt, Christian and Agrawala, Maneesh}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3306346.3323028}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {38}, NUMBER = {4}, EID = {68}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2019}, }
Endnote
%0 Journal Article %A Fried, Ohad %A Tewari, Ayush %A Zollhöfer, Michael %A Finkelstein, Adam %A Shechtman, Eli %A Goldman, Dan B. %A Genova, Kyle %A Jin, Zeyu %A Theobalt, Christian %A Agrawala, Maneesh %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Text-based Editing of Talking-head Video : %G eng %U http://hdl.handle.net/21.11116/0000-0004-8458-4 %R 10.1145/3306346.3323028 %7 2019 %D 2019 %J ACM Transactions on Graphics %V 38 %N 4 %Z sequence number: 68 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2019 %O ACM SIGGRAPH 2019 Los Angeles, CA, USA, 28 July - 1 August
Habermann, M., Xu, W., Zollhöfer, M., Pons-Moll, G., and Theobalt, C. 2019a. LiveCap: Real-time Human Performance Capture from Monocular Video. ACM Transactions on Graphics38, 2.
Export
BibTeX
@article{Habermann_TOG19, TITLE = {{LiveCap}: {R}eal-time Human Performance Capture from Monocular Video}, AUTHOR = {Habermann, Marc and Xu, Weipeng and Zollh{\"o}fer, Michael and Pons-Moll, Gerard and Theobalt, Christian}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3311970}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {ACM Transactions on Graphics}, VOLUME = {38}, NUMBER = {2}, EID = {14}, }
Endnote
%0 Journal Article %A Habermann, Marc %A Xu, Weipeng %A Zollhöfer, Michael %A Pons-Moll, Gerard %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T LiveCap: Real-time Human Performance Capture from Monocular Video : %G eng %U http://hdl.handle.net/21.11116/0000-0002-B947-E %R 10.1145/3311970 %7 2019 %D 2019 %J ACM Transactions on Graphics %V 38 %N 2 %Z sequence number: 14 %I ACM %C New York, NY %@ false
Hladký, J., Seidel, H.-P., and Steinberger, M. 2019a. The Camera Offset Space: Real-time Potentially Visible Set Computations for Streaming Rendering. ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia 2019)38, 6.
Export
BibTeX
@article{Hladky_SA2019, TITLE = {The Camera Offset Space: Real-time Potentially Visible Set Computations for Streaming Rendering}, AUTHOR = {Hladk{\'y}, Jozef and Seidel, Hans-Peter and Steinberger, Markus}, LANGUAGE = {eng}, ISSN = {0730-0301}, ISBN = {978-1-4503-6008-1}, DOI = {10.1145/3355089.3356530}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia)}, VOLUME = {38}, NUMBER = {6}, EID = {231}, BOOKTITLE = {Proceedings of ACM SIGGRAPH Asia 2019}, }
Endnote
%0 Journal Article %A Hladký, Jozef %A Seidel, Hans-Peter %A Steinberger, Markus %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T The Camera Offset Space: Real-time Potentially Visible Set Computations for Streaming Rendering : %G eng %U http://hdl.handle.net/21.11116/0000-0005-4E4F-D %R 10.1145/3355089.3356530 %7 2019 %D 2019 %J ACM Transactions on Graphics %V 38 %N 6 %Z sequence number: 231 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH Asia 2019 %O ACM SIGGRAPH Asia 2019 Brisbane, Australia, 17 - 20 November 2019 SA'19 SA 2019 %@ 978-1-4503-6008-1
Hladký, J., Seidel, H.-P., and Steinberger, M. 2019b. Tessellated Shading Streaming. Computer Graphics Forum (Proc. Eurographics Symposium on Rendering 2019)38, 4.
Export
BibTeX
@article{Hladky_EGSR2019, TITLE = {Tessellated Shading Streaming}, AUTHOR = {Hladk{\'y}, Jozef and Seidel, Hans-Peter and Steinberger, Markus}, LANGUAGE = {eng}, ISSN = {0167-7055}, URL = {https://diglib.eg.org/handle/10.1111/cgf13780}, DOI = {10.1111/cgf.13780}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {Computer Graphics Forum (Proc. Eurographics Symposium on Rendering)}, VOLUME = {38}, NUMBER = {4}, PAGES = {171--182}, BOOKTITLE = {Eurographics Symposium on Rendering 2019}, EDITOR = {Boubekeur, Tamy and Sen, Pradeep}, }
Endnote
%0 Journal Article %A Hladký, Jozef %A Seidel, Hans-Peter %A Steinberger, Markus %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Tessellated Shading Streaming : %G eng %U http://hdl.handle.net/21.11116/0000-0004-4897-1 %R 10.1111/cgf.13780 %U https://diglib.eg.org/handle/10.1111/cgf13780 %7 2019 %D 2019 %J Computer Graphics Forum %V 38 %N 4 %& 171 %P 171 - 182 %I Wiley-Blackwell %C Oxford %@ false %B Eurographics Symposium on Rendering 2019 %O Eurographics Symposium on Rendering 2019 EGSR 2019 Strasbourg, France, July 10 - 12, 2109
Kim, H., Elgharib, M., Zollhöfer, M., et al. 2019. Neural Style-preserving Visual Dubbing. ACM Transactions on Algorithms38, 6.
Export
BibTeX
@article{Kim2019, TITLE = {Neural Style-preserving Visual Dubbing}, AUTHOR = {Kim, Hyeongwoo and Elgharib, Mohamed and Zollh{\"o}fer, Michael and Seidel, Hans-Peter and Beeler, Thabo and Richardt, Christian and Theobalt, Christian}, LANGUAGE = {eng}, ISSN = {1549-6325}, DOI = {10.1145/3355089.3356500}, PUBLISHER = {Association for Computing Machinery}, ADDRESS = {New York, NY}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {ACM Transactions on Algorithms}, VOLUME = {38}, NUMBER = {6}, EID = {178}, }
Endnote
%0 Journal Article %A Kim, Hyeongwoo %A Elgharib, Mohamed %A Zollhöfer, Michael %A Seidel, Hans-Peter %A Beeler, Thabo %A Richardt, Christian %A Theobalt, Christian %+ 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 Computer Graphics, MPI for Informatics, Max Planck Society %T Neural Style-preserving Visual Dubbing : %G eng %U http://hdl.handle.net/21.11116/0000-0005-6AC0-B %R 10.1145/3355089.3356500 %7 2019 %D 2019 %J ACM Transactions on Algorithms %V 38 %N 6 %Z sequence number: 178 %I Association for Computing Machinery %C New York, NY %@ false
Kovalenko, O., Golyanik, V., Malik, J., Elhayek, A., and Stricker, D. 2019. Structure from Articulated Motion: Accurate and Stable Monocular 3D Reconstruction without Training Data. Sensors19, 20.
Export
BibTeX
@article{Kovalenko2019, TITLE = {Structure from Articulated Motion: {A}ccurate and Stable Monocular {3D} Reconstruction without Training Data}, AUTHOR = {Kovalenko, Onorina and Golyanik, Vladislav and Malik, Jameel and Elhayek, Ahmed and Stricker, Didier}, LANGUAGE = {eng}, ISSN = {1424-8220}, DOI = {10.3390/s19204603}, PUBLISHER = {MDPI}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, JOURNAL = {Sensors}, VOLUME = {19}, NUMBER = {20}, EID = {4603}, }
Endnote
%0 Journal Article %A Kovalenko, Onorina %A Golyanik, Vladislav %A Malik, Jameel %A Elhayek, Ahmed %A Stricker, Didier %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations %T Structure from Articulated Motion: Accurate and Stable Monocular 3D Reconstruction without Training Data : %G eng %U http://hdl.handle.net/21.11116/0000-0005-5CB5-8 %R 10.3390/s19204603 %7 2019 %D 2019 %J Sensors %V 19 %N 20 %Z sequence number: 4603 %I MDPI %@ false
Leimkühler, T., Singh, G., Myszkowski, K., Seidel, H.-P., and Ritschel, T. 2019. Deep Point Correlation Design. ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia 2019)38, 6.
Export
BibTeX
@article{Leimkuehler_SA2019, TITLE = {Deep Point Correlation Design}, AUTHOR = {Leimk{\"u}hler, Thomas and Singh, Gurprit and Myszkowski, Karol and Seidel, Hans-Peter and Ritschel, Tobias}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3355089.3356562}, PUBLISHER = {ACM}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, ADDRESS = {New York, NY}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia)}, VOLUME = {38}, NUMBER = {6}, EID = {226}, BOOKTITLE = {Proceedings of ACM SIGGRAPH Asia 2019}, }
Endnote
%0 Journal Article %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 Deep Point Correlation Design : %G eng %U http://hdl.handle.net/21.11116/0000-0004-9BF3-B %R 10.1145/3355089.3356562 %7 2019 %D 2019 %J ACM Transactions on Graphics %V 38 %N 6 %Z sequence number: 226 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH Asia 2019 %O ACM SIGGRAPH Asia 2019 Brisbane, Australia, 17 - 20 November 2019 SA'19 SA 2019 %I ACM %C New York, NY
Meka, A., Hane, C., Pandey, R., et al. 2019. Deep Reflectance Fields High-Quality Facial Reflectance Field Inference from Color Gradient Illumination. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2019)38, 4.
Export
BibTeX
@article{Meka_SIGGRAPH2019, TITLE = {Deep Reflectance Fields High-Quality Facial Reflectance Field Inference from Color Gradient Illumination}, AUTHOR = {Meka, Abhimitra and Hane, Christian and Pandey, Rohit and Zollh{\"o}fer, Michael and Fanello, Sean and Fyffe, Graham and Kowdle, Adarsh and Yu, Xueming and Busch, Jay and Dour-Garian, Jason and Denny, Peter and Bouaziz, Sofien and Lincoln, Peter and Whalen, Matt and Harvey, Geoff and Taylor, Jonathan and Izadi, Shahram and Tagliasacchi, Andrea and Debevec, Paul and Theobalt, Christian and Valentin, Julien and Rhemann, Christoph}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3306346.3323027}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {38}, NUMBER = {4}, EID = {77}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2019}, }
Endnote
%0 Journal Article %A Meka, Abhimitra %A Hane, Christian %A Pandey, Rohit %A Zollhöfer, Michael %A Fanello, Sean %A Fyffe, Graham %A Kowdle, Adarsh %A Yu, Xueming %A Busch, Jay %A Dour-Garian, Jason %A Denny, Peter %A Bouaziz, Sofien %A Lincoln, Peter %A Whalen, Matt %A Harvey, Geoff %A Taylor, Jonathan %A Izadi, Shahram %A Tagliasacchi, Andrea %A Debevec, Paul %A Theobalt, Christian %A Valentin, Julien %A Rhemann, Christoph %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations %T Deep Reflectance Fields High-Quality Facial Reflectance Field Inference from Color Gradient Illumination : %G eng %U http://hdl.handle.net/21.11116/0000-0004-8453-9 %R 10.1145/3306346.3323027 %7 2019 %D 2019 %J ACM Transactions on Graphics %V 38 %N 4 %Z sequence number: 77 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2019 %O ACM SIGGRAPH 2019 Los Angeles, CA, USA, 28 July - 1 August
Mueller, F., Davis, M., Bernard, F., et al. 2019. Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2019)38, 4.
Export
BibTeX
@article{MuellerTOG2019, TITLE = {Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera}, AUTHOR = {Mueller, Franziska and Davis, Micah and Bernard, Florian and Sotnychenko, Oleksandr and Verschoor, Mickeal and Otaduy, Miguel A. and Casas, Dan and Theobalt, Christian}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3306346.3322958}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {38}, NUMBER = {4}, EID = {49}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2019}, }
Endnote
%0 Journal Article %A Mueller, Franziska %A Davis, Micah %A Bernard, Florian %A Sotnychenko, Oleksandr %A Verschoor, Mickeal %A Otaduy, Miguel A. %A Casas, Dan %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 External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera : %G eng %U http://hdl.handle.net/21.11116/0000-0004-844A-4 %R 10.1145/3306346.3322958 %7 2019 %D 2019 %J ACM Transactions on Graphics %V 38 %N 4 %Z sequence number: 49 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2019 %O ACM SIGGRAPH 2019 Los Angeles, CA, USA, 28 July - 1 August
Singh, G., Öztireli, C., Ahmed, A.G.M., et al. 2019. Analysis of Sample Correlations for Monte Carlo Rendering. Computer Graphics Forum (Proc. EUROGRAPHICS 2019)38, 2.
Export
BibTeX
@article{Singh_EG2019STAR, TITLE = {Analysis of Sample Correlations for {Monte Carlo} Rendering}, AUTHOR = {Singh, Gurprit and O\"ztireli, Cengiz and Ahmed, Abdalla G.M. and Coeurjolly, David and Subr, Kartic and Ostromoukhov, Victor and Deussen, Oliver and Ramamoorthi, Ravi and Jarosz, Wojciech}, LANGUAGE = {eng}, ISSN = {0167-7055}, DOI = {10.1111/cgf.13653}, PUBLISHER = {Blackwell-Wiley}, ADDRESS = {Oxford}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {Computer Graphics Forum (Proc. EUROGRAPHICS)}, VOLUME = {38}, NUMBER = {2}, PAGES = {473--491}, BOOKTITLE = {EUROGRAPHICS 2019 STAR -- State of The Art Reports}, }
Endnote
%0 Journal Article %A Singh, Gurprit %A Öztireli, Cengiz %A Ahmed, Abdalla G.M. %A Coeurjolly, David %A Subr, Kartic %A Ostromoukhov, Victor %A Deussen, Oliver %A Ramamoorthi, Ravi %A Jarosz, Wojciech %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations %T Analysis of Sample Correlations for Monte Carlo Rendering : %G eng %U http://hdl.handle.net/21.11116/0000-0002-F487-2 %R 10.1111/cgf.13653 %7 2019 %D 2019 %J Computer Graphics Forum %O Computer Graphics Forum : journal of the European Association for Computer Graphics Comput. Graph. Forum %V 38 %N 2 %& 473 %P 473 - 491 %I Blackwell-Wiley %C Oxford %@ false %B EUROGRAPHICS 2019 STAR – State of The Art Reports %O EUROGRAPHICS 2019 EG 2019 The 40th Annual Conference of the European Association for Computer Graphics ; Genova, Italy, May 6-10
Sumin, D., Rittig, T., Babaei, V., et al. 2019. Geometry-Aware Scattering Compensation for 3D Printing. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2019)38, 4.
Export
BibTeX
@article{SuminRittig2019, TITLE = {Geometry-Aware Scattering Compensation for {3D} Printing}, AUTHOR = {Sumin, Denis and Rittig, Tobias and Babaei, Vahid and Nindel, Thomas and Wilkie, Alexander and Didyk, Piotr and Bickel, Bernd and K{\v r}iv{\'a}nek, Jaroslav and Myszkowski, Karol and Weyrich, Tim}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3306346.3322992}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {38}, NUMBER = {4}, EID = {111}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2019}, }
Endnote
%0 Journal Article %A Sumin, Denis %A Rittig, Tobias %A Babaei, Vahid %A Nindel, Thomas %A Wilkie, Alexander %A Didyk, Piotr %A Bickel, Bernd %A Křivánek, Jaroslav %A Myszkowski, Karol %A Weyrich, Tim %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Geometry-Aware Scattering Compensation for 3D Printing : %G eng %U http://hdl.handle.net/21.11116/0000-0003-7D65-0 %R 10.1145/3306346.3322992 %7 2019 %D 2019 %J ACM Transactions on Graphics %V 38 %N 4 %Z sequence number: 111 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2019 %O ACM SIGGRAPH 2019 Los Angeles, CA, USA, 28 July - 1 August
Thies, J., Zollhöfer, M., Stamminger, M., Theobalt, C., and Nießner, M. 2019a. Face2Face: Real-Time Face Capture and Reenactment of RGB Videos. Communications of the ACM62, 1.
Export
BibTeX
@article{thies2019face, TITLE = {{Face2Face}: {R}eal-Time Face Capture and Reenactment of {RGB} Videos}, AUTHOR = {Thies, Justus and Zollh{\"o}fer, Michael and Stamminger, Marc and Theobalt, Christian and Nie{\ss}ner, Matthias}, LANGUAGE = {eng}, ISSN = {0001-0782}, DOI = {10.1145/3292039}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {Communications of the ACM}, VOLUME = {62}, NUMBER = {1}, PAGES = {96--104}, }
Endnote
%0 Journal Article %A Thies, Justus %A Zollhöfer, Michael %A Stamminger, Marc %A Theobalt, Christian %A Nießner, Matthias %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Face2Face: Real-Time Face Capture and Reenactment of RGB Videos : %G eng %U http://hdl.handle.net/21.11116/0000-0002-C0A7-8 %R 10.1145/3292039 %7 2019 %D 2019 %J Communications of the ACM %V 62 %N 1 %& 96 %P 96 - 104 %I ACM %C New York, NY %@ false
Tursun, O.T., Arabadzhiyska, E., Wernikowski, M., et al. 2019. Luminance-Contrast-Aware Foveated Rendering. ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2019)38, 4.
Export
BibTeX
@article{Tursun2019Luminance, TITLE = {Luminance-Contrast-Aware Foveated Rendering}, AUTHOR = {Tursun, Okan Tarhan and Arabadzhiyska, Elena and Wernikowski, Marek and Mantiuk, Rados{\l}aw and Seidel, Hans-Peter and Myszkowski, Karol and Didyk, Piotr}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3306346.3322985}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {ACM Transactions on Graphics (Proc. ACM SIGGRAPH)}, VOLUME = {38}, NUMBER = {4}, EID = {98}, BOOKTITLE = {Proceedings of ACM SIGGRAPH 2019}, }
Endnote
%0 Journal Article %A Tursun, Okan Tarhan %A Arabadzhiyska, Elena %A Wernikowski, Marek %A Mantiuk, Radosław %A Seidel, Hans-Peter %A Myszkowski, Karol %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 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 Luminance-Contrast-Aware Foveated Rendering : %G eng %U http://hdl.handle.net/21.11116/0000-0003-75D5-9 %R 10.1145/3306346.3322985 %7 2019 %D 2019 %J ACM Transactions on Graphics %V 38 %N 4 %Z sequence number: 98 %I ACM %C New York, NY %@ false %B Proceedings of ACM SIGGRAPH 2019 %O ACM SIGGRAPH 2019 Los Angeles, CA, USA, 28 July - 1 August
Wolski, K., Giunchi,, D., Kinuwaki, S., et al. 2019. Selecting Texture Resolution Using a Task-specific Visibility Metric. Computer Graphics Forum (Proc. Pacific Graphics 2019)38, 7.
Export
BibTeX
@article{Wolski_PG2019, TITLE = {Selecting Texture Resolution Using a Task-specific Visibility Metric}, AUTHOR = {Wolski, Krzysztof and Giunchi,, Daniele and Kinuwaki, Shinichi and Didyk, Piotr and Myszkowski, Karol and Mantiuk, Rafa{\l} K. and Anthony, Steed}, LANGUAGE = {eng}, ISSN = {1467-8659}, DOI = {10.1111/cgf.13871}, PUBLISHER = {Wiley-Blackwell}, ADDRESS = {Oxford, UK}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {Computer Graphics Forum (Proc. Pacific Graphics)}, VOLUME = {38}, NUMBER = {7}, PAGES = {685--696}, BOOKTITLE = {27th Annual International Conference on Computer Graphics and Applications (Pacific Graphics 2019)}, }
Endnote
%0 Journal Article %A Wolski, Krzysztof %A Giunchi,, Daniele %A Kinuwaki, Shinichi %A Didyk, Piotr %A Myszkowski, Karol %A Mantiuk, Rafał K. %A Anthony, Steed %+ 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 External Organizations %T Selecting Texture Resolution Using a Task-specific Visibility Metric : %G eng %U http://hdl.handle.net/21.11116/0000-0004-9BB3-3 %R 10.1111/cgf.13871 %7 2019 %D 2019 %J Computer Graphics Forum %V 38 %N 7 %& 685 %P 685 - 696 %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
Xu, W., Chatterjee, A., Zollhöfer, M., et al. 2019a. Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera. IEEE Transactions on Visualization and Computer Graphics (Proc. IEEE VR 2019)25, 5.
Export
BibTeX
@article{Xu2019Mo2Cap2, 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}, ISSN = {1077-2626}, DOI = {10.1109/TVCG.2019.2898650}, PUBLISHER = {IEEE}, ADDRESS = {Piscataway, NJ}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {IEEE Transactions on Visualization and Computer Graphics (Proc. IEEE VR)}, VOLUME = {25}, NUMBER = {5}, PAGES = {2093--2101}, BOOKTITLE = {Selected Proceedings IEEE Virtual Reality 2019 (IEEE VR 2019)}, }
Endnote
%0 Journal Article %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/21.11116/0000-0002-F1DB-7 %R 10.1109/TVCG.2019.2898650 %7 2019 %D 2019 %J IEEE Transactions on Visualization and Computer Graphics %V 25 %N 5 %& 2093 %P 2093 - 2101 %I IEEE %C Piscataway, NJ %@ false %B Selected Proceedings IEEE Virtual Reality 2019 %O IEEE VR 2019 Osaka, Japan, March 23rd - 27th
Yu, H., Bemana, M., Wernikowski, M., et al. 2019. A Perception-driven Hybrid Decomposition for Multi-layer Accommodative Displays. IEEE Transactions on Visualization and Computer Graphics (Proc. IEEE VR 2019)25, 5.
Export
BibTeX
@article{Yu_VR2019, TITLE = {A Perception-driven Hybrid Decomposition for Multi-layer Accommodative Displays}, AUTHOR = {Yu, Hyeonseung and Bemana, Mojtaba and Wernikowski, Marek and Chwesiuk, Micha{\l} and Tursun, Okan Tarhan and Singh, Gurprit and Myszkowski, Karol and Mantiuk, Rados{\l}aw and Seidel, Hans-Peter and Didyk, Piotr}, LANGUAGE = {eng}, ISSN = {1077-2626}, DOI = {10.1109/TVCG.2019.2898821}, PUBLISHER = {IEEE Computer Society}, ADDRESS = {New York, NY}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, JOURNAL = {IEEE Transactions on Visualization and Computer Graphics (Proc. IEEE VR)}, VOLUME = {25}, NUMBER = {5}, PAGES = {1940--1950}, BOOKTITLE = {Selected Proceedings IEEE Virtual Reality 2019 (IEEE VR 2019)}, EDITOR = {Thomas, Bruce and Welch, Greg and Kuhlen, Torsten and Johnson, Kyle}, }
Endnote
%0 Journal Article %A Yu, Hyeonseung %A Bemana, Mojtaba %A Wernikowski, Marek %A Chwesiuk, Michał %A Tursun, Okan Tarhan %A Singh, Gurprit %A Myszkowski, Karol %A Mantiuk, Radosław %A Seidel, Hans-Peter %A Didyk, Piotr %+ 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 Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T A Perception-driven Hybrid Decomposition for Multi-layer Accommodative Displays : %G eng %U http://hdl.handle.net/21.11116/0000-0002-DCB5-A %R 10.1109/TVCG.2019.2898821 %7 2019 %D 2019 %J IEEE Transactions on Visualization and Computer Graphics %V 25 %N 5 %& 1940 %P 1940 - 1950 %I IEEE Computer Society %C New York, NY %@ false %B Selected Proceedings IEEE Virtual Reality 2019 %O IEEE VR 2019 Osaka, Japan, 23rd - 27th March
Conference Paper
Alldieck, T., Pons-Moll, G., Theobalt, C., and Magnor, M.A. Tex2Shape: Detailed Full Human Body Geometry from a Single Image. ICCV 2019, International Conference on Computer Vision, IEEE.
(arXiv: 1904.08645, Accepted/in press)
Abstract
We present a simple yet effective method to infer detailed full human body shape from only a single photograph. Our model can infer full-body shape including face, hair, and clothing including wrinkles at interactive frame-rates. Results feature details even on parts that are occluded in the input image. Our main idea is to turn shape regression into an aligned image-to-image translation problem. The input to our method is a partial texture map of the visible region obtained from off-the-shelf methods. From a partial texture, we estimate detailed normal and vector displacement maps, which can be applied to a low-resolution smooth body model to add detail and clothing. Despite being trained purely with synthetic data, our model generalizes well to real-world photographs. Numerous results demonstrate the versatility and robustness of our method.
Export
BibTeX
@inproceedings{Alldieck_arXiv1904.08645, TITLE = {{Tex2Shape}: Detailed Full Human Body Geometry from a Single Image}, AUTHOR = {Alldieck, Thiemo and Pons-Moll, Gerard and Theobalt, Christian and Magnor, Marcus A.}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1904.08645}, EPRINT = {1904.08645}, EPRINTTYPE = {arXiv}, PUBLISHER = {IEEE}, YEAR = {2019}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We present a simple yet effective method to infer detailed full human body shape from only a single photograph. Our model can infer full-body shape including face, hair, and clothing including wrinkles at interactive frame-rates. Results feature details even on parts that are occluded in the input image. Our main idea is to turn shape regression into an aligned image-to-image translation problem. The input to our method is a partial texture map of the visible region obtained from off-the-shelf methods. From a partial texture, we estimate detailed normal and vector displacement maps, which can be applied to a low-resolution smooth body model to add detail and clothing. Despite being trained purely with synthetic data, our model generalizes well to real-world photographs. Numerous results demonstrate the versatility and robustness of our method.}, BOOKTITLE = {ICCV 2019, International Conference on Computer Vision}, ADDRESS = {Seoul, Korea}, }
Endnote
%0 Conference Proceedings %A Alldieck, Thiemo %A Pons-Moll, Gerard %A Theobalt, Christian %A Magnor, Marcus A. %+ External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Tex2Shape: Detailed Full Human Body Geometry from a Single Image : %G eng %U http://hdl.handle.net/21.11116/0000-0003-ECBE-E %U http://arxiv.org/abs/1904.08645 %D 2019 %B International Conference on Computer Vision %Z date of event: 2019-10-27 - 2019-11-02 %C Seoul, Korea %X We present a simple yet effective method to infer detailed full human body shape from only a single photograph. Our model can infer full-body shape including face, hair, and clothing including wrinkles at interactive frame-rates. Results feature details even on parts that are occluded in the input image. Our main idea is to turn shape regression into an aligned image-to-image translation problem. The input to our method is a partial texture map of the visible region obtained from off-the-shelf methods. From a partial texture, we estimate detailed normal and vector displacement maps, which can be applied to a low-resolution smooth body model to add detail and clothing. Despite being trained purely with synthetic data, our model generalizes well to real-world photographs. Numerous results demonstrate the versatility and robustness of our method. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV %B ICCV 2019 %I IEEE
Alldieck, T., Magnor, M.A., Bhatnagar, B.L., Theobalt, C., and Pons-Moll, G. 2019a. Learning to Reconstruct People in Clothing from a Single RGB Camera. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), IEEE.
Export
BibTeX
@inproceedings{alldieck19cvpr, TITLE = {Learning to Reconstruct People in Clothing from a Single {RGB} Camera}, AUTHOR = {Alldieck, Thiemo and Magnor, Marcus A. and Bhatnagar, Bharat Lal and Theobalt, Christian and Pons-Moll, Gerard}, ISBN = {978-1-7281-3293-8}, DOI = {10.1109/CVPR.2019.00127}, PUBLISHER = {IEEE}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019)}, PAGES = {1175--1186}, ADDRESS = {Long Beach, CA, USA}, }
Endnote
%0 Conference Proceedings %A Alldieck, Thiemo %A Magnor, Marcus A. %A Bhatnagar, Bharat Lal %A Theobalt, Christian %A Pons-Moll, Gerard %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Learning to Reconstruct People in Clothing from a Single RGB Camera : %U http://hdl.handle.net/21.11116/0000-0003-5F97-9 %R 10.1109/CVPR.2019.00127 %D 2019 %B 32nd IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2019-06-15 - 2019-06-20 %C Long Beach, CA, USA %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 1175 - 1186 %I IEEE %@ 978-1-7281-3293-8
Bhatnagar, B.L., Tiwari, G., Theobalt, C., and Pons-Moll, G. Multi-Garment Net: Learning to Dress 3D People from Images. ICCV 2019, International Conference on Computer Vision, IEEE.
(arXiv: 1908.06903, Accepted/in press)
Abstract
We present Multi-Garment Network (MGN), a method to predict body shape and clothing, layered on top of the SMPL model from a few frames (1-8) of a video. Several experiments demonstrate that this representation allows higher level of control when compared to single mesh or voxel representations of shape. Our model allows to predict garment geometry, relate it to the body shape, and transfer it to new body shapes and poses. To train MGN, we leverage a digital wardrobe containing 712 digital garments in correspondence, obtained with a novel method to register a set of clothing templates to a dataset of real 3D scans of people in different clothing and poses. Garments from the digital wardrobe, or predicted by MGN, can be used to dress any body shape in arbitrary poses. We will make publicly available the digital wardrobe, the MGN model, and code to dress SMPL with the garments.
Export
BibTeX
@inproceedings{bhatnagar2019mgn, TITLE = {Multi-Garment Net: {L}earning to Dress {3D} People from Images}, AUTHOR = {Bhatnagar, Bharat Lal and Tiwari, Garvita and Theobalt, Christian and Pons-Moll, Gerard}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1908.06903}, EPRINT = {1908.06903}, EPRINTTYPE = {arXiv}, PUBLISHER = {IEEE}, YEAR = {2019}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We present Multi-Garment Network (MGN), a method to predict body shape and clothing, layered on top of the SMPL model from a few frames (1-8) of a video. Several experiments demonstrate that this representation allows higher level of control when compared to single mesh or voxel representations of shape. Our model allows to predict garment geometry, relate it to the body shape, and transfer it to new body shapes and poses. To train MGN, we leverage a digital wardrobe containing 712 digital garments in correspondence, obtained with a novel method to register a set of clothing templates to a dataset of real 3D scans of people in different clothing and poses. Garments from the digital wardrobe, or predicted by MGN, can be used to dress any body shape in arbitrary poses. We will make publicly available the digital wardrobe, the MGN model, and code to dress SMPL with the garments.}, BOOKTITLE = {ICCV 2019, International Conference on Computer Vision}, ADDRESS = {Seoul, Korea}, }
Endnote
%0 Conference Proceedings %A Bhatnagar, Bharat Lal %A Tiwari, Garvita %A Theobalt, Christian %A Pons-Moll, Gerard %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Multi-Garment Net: Learning to Dress 3D People from Images : %G eng %U http://hdl.handle.net/21.11116/0000-0004-89E8-C %U http://arxiv.org/abs/1908.06903 %D 2019 %B International Conference on Computer Vision %Z date of event: 2019-10-27 - 2019-11-02 %C Seoul, Korea %X We present Multi-Garment Network (MGN), a method to predict body shape and clothing, layered on top of the SMPL model from a few frames (1-8) of a video. Several experiments demonstrate that this representation allows higher level of control when compared to single mesh or voxel representations of shape. Our model allows to predict garment geometry, relate it to the body shape, and transfer it to new body shapes and poses. To train MGN, we leverage a digital wardrobe containing 712 digital garments in correspondence, obtained with a novel method to register a set of clothing templates to a dataset of real 3D scans of people in different clothing and poses. Garments from the digital wardrobe, or predicted by MGN, can be used to dress any body shape in arbitrary poses. We will make publicly available the digital wardrobe, the MGN model, and code to dress SMPL with the garments. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV %B ICCV 2019 %I IEEE
Bojja, A.K., Mueller, F., Malireddi, S.R., et al. 2019. HandSeg: An Automatically Labeled Dataset for Hand Segmentation from Depth Images. 16th Conference on Computer and Robot Vision (CRV 2019), IEEE.
Export
BibTeX
@inproceedings{Malireddi_CRV2019, TITLE = {{HandSeg}: {An Automatically Labeled Dataset for Hand Segmentation from Depth Images}}, AUTHOR = {Bojja, Abhishake Kumar and Mueller, Franziska and Malireddi, Sri Raghu and Oberweger, Markus and Lepetit, Vincent and Theobalt, Christian and Yi, Kwang Moo and Tagliasacchi, Andrea}, LANGUAGE = {eng}, ISBN = {978-1-7281-1838-3}, DOI = {10.1109/CRV.2019.00028}, PUBLISHER = {IEEE}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, BOOKTITLE = {16th Conference on Computer and Robot Vision (CRV 2019)}, PAGES = {151--158}, ADDRESS = {Kingston, Canada}, }
Endnote
%0 Conference Proceedings %A Bojja, Abhishake Kumar %A Mueller, Franziska %A Malireddi, Sri Raghu %A Oberweger, Markus %A Lepetit, Vincent %A Theobalt, Christian %A Yi, Kwang Moo %A Tagliasacchi, Andrea %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations %T HandSeg: An Automatically Labeled Dataset for Hand Segmentation from Depth Images : %G eng %U http://hdl.handle.net/21.11116/0000-0005-6BC4-6 %R 10.1109/CRV.2019.00028 %D 2019 %B 16th Conference on Computer and Robot Vision %Z date of event: 2019-05-29 - 2019-05-31 %C Kingston, Canada %B 16th Conference on Computer and Robot Vision %P 151 - 158 %I IEEE %@ 978-1-7281-1838-3
Castelli Aleardi, L., Salihoglu, S., Singh, G., and Ovsjanikov, M. 2019. Spectral Measures of Distortion for Change Detection in Dynamic Graphs. Complex Networks and Their Applications VII, Springer.
Export
BibTeX
@inproceedings{Castelli_COMPLEX2018, TITLE = {Spectral Measures of Distortion for Change Detection in Dynamic Graphs}, AUTHOR = {Castelli Aleardi, Luca and Salihoglu, Semih and Singh, Gurprit and Ovsjanikov, Maks}, LANGUAGE = {eng}, ISBN = {978-3-030-05413-7; 978-3-030-05414-4}, DOI = {10.1007/978-3-030-05414-4_5}, PUBLISHER = {Springer}, YEAR = {2018}, MARGINALMARK = {$\bullet$}, DATE = {2019}, BOOKTITLE = {Complex Networks and Their Applications VII}, EDITOR = {Aiello, Luca Maria and Cherifi, Chantal and Cherifi, Hocine and Lambiotte, Renaud and Li{\'o}, Pietro and Rocha, Luis M.}, PAGES = {54--66}, SERIES = {Studies in Computational Intelligence}, VOLUME = {813}, ADDRESS = {Cambridge, UK}, }
Endnote
%0 Conference Proceedings %A Castelli Aleardi, Luca %A Salihoglu, Semih %A Singh, Gurprit %A Ovsjanikov, Maks %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Spectral Measures of Distortion for Change Detection in Dynamic Graphs : %G eng %U http://hdl.handle.net/21.11116/0000-0003-F1F9-4 %R 10.1007/978-3-030-05414-4_5 %D 2019 %B 7th International Conference on Complex Networks and Their Applications %Z date of event: 2018-12-11 - 2018-12-13 %C Cambridge, UK %B Complex Networks and Their Applications VII %E Aiello, Luca Maria; Cherifi, Chantal; Cherifi, Hocine; Lambiotte, Renaud; Lió, Pietro; Rocha, Luis M. %P 54 - 66 %I Springer %@ 978-3-030-05413-7 978-3-030-05414-4 %B Studies in Computational Intelligence %N 813
Díaz Barros, J.M., Golyanik, V., Varanasi, K., and Stricker, D. 2019. Face It!: A Pipeline for Real-Time Performance-Driven Facial Animation. IEEE International Conference on Image Processing (ICIP 2019), IEEE.
Export
BibTeX
@inproceedings{DiazBarros_ICIP2019, TITLE = {Face It!: {A} Pipeline for Real-Time Performance-Driven Facial Animation}, AUTHOR = {D{\'i}az Barros, Jilliam Mar{\'i}a and Golyanik, Vladislav and Varanasi, Kiran and Stricker, Didier}, LANGUAGE = {eng}, ISBN = {978-1-5386-6249-6}, DOI = {10.1109/ICIP.2019.8803330}, PUBLISHER = {IEEE}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE International Conference on Image Processing (ICIP 2019)}, PAGES = {2209--2213}, ADDRESS = {Taipei, Taiwan}, }
Endnote
%0 Conference Proceedings %A Díaz Barros, Jilliam María %A Golyanik, Vladislav %A Varanasi, Kiran %A Stricker, Didier %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations %T Face It!: A Pipeline for Real-Time Performance-Driven Facial Animation : %G eng %U http://hdl.handle.net/21.11116/0000-0005-982B-0 %R 10.1109/ICIP.2019.8803330 %D 2019 %B IEEE International Conference on Image Processing %Z date of event: 2019-09-22 - 2019-09-25 %C Taipei, Taiwan %B IEEE International Conference on Image Processing %P 2209 - 2213 %I IEEE %@ 978-1-5386-6249-6
Golyanik, V. and Theobalt, C. 2019a. Optimising for Scale in Globally Multiply-Linked Gravitational Point Set Registration Leads to Singularities. International Conference on 3D Vision, IEEE.
Export
BibTeX
@inproceedings{Golyanik_3DV2019, TITLE = {Optimising for Scale in Globally Multiply-Linked Gravitational Point Set Registration Leads to Singularities}, AUTHOR = {Golyanik, Vladislav and Theobalt, Christian}, LANGUAGE = {eng}, ISBN = {978-1-7281-3131-3}, DOI = {10.1109/3DV.2019.00027}, PUBLISHER = {IEEE}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, BOOKTITLE = {International Conference on 3D Vision}, PAGES = {164--172}, ADDRESS = {Qu{\'e}bec City, Canada}, }
Endnote
%0 Conference Proceedings %A Golyanik, Vladislav %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Optimising for Scale in Globally Multiply-Linked Gravitational Point Set Registration Leads to Singularities : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7B4E-B %R 10.1109/3DV.2019.00027 %D 2019 %B International Conference on 3D Vision %Z date of event: 2019-09-16 - 2019-09-19 %C Québec City, Canada %B International Conference on 3D Vision %P 164 - 172 %I IEEE %@ 978-1-7281-3131-3
Golyanik, V., Jonas, A., and Stricker, D. 2019a. Consolidating Segmentwise Non-Rigid Structure from Motion. Proceedings of the Sixteenth International Conference on Machine Vision Applications (MVA 2019), IEEE.
Export
BibTeX
@inproceedings{Golyanik_MVA2019, TITLE = {Consolidating Segmentwise Non-Rigid Structure from Motion}, AUTHOR = {Golyanik, Vladislav and Jonas, Andr{\'e} and Stricker, Didier}, LANGUAGE = {eng}, ISBN = {978-4-901122-18-4}, DOI = {10.23919/MVA.2019.8757909}, PUBLISHER = {IEEE}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of the Sixteenth International Conference on Machine Vision Applications (MVA 2019)}, PAGES = {1--6}, ADDRESS = {Tokyo, Japan}, }
Endnote
%0 Conference Proceedings %A Golyanik, Vladislav %A Jonas, André %A Stricker, Didier %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations %T Consolidating Segmentwise Non-Rigid Structure from Motion : %G eng %U http://hdl.handle.net/21.11116/0000-0005-9823-8 %R 10.23919/MVA.2019.8757909 %D 2019 %B Sixteenth International Conference on Machine Vision Applications %Z date of event: 2019-05-27 - 2019-05-31 %C Tokyo, Japan %B Proceedings of the Sixteenth International Conference on Machine Vision Applications %P 1 - 6 %I IEEE %@ 978-4-901122-18-4
Golyanik, V., Theobalt, C., and Stricker, D. Accelerated Gravitational Point Set Alignment with Altered Physical Laws. ICCV 2019, International Conference on Computer Vision, IEEE.
(Accepted/in press)
Export
BibTeX
@inproceedings{BHRGA2019, TITLE = {Accelerated Gravitational Point Set Alignment with Altered Physical Laws}, AUTHOR = {Golyanik, Vladislav and Theobalt, Christian and Stricker, Didier}, LANGUAGE = {eng}, PUBLISHER = {IEEE}, YEAR = {2019}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {ICCV 2019, International Conference on Computer Vision}, ADDRESS = {Seoul, Korea}, }
Endnote
%0 Conference Proceedings %A Golyanik, Vladislav %A Theobalt, Christian %A Stricker, Didier %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Accelerated Gravitational Point Set Alignment with Altered Physical Laws : %G eng %U http://hdl.handle.net/21.11116/0000-0005-9473-2 %D 2019 %B International Conference on Computer Vision %Z date of event: 2019-10-27 - 2019-11-02 %C Seoul, Korea %B ICCV 2019 %I IEEE
Habermann, M., Xu, W., Rohdin, H., Zollhöfer, M., Pons-Moll, G., and Theobalt, C. 2019b. NRST: Non-rigid Surface Tracking from Monocular Video. Pattern Recognition (GCPR 2018), Springer.
Export
BibTeX
@inproceedings{Habermann_GVPR18, TITLE = {{NRST}: {N}on-rigid Surface Tracking from Monocular Video}, AUTHOR = {Habermann, Marc and Xu, Weipeng and Rohdin, Helge and Zollh{\"o}fer, Michael and Pons-Moll, Gerard and Theobalt, Christian}, LANGUAGE = {eng}, ISBN = {978-3-030-12938-5}, DOI = {10.1007/978-3-030-12939-2_23}, PUBLISHER = {Springer}, YEAR = {2018}, MARGINALMARK = {$\bullet$}, DATE = {2019}, BOOKTITLE = {Pattern Recognition (GCPR 2018)}, EDITOR = {Brox, Thomas and Bruhn, Andr{\'e}s and Fritz, Mario}, PAGES = {335--348}, SERIES = {Lecture Notes in Computer Science}, VOLUME = {11269}, ADDRESS = {Stuttgart, Germany}, }
Endnote
%0 Conference Proceedings %A Habermann, Marc %A Xu, Weipeng %A Rohdin, Helge %A Zollhöfer, Michael %A Pons-Moll, Gerard %A Theobalt, Christian %+ 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 Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T NRST: Non-rigid Surface Tracking from Monocular Video : %G eng %U http://hdl.handle.net/21.11116/0000-0002-B94C-9 %R 10.1007/978-3-030-12939-2_23 %D 2019 %B 40th German Conference on Pattern Recognition %Z date of event: 2018-10-09 - 2018-10-12 %C Stuttgart, Germany %B Pattern Recognition %E Brox, Thomas; Bruhn, Andrés; Fritz, Mario %P 335 - 348 %I Springer %@ 978-3-030-12938-5 %B Lecture Notes in Computer Science %N 11269
Habibie, I., Xu, W., Mehta, D., Pons-Moll, G., and Theobalt, C. 2019a. In the Wild Human Pose Estimation using Explicit 2D Features and Intermediate 3D Representations. 32nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), IEEE.
Export
BibTeX
@inproceedings{habibieCVPR19, TITLE = {In the Wild Human Pose Estimation using Explicit {2D} Features and Intermediate 3D Representations}, AUTHOR = {Habibie, Ikhsanul and Xu, Weipeng and Mehta, Dushyant and Pons-Moll, Gerard and Theobalt, Christian}, LANGUAGE = {eng}, ISBN = {978-1-7281-3293-8}, DOI = {10.1109/CVPR.2019.01116}, PUBLISHER = {IEEE}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {32nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019)}, PAGES = {10897--10906}, ADDRESS = {Long Beach, CA, USA}, }
Endnote
%0 Conference Proceedings %A Habibie, Ikhsanul %A Xu, Weipeng %A Mehta, Dushyant %A Pons-Moll, Gerard %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 Machine Learning, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T In the Wild Human Pose Estimation using Explicit 2D Features and Intermediate 3D Representations : %G eng %U http://hdl.handle.net/21.11116/0000-0003-6520-7 %R 10.1109/CVPR.2019.01116 %D 2019 %B 32nd IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2019-06-15 - 2019-06-20 %C Long Beach, CA, USA %B 32nd IEEE Conference on Computer Vision and Pattern Recognition %P 10897 - 10906 %I IEEE %@ 978-1-7281-3293-8
Mehta, D., Kim, K.I., and Theobalt, C. 2019a. On Implicit Filter Level Sparsity in Convolutional Neural Networks. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), IEEE.
Export
BibTeX
@inproceedings{Mehta_CVPR2019, TITLE = {On Implicit Filter Level Sparsity in Convolutional Neural Networks}, AUTHOR = {Mehta, Dushyant and Kim, Kwang In and Theobalt, Christian}, LANGUAGE = {eng}, ISBN = {978-1-7281-3293-8}, DOI = {10.1109/CVPR.2019.00061}, PUBLISHER = {IEEE}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019)}, PAGES = {520--528}, ADDRESS = {Long Beach, CA, USA}, }
Endnote
%0 Conference Proceedings %A Mehta, Dushyant %A Kim, Kwang In %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T On Implicit Filter Level Sparsity in Convolutional Neural Networks : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7CB8-1 %R 10.1109/CVPR.2019.00061 %D 2019 %B 32nd IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2019-06-16 - 2019-06-20 %C Long Beach, CA, USA %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 520 - 528 %I IEEE %@ 978-1-7281-3293-8
Mehta, D., Sotnychenko, O., Mueller, F., et al. 2019b. XNect Demo (v2): Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera. CVPR 2019 Demonstrations.
Export
BibTeX
@inproceedings{XNectDemoV2_CVPR2019, TITLE = {Demo of {VNect} (v2): {R}eal-time {3D} Human Pose Estimation with a Single {RGB} Camera}, AUTHOR = {Mehta, Dushyant and Sotnychenko, Oleksandr and Mueller, Franziska and Xu, Weipeng and Seidel, Hans-Peter and Fua, Pascal and Elgharib, Mohamed and Rhodin, Helge and Pons-Moll, Gerard and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://gvv.mpi-inf.mpg.de/projects/XNectDemoV2/}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {CVPR 2019 Demonstrations}, ADDRESS = {Long Beach, CA, USA}, }
Endnote
%0 Conference Proceedings %A Mehta, Dushyant %A Sotnychenko, Oleksandr %A Mueller, Franziska %A Xu, Weipeng %A Seidel, Hans-Peter %A Fua, Pascal %A Elgharib, Mohamed %A Rhodin, Helge %A Pons-Moll, Gerard %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 External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T XNect Demo (v2): Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera : %G eng %U http://hdl.handle.net/21.11116/0000-0004-71DB-6 %U http://gvv.mpi-inf.mpg.de/projects/XNectDemoV2/ %D 2019 %B 32nd IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2019-06-16 - 2019-06-20 %C Long Beach, CA, USA %B CVPR 2019 Demonstrations %U http://gvv.mpi-inf.mpg.de/projects/XNectDemoV2/
Shekhar, S., Semmo, A., Trapp, M., et al. Consistent Filtering of Videos and Dense Light-Fields without Optic-Flow. Vision, Modeling and Visualization 2019 (VMV 2019), Eurographics Association.
(Accepted/in press)
Export
BibTeX
@inproceedings{Shekhar_VMV2019, TITLE = {Consistent Filtering of Videos and Dense Light-Fields without Optic-Flow}, AUTHOR = {Shekhar, Sumit and Semmo, Amir and Trapp, Matthias and Tursun, Okan Tarhan and Pasewaldt, Sebastian and Myszkowski, Karol and D{\"o}llner, J{\"u}rgen}, LANGUAGE = {eng}, PUBLISHER = {Eurographics Association}, YEAR = {2019}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Vision, Modeling and Visualization 2019 (VMV 2019)}, ADDRESS = {Rostock, Germany}, }
Endnote
%0 Conference Proceedings %A Shekhar, Sumit %A Semmo, Amir %A Trapp, Matthias %A Tursun, Okan Tarhan %A Pasewaldt, Sebastian %A Myszkowski, Karol %A Döllner, Jürgen %+ 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 External Organizations %T Consistent Filtering of Videos and Dense Light-Fields without Optic-Flow : %G eng %U http://hdl.handle.net/21.11116/0000-0004-9C10-A %D 2019 %B 24th International Symposium on Vision, Modeling, and Visualization %Z date of event: 2019-09-30 - 2019-10-02 %C Rostock, Germany %B Vision, Modeling and Visualization 2019 %I Eurographics Association
Shimada, S., Golyanik, V., Theobalt, C., and Stricker, D. 2019a. IsMo-GAN: Adversarial Learning for Monocular Non-Rigid 3D Reconstruction. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2019), Computer Vision Foundation.
Export
BibTeX
@inproceedings{Shimada_2019, TITLE = {{IsMo-GAN}: {A}dversarial Learning for Monocular Non-Rigid {3D} Reconstruction}, AUTHOR = {Shimada, Soshi and Golyanik, Vladislav and Theobalt, Christian and Stricker, Didier}, LANGUAGE = {eng}, PUBLISHER = {Computer Vision Foundation}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2019)}, ADDRESS = {Long Beach, CA, USA}, }
Endnote
%0 Conference Proceedings %A Shimada, Soshi %A Golyanik, Vladislav %A Theobalt, Christian %A Stricker, Didier %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T IsMo-GAN: Adversarial Learning for Monocular Non-Rigid 3D Reconstruction : %G eng %U http://hdl.handle.net/21.11116/0000-0005-9410-1 %D 2019 %B Photogrammetric Computer Vision Workshop %Z date of event: 2019-06-17 - 2019-06-17 %C Long Beach, CA, USA %B IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops %I Computer Vision Foundation
Shimada, S., Golyanik, V., Tretschk, E., Stricker, D., and Theobalt, C. 2019b. DispVoxNets: Non-Rigid Point Set Alignment with Supervised Learning Proxies. International Conference on 3D Vision, IEEE.
Export
BibTeX
@inproceedings{Shimada_3DV2019, TITLE = {{DispVoxNets}: {N}on-Rigid Point Set Alignment with Supervised Learning Proxies}, AUTHOR = {Shimada, Soshi and Golyanik, Vladislav and Tretschk, Edgar and Stricker, Didier and Theobalt, Christian}, LANGUAGE = {eng}, ISBN = {978-1-7281-3131-3}, DOI = {10.1109/3DV.2019.00013}, PUBLISHER = {IEEE}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, BOOKTITLE = {International Conference on 3D Vision}, PAGES = {27--36}, ADDRESS = {Qu{\'e}bec City, Canada}, }
Endnote
%0 Conference Proceedings %A Shimada, Soshi %A Golyanik, Vladislav %A Tretschk, Edgar %A Stricker, Didier %A Theobalt, Christian %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T DispVoxNets: Non-Rigid Point Set Alignment with Supervised Learning Proxies : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7B48-1 %R 10.1109/3DV.2019.00013 %D 2019 %B International Conference on 3D Vision %Z date of event: 2019-09-16 - 2019-09-19 %C Québec City, Canada %B International Conference on 3D Vision %P 27 - 36 %I IEEE %@ 978-1-7281-3131-3
Su, Y., Golyanik, V., Minaskan, N., Ali, S.A., and Stricker, D. 2019. A Shape Completion Component for Monocular Non-Rigid SLAM. Adjunct Proceedings of the 2019 IEEE International Symposium on Mixed and Augmented Reality (ISMAR-Adjunct 2019), IEEE.
Export
BibTeX
@inproceedings{Su_ISMAR2019, TITLE = {A Shape Completion Component for Monocular Non-Rigid {SLAM}}, AUTHOR = {Su, Yongzhi and Golyanik, Vladislav and Minaskan, Nareg and Ali, Sk Aziz and Stricker, Didier}, LANGUAGE = {eng}, ISBN = {978-1-7281-4765-9}, DOI = {10.1109/ISMAR-Adjunct.2019.00-18}, PUBLISHER = {IEEE}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Adjunct Proceedings of the 2019 IEEE International Symposium on Mixed and Augmented Reality (ISMAR-Adjunct 2019)}, PAGES = {332--337}, ADDRESS = {Beijing, China}, }
Endnote
%0 Conference Proceedings %A Su, Yongzhi %A Golyanik, Vladislav %A Minaskan, Nareg %A Ali, Sk Aziz %A Stricker, Didier %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations %T A Shape Completion Component for Monocular Non-Rigid SLAM : %G eng %U http://hdl.handle.net/21.11116/0000-0005-9832-7 %R 10.1109/ISMAR-Adjunct.2019.00-18 %D 2019 %B IEEE International Symposium on Mixed and Augmented Reality %Z date of event: 2019-10-14 - 2019-10-18 %C Beijing, China %B Adjunct Proceedings of the 2019 IEEE International Symposium on Mixed and Augmented Reality %P 332 - 337 %I IEEE %@ 978-1-7281-4765-9
Swoboda, P., Kainmüller, D., Mokarian, A., Theobalt, C., and Bernard, F. 2019. A Convex Relaxation for Multi-Graph Matching. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), IEEE.
Export
BibTeX
@inproceedings{SwobodaCVPR2019a, TITLE = {A Convex Relaxation for Multi-Graph Matching}, AUTHOR = {Swoboda, Paul and Kainm{\"u}ller, Dagmar and Mokarian, Ashkan and Theobalt, Christian and Bernard, Florian}, LANGUAGE = {eng}, ISBN = {978-1-7281-3293-8}, DOI = {10.1109/CVPR.2019.01141}, PUBLISHER = {IEEE}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019)}, PAGES = {11156--11165}, ADDRESS = {Long Beach, CA, USA}, }
Endnote
%0 Conference Proceedings %A Swoboda, Paul %A Kainmüller, Dagmar %A Mokarian, Ashkan %A Theobalt, Christian %A Bernard, Florian %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T A Convex Relaxation for Multi-Graph Matching : %G eng %U http://hdl.handle.net/21.11116/0000-0005-74B8-9 %R 10.1109/CVPR.2019.01141 %D 2019 %B 32nd IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2019-06-15 - 2019-06-20 %C Long Beach, CA, USA %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 11156 - 11165 %I IEEE %@ 978-1-7281-3293-8
Tewari, A., Bernard, F., Garrido, P., et al. 2019. FML: Face Model Learning From Videos. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), IEEE.
Export
BibTeX
@inproceedings{TewariCVPR2019, TITLE = {{FML}: {F}ace 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}, ISBN = {978-1-7281-3293-8}, DOI = {10.1109/CVPR.2019.01107}, PUBLISHER = {IEEE}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019)}, PAGES = {10812--10822}, ADDRESS = {Long Beach, CA, USA}, }
Endnote
%0 Conference Proceedings %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 External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T FML: Face Model Learning From Videos : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7B0C-5 %R 10.1109/CVPR.2019.01107 %D 2019 %B 32nd IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2019-06-16 - 2019-06-20 %C Long Beach, CA, USA %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 10812 - 10822 %I IEEE %@ 978-1-7281-3293-8
Winter, M., Mlakar, D., Zayer, R., Seidel, H.-P., and Steinberger, M. 2019. Adaptive Sparse Matrix-Matrix Multiplication on the GPU. PPoPP’19, 24th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, ACM.
Export
BibTeX
@inproceedings{PPOPP:2019:ASPMM, TITLE = {Adaptive Sparse Matrix-Matrix Multiplication on the {GPU}}, AUTHOR = {Winter, Martin and Mlakar, Daniel and Zayer, Rhaleb and Seidel, Hans-Peter and Steinberger, Markus}, LANGUAGE = {eng}, ISBN = {978-1-4503-6225-2}, DOI = {10.1145/3293883.3295701}, PUBLISHER = {ACM}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, BOOKTITLE = {PPoPP'19, 24th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming}, PAGES = {68--81}, ADDRESS = {Washington, DC, 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 Adaptive Sparse Matrix-Matrix Multiplication on the GPU : %G eng %U http://hdl.handle.net/21.11116/0000-0002-EFE9-B %R 10.1145/3293883.3295701 %D 2019 %B 24th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming %Z date of event: 2019-02-16 - 2019-02-20 %C Washington, DC, USA %B PPoPP'19 %P 68 - 81 %I ACM %@ 978-1-4503-6225-2
Yenamandra, T., Bernard, F., Wang, J., Mueller, F., and Theobalt, C. 2019a. Convex Optimisation for Inverse Kinematics. International Conference on 3D Vision, IEEE.
Export
BibTeX
@inproceedings{Yenamandra_3DV2019, TITLE = {Convex Optimisation for Inverse Kinematics}, AUTHOR = {Yenamandra, Tarum and Bernard, Florian and Wang, Jiayi and Mueller, Franziska and Theobalt, Christian}, LANGUAGE = {eng}, ISBN = {978-1-7281-3131-3}, DOI = {10.1109/3DV.2019.00043}, PUBLISHER = {IEEE}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, BOOKTITLE = {International Conference on 3D Vision}, PAGES = {318--327}, ADDRESS = {Qu{\'e}bec City, Canada}, }
Endnote
%0 Conference Proceedings %A Yenamandra, Tarum %A Bernard, Florian %A Wang, Jiayi %A Mueller, Franziska %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 Convex Optimisation for Inverse Kinematics : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7B63-2 %R 10.1109/3DV.2019.00043 %D 2019 %B International Conference on 3D Vision %Z date of event: 2019-09-16 - 2019-09-19 %C Québec City, Canada %B International Conference on 3D Vision %P 318 - 327 %I IEEE %@ 978-1-7281-3131-3
Ye, N., Wolski, K., and Mantiuk, R.K. Predicting Visible Image Differences under Varying Display Brightness and Viewing Distance. 32nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), IEEE.
(Accepted/in press)
Export
BibTeX
@inproceedings{Ye19, TITLE = {Predicting Visible Image Differences under Varying Display Brightness and Viewing Distance}, AUTHOR = {Ye, Nanyang and Wolski, Krzysztof and Mantiuk, Rafa{\l} K.}, LANGUAGE = {eng}, PUBLISHER = {IEEE}, YEAR = {2019}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {32nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019)}, ADDRESS = {Long Beach, CA, USA}, }
Endnote
%0 Conference Proceedings %A Ye, Nanyang %A Wolski, Krzysztof %A Mantiuk, Rafał K. %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T Predicting Visible Image Differences under Varying Display Brightness and Viewing Distance : %G eng %U http://hdl.handle.net/21.11116/0000-0003-2748-1 %D 2019 %B 32nd IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2019-06-16 - 2019-06-20 %C Long Beach, CA, USA %B 32nd IEEE Conference on Computer Vision and Pattern Recognition %I IEEE
Yu, T., Zheng, Z., Zhong, Y., et al. SimulCap : Single-View Human Performance Capture with Cloth Simulation. 32nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), IEEE.
(Accepted/in press)
Export
BibTeX
@inproceedings{SimulCap19, TITLE = {{SimulCap} : {S}ingle-View Human Performance Capture with Cloth Simulation}, AUTHOR = {Yu, Tao and Zheng, Zerong and Zhong, Yuan and Zhao, Jianhui and Quionhai, Dai and Pons-Moll, Gerard and Liu, Yebin}, PUBLISHER = {IEEE}, YEAR = {2019}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {32nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019)}, ADDRESS = {Long Beach, CA, USA}, }
Endnote
%0 Conference Proceedings %A Yu, Tao %A Zheng, Zerong %A Zhong, Yuan %A Zhao, Jianhui %A Quionhai, Dai %A Pons-Moll, Gerard %A Liu, Yebin %+ External Organizations External Organizations External Organizations External Organizations External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T SimulCap : Single-View Human Performance Capture with Cloth Simulation : %U http://hdl.handle.net/21.11116/0000-0003-651E-B %D 2019 %B 32nd IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2019-06-16 - 2019-06-20 %C Long Beach, CA, USA %B 32nd IEEE Conference on Computer Vision and Pattern Recognition %I IEEE
Paper
Alldieck, T., Pons-Moll, G., Theobalt, C., and Magnor, M.A. 2019b. Tex2Shape: Detailed Full Human Body Geometry From a Single Image. http://arxiv.org/abs/1904.08645.
(arXiv: 1904.08645)
Abstract
We present a simple yet effective method to infer detailed full human body shape from only a single photograph. Our model can infer full-body shape including face, hair, and clothing including wrinkles at interactive frame-rates. Results feature details even on parts that are occluded in the input image. Our main idea is to turn shape regression into an aligned image-to-image translation problem. The input to our method is a partial texture map of the visible region obtained from off-the-shelf methods. From a partial texture, we estimate detailed normal and vector displacement maps, which can be applied to a low-resolution smooth body model to add detail and clothing. Despite being trained purely with synthetic data, our model generalizes well to real-world photographs. Numerous results demonstrate the versatility and robustness of our method.
Export
BibTeX
@online{Alldieck_arXiv1904.08645, TITLE = {{Tex2Shape}: Detailed Full Human Body Geometry From a Single Image}, AUTHOR = {Alldieck, Thiemo and Pons-Moll, Gerard and Theobalt, Christian and Magnor, Marcus A.}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1904.08645}, EPRINT = {1904.08645}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We present a simple yet effective method to infer detailed full human body shape from only a single photograph. Our model can infer full-body shape including face, hair, and clothing including wrinkles at interactive frame-rates. Results feature details even on parts that are occluded in the input image. Our main idea is to turn shape regression into an aligned image-to-image translation problem. The input to our method is a partial texture map of the visible region obtained from off-the-shelf methods. From a partial texture, we estimate detailed normal and vector displacement maps, which can be applied to a low-resolution smooth body model to add detail and clothing. Despite being trained purely with synthetic data, our model generalizes well to real-world photographs. Numerous results demonstrate the versatility and robustness of our method.}, }
Endnote
%0 Report %A Alldieck, Thiemo %A Pons-Moll, Gerard %A Theobalt, Christian %A Magnor, Marcus A. %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Tex2Shape: Detailed Full Human Body Geometry From a Single Image : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7CF6-B %U http://arxiv.org/abs/1904.08645 %D 2019 %X We present a simple yet effective method to infer detailed full human body shape from only a single photograph. Our model can infer full-body shape including face, hair, and clothing including wrinkles at interactive frame-rates. Results feature details even on parts that are occluded in the input image. Our main idea is to turn shape regression into an aligned image-to-image translation problem. The input to our method is a partial texture map of the visible region obtained from off-the-shelf methods. From a partial texture, we estimate detailed normal and vector displacement maps, which can be applied to a low-resolution smooth body model to add detail and clothing. Despite being trained purely with synthetic data, our model generalizes well to real-world photographs. Numerous results demonstrate the versatility and robustness of our method. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV
Alldieck, T., Magnor, M.A., Bhatnagar, B.L., Theobalt, C., and Pons-Moll, G. 2019c. Learning to Reconstruct People in Clothing from a Single RGB Camera. http://arxiv.org/abs/1903.05885.
(arXiv: 1903.05885)
Abstract
We present a learning-based model to infer the personalized 3D shape of people from a few frames (1-8) of a monocular video in which the person is moving, in less than 10 seconds with a reconstruction accuracy of 5mm. Our model learns to predict the parameters of a statistical body model and instance displacements that add clothing and hair to the shape. The model achieves fast and accurate predictions based on two key design choices. First, by predicting shape in a canonical T-pose space, the network learns to encode the images of the person into pose-invariant latent codes, where the information is fused. Second, based on the observation that feed-forward predictions are fast but do not always align with the input images, we predict using both, bottom-up and top-down streams (one per view) allowing information to flow in both directions. Learning relies only on synthetic 3D data. Once learned, the model can take a variable number of frames as input, and is able to reconstruct shapes even from a single image with an accuracy of 6mm. Results on 3 different datasets demonstrate the efficacy and accuracy of our approach.
Export
BibTeX
@online{Alldieck_arXiv1903.05885, TITLE = {Learning to Reconstruct People in Clothing from a Single {RGB} Camera}, AUTHOR = {Alldieck, Thiemo and Magnor, Marcus A. and Bhatnagar, Bharat Lal and Theobalt, Christian and Pons-Moll, Gerard}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1903.05885}, EPRINT = {1903.05885}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We present a learning-based model to infer the personalized 3D shape of people from a few frames (1-8) of a monocular video in which the person is moving, in less than 10 seconds with a reconstruction accuracy of 5mm. Our model learns to predict the parameters of a statistical body model and instance displacements that add clothing and hair to the shape. The model achieves fast and accurate predictions based on two key design choices. First, by predicting shape in a canonical T-pose space, the network learns to encode the images of the person into pose-invariant latent codes, where the information is fused. Second, based on the observation that feed-forward predictions are fast but do not always align with the input images, we predict using both, bottom-up and top-down streams (one per view) allowing information to flow in both directions. Learning relies only on synthetic 3D data. Once learned, the model can take a variable number of frames as input, and is able to reconstruct shapes even from a single image with an accuracy of 6mm. Results on 3 different datasets demonstrate the efficacy and accuracy of our approach.}, }
Endnote
%0 Report %A Alldieck, Thiemo %A Magnor, Marcus A. %A Bhatnagar, Bharat Lal %A Theobalt, Christian %A Pons-Moll, Gerard %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Learning to Reconstruct People in Clothing from a Single RGB Camera : %G eng %U http://hdl.handle.net/21.11116/0000-0003-FE01-E %U http://arxiv.org/abs/1903.05885 %D 2019 %X We present a learning-based model to infer the personalized 3D shape of people from a few frames (1-8) of a monocular video in which the person is moving, in less than 10 seconds with a reconstruction accuracy of 5mm. Our model learns to predict the parameters of a statistical body model and instance displacements that add clothing and hair to the shape. The model achieves fast and accurate predictions based on two key design choices. First, by predicting shape in a canonical T-pose space, the network learns to encode the images of the person into pose-invariant latent codes, where the information is fused. Second, based on the observation that feed-forward predictions are fast but do not always align with the input images, we predict using both, bottom-up and top-down streams (one per view) allowing information to flow in both directions. Learning relies only on synthetic 3D data. Once learned, the model can take a variable number of frames as input, and is able to reconstruct shapes even from a single image with an accuracy of 6mm. Results on 3 different datasets demonstrate the efficacy and accuracy of our approach. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV
Bemana, M., Myszkowski, K., Seidel, H.-P., and Ritschel, T. 2019b. Neural View-Interpolation for Sparse Light Field Video. http://arxiv.org/abs/1910.13921.
(arXiv: 1910.13921)
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.
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}, MARGINALMARK = {$\bullet$}, 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
Bhatnagar, B.L., Tiwari, G., Theobalt, C., and Pons-Moll, G. 2019. Multi-Garment Net: Learning to Dress 3D People from Images. http://arxiv.org/abs/1908.06903.
(arXiv: 1908.06903)
Abstract
We present Multi-Garment Network (MGN), a method to predict body shape and clothing, layered on top of the SMPL model from a few frames (1-8) of a video. Several experiments demonstrate that this representation allows higher level of control when compared to single mesh or voxel representations of shape. Our model allows to predict garment geometry, relate it to the body shape, and transfer it to new body shapes and poses. To train MGN, we leverage a digital wardrobe containing 712 digital garments in correspondence, obtained with a novel method to register a set of clothing templates to a dataset of real 3D scans of people in different clothing and poses. Garments from the digital wardrobe, or predicted by MGN, can be used to dress any body shape in arbitrary poses. We will make publicly available the digital wardrobe, the MGN model, and code to dress SMPL with the garments.
Export
BibTeX
@online{, TITLE = {Multi-Garment Net: {L}earning to Dress {3D} People from Images}, AUTHOR = {Bhatnagar, Bharat Lal and Tiwari, Garvita and Theobalt, Christian and Pons-Moll, Gerard}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1908.06903}, DOI = {Bhatnagar_arXiv1908.06903}, EPRINT = {1908.06903}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We present Multi-Garment Network (MGN), a method to predict body shape and clothing, layered on top of the SMPL model from a few frames (1-8) of a video. Several experiments demonstrate that this representation allows higher level of control when compared to single mesh or voxel representations of shape. Our model allows to predict garment geometry, relate it to the body shape, and transfer it to new body shapes and poses. To train MGN, we leverage a digital wardrobe containing 712 digital garments in correspondence, obtained with a novel method to register a set of clothing templates to a dataset of real 3D scans of people in different clothing and poses. Garments from the digital wardrobe, or predicted by MGN, can be used to dress any body shape in arbitrary poses. We will make publicly available the digital wardrobe, the MGN model, and code to dress SMPL with the garments.}, }
Endnote
%0 Report %A Bhatnagar, Bharat Lal %A Tiwari, Garvita %A Theobalt, Christian %A Pons-Moll, Gerard %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Multi-Garment Net: Learning to Dress 3D People from Images : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7D67-C %U http://arxiv.org/abs/1908.06903 %R Bhatnagar_arXiv1908.06903 %D 2019 %X We present Multi-Garment Network (MGN), a method to predict body shape and clothing, layered on top of the SMPL model from a few frames (1-8) of a video. Several experiments demonstrate that this representation allows higher level of control when compared to single mesh or voxel representations of shape. Our model allows to predict garment geometry, relate it to the body shape, and transfer it to new body shapes and poses. To train MGN, we leverage a digital wardrobe containing 712 digital garments in correspondence, obtained with a novel method to register a set of clothing templates to a dataset of real 3D scans of people in different clothing and poses. Garments from the digital wardrobe, or predicted by MGN, can be used to dress any body shape in arbitrary poses. We will make publicly available the digital wardrobe, the MGN model, and code to dress SMPL with the garments. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV
Božič, A., Zollhöfer, M., Theobalt, C., and Nießner, M. 2019. DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data. http://arxiv.org/abs/1912.04302.
(arXiv: 1912.04302)
Abstract
Applying data-driven approaches to non-rigid 3D reconstruction has been difficult, which we believe can be attributed to the lack of a large-scale training corpus. One recent approach proposes self-supervision based on non-rigid reconstruction. Unfortunately, this method fails for important cases such as highly non-rigid deformations. We first address this problem of lack of data by introducing a novel semi-supervised strategy to obtain dense inter-frame correspondences from a sparse set of annotations. This way, we obtain a large dataset of 400 scenes, over 390,000 RGB-D frames, and 2,537 densely aligned frame pairs; in addition, we provide a test set along with several metrics for evaluation. Based on this corpus, we introduce a data-driven non-rigid feature matching approach, which we integrate into an optimization-based reconstruction pipeline. Here, we propose a new neural network that operates on RGB-D frames, while maintaining robustness under large non-rigid deformations and producing accurate predictions. Our approach significantly outperforms both existing non-rigid reconstruction methods that do not use learned data terms, as well as learning-based approaches that only use self-supervision.
Export
BibTeX
@online{Bozic_arXiv1912.04302, TITLE = {{DeepDeform}: Learning Non-rigid {RGB}-D Reconstruction with Semi-supervised Data}, AUTHOR = {Bo{\v z}i{\v c}, Alja{\v z} and Zollh{\"o}fer, Michael and Theobalt, Christian and Nie{\ss}ner, Matthias}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1912.04302}, EPRINT = {1912.04302}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Applying data-driven approaches to non-rigid 3D reconstruction has been difficult, which we believe can be attributed to the lack of a large-scale training corpus. One recent approach proposes self-supervision based on non-rigid reconstruction. Unfortunately, this method fails for important cases such as highly non-rigid deformations. We first address this problem of lack of data by introducing a novel semi-supervised strategy to obtain dense inter-frame correspondences from a sparse set of annotations. This way, we obtain a large dataset of 400 scenes, over 390,000 RGB-D frames, and 2,537 densely aligned frame pairs; in addition, we provide a test set along with several metrics for evaluation. Based on this corpus, we introduce a data-driven non-rigid feature matching approach, which we integrate into an optimization-based reconstruction pipeline. Here, we propose a new neural network that operates on RGB-D frames, while maintaining robustness under large non-rigid deformations and producing accurate predictions. Our approach significantly outperforms both existing non-rigid reconstruction methods that do not use learned data terms, as well as learning-based approaches that only use self-supervision.}, }
Endnote
%0 Report %A Božič, Aljaž %A Zollhöfer, Michael %A Theobalt, Christian %A Nießner, Matthias %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7DDE-6 %U http://arxiv.org/abs/1912.04302 %D 2019 %X Applying data-driven approaches to non-rigid 3D reconstruction has been difficult, which we believe can be attributed to the lack of a large-scale training corpus. One recent approach proposes self-supervision based on non-rigid reconstruction. Unfortunately, this method fails for important cases such as highly non-rigid deformations. We first address this problem of lack of data by introducing a novel semi-supervised strategy to obtain dense inter-frame correspondences from a sparse set of annotations. This way, we obtain a large dataset of 400 scenes, over 390,000 RGB-D frames, and 2,537 densely aligned frame pairs; in addition, we provide a test set along with several metrics for evaluation. Based on this corpus, we introduce a data-driven non-rigid feature matching approach, which we integrate into an optimization-based reconstruction pipeline. Here, we propose a new neural network that operates on RGB-D frames, while maintaining robustness under large non-rigid deformations and producing accurate predictions. Our approach significantly outperforms both existing non-rigid reconstruction methods that do not use learned data terms, as well as learning-based approaches that only use self-supervision. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Graphics, cs.GR
Egger, B., Smith, W.A.P., Tewari, A., et al. 2019a. 3D Morphable Face Models -- Past, Present and Future. http://arxiv.org/abs/1909.01815.
(arXiv: 1909.01815)
Abstract
In this paper, we provide a detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed. The challenges in building and applying these models, namely capture, modeling, image formation, and image analysis, are still active research topics, and we review the state-of-the-art in each of these areas. We also look ahead, identifying unsolved challenges, proposing directions for future research and highlighting the broad range of current and future applications.
Export
BibTeX
@online{Egger_arXIv1909.01815, TITLE = {{3D} Morphable Face Models -- Past, Present and Future}, AUTHOR = {Egger, Bernhard and Smith, William A. P. and Tewari, Ayush and Wuhrer, Stefanie and Zollh{\"o}fer, Michael and Beeler, Thabo and Bernard, Florian and Bolkart, Timo and Kortylewski, Adam and Romdhani, Sami and Theobalt, Christian and Blanz, Volker and Vetter, Thomas}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1909.01815}, EPRINT = {1909.01815}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {In this paper, we provide a detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed. The challenges in building and applying these models, namely capture, modeling, image formation, and image analysis, are still active research topics, and we review the state-of-the-art in each of these areas. We also look ahead, identifying unsolved challenges, proposing directions for future research and highlighting the broad range of current and future applications.}, }
Endnote
%0 Report %A Egger, Bernhard %A Smith, William A. P. %A Tewari, Ayush %A Wuhrer, Stefanie %A Zollhöfer, Michael %A Beeler, Thabo %A Bernard, Florian %A Bolkart, Timo %A Kortylewski, Adam %A Romdhani, Sami %A Theobalt, Christian %A Blanz, Volker %A Vetter, Thomas %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations %T 3D Morphable Face Models -- Past, Present and Future : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7D8E-0 %U http://arxiv.org/abs/1909.01815 %D 2019 %X In this paper, we provide a detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed. The challenges in building and applying these models, namely capture, modeling, image formation, and image analysis, are still active research topics, and we review the state-of-the-art in each of these areas. We also look ahead, identifying unsolved challenges, proposing directions for future research and highlighting the broad range of current and future applications. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Graphics, cs.GR,Computer Science, Learning, cs.LG
Elgharib, M., BR, M., Tewari, A., et al. 2019. EgoFace: Egocentric Face Performance Capture and Videorealistic Reenactment. http://arxiv.org/abs/1905.10822.
(arXiv: 1905.10822)
Abstract
Face performance capture and reenactment techniques use multiple cameras and sensors, positioned at a distance from the face or mounted on heavy wearable devices. This limits their applications in mobile and outdoor environments. We present EgoFace, a radically new lightweight setup for face performance capture and front-view videorealistic reenactment using a single egocentric RGB camera. Our lightweight setup allows operations in uncontrolled environments, and lends itself to telepresence applications such as video-conferencing from dynamic environments. The input image is projected into a low dimensional latent space of the facial expression parameters. Through careful adversarial training of the parameter-space synthetic rendering, a videorealistic animation is produced. Our problem is challenging as the human visual system is sensitive to the smallest face irregularities that could occur in the final results. This sensitivity is even stronger for video results. Our solution is trained in a pre-processing stage, through a supervised manner without manual annotations. EgoFace captures a wide variety of facial expressions, including mouth movements and asymmetrical expressions. It works under varying illuminations, background, movements, handles people from different ethnicities and can operate in real time.
Export
BibTeX
@online{Elgharib_arXiv1905.10822, TITLE = {{EgoFace}: Egocentric Face Performance Capture and Videorealistic Reenactment}, AUTHOR = {Elgharib, Mohamed and BR, Mallikarjun and Tewari, Ayush and Kim, Hyeongwoo and Liu, Wentao and Seidel, Hans-Peter and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1905.10822}, EPRINT = {1905.10822}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Face performance capture and reenactment techniques use multiple cameras and sensors, positioned at a distance from the face or mounted on heavy wearable devices. This limits their applications in mobile and outdoor environments. We present EgoFace, a radically new lightweight setup for face performance capture and front-view videorealistic reenactment using a single egocentric RGB camera. Our lightweight setup allows operations in uncontrolled environments, and lends itself to telepresence applications such as video-conferencing from dynamic environments. The input image is projected into a low dimensional latent space of the facial expression parameters. Through careful adversarial training of the parameter-space synthetic rendering, a videorealistic animation is produced. Our problem is challenging as the human visual system is sensitive to the smallest face irregularities that could occur in the final results. This sensitivity is even stronger for video results. Our solution is trained in a pre-processing stage, through a supervised manner without manual annotations. EgoFace captures a wide variety of facial expressions, including mouth movements and asymmetrical expressions. It works under varying illuminations, background, movements, handles people from different ethnicities and can operate in real time.}, }
Endnote
%0 Report %A Elgharib, Mohamed %A BR, Mallikarjun %A Tewari, Ayush %A Kim, Hyeongwoo %A Liu, Wentao %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 EgoFace: Egocentric Face Performance Capture and Videorealistic Reenactment : %G eng %U http://hdl.handle.net/21.11116/0000-0003-F1E6-9 %U http://arxiv.org/abs/1905.10822 %D 2019 %X Face performance capture and reenactment techniques use multiple cameras and sensors, positioned at a distance from the face or mounted on heavy wearable devices. This limits their applications in mobile and outdoor environments. We present EgoFace, a radically new lightweight setup for face performance capture and front-view videorealistic reenactment using a single egocentric RGB camera. Our lightweight setup allows operations in uncontrolled environments, and lends itself to telepresence applications such as video-conferencing from dynamic environments. The input image is projected into a low dimensional latent space of the facial expression parameters. Through careful adversarial training of the parameter-space synthetic rendering, a videorealistic animation is produced. Our problem is challenging as the human visual system is sensitive to the smallest face irregularities that could occur in the final results. This sensitivity is even stronger for video results. Our solution is trained in a pre-processing stage, through a supervised manner without manual annotations. EgoFace captures a wide variety of facial expressions, including mouth movements and asymmetrical expressions. It works under varying illuminations, background, movements, handles people from different ethnicities and can operate in real time. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Graphics, cs.GR %U http://gvv.mpi-inf.mpg.de/projects/EgoFace/
Fried, O., Tewari, A., Zollhöfer, M., et al. 2019b. Text-based Editing of Talking-head Video. http://arxiv.org/abs/1906.01524.
(arXiv: 1906.01524)
Abstract
Editing talking-head video to change the speech content or to remove filler words is challenging. We propose a novel method to edit talking-head video based on its transcript to produce a realistic output video in which the dialogue of the speaker has been modified, while maintaining a seamless audio-visual flow (i.e. no jump cuts). Our method automatically annotates an input talking-head video with phonemes, visemes, 3D face pose and geometry, reflectance, expression and scene illumination per frame. To edit a video, the user has to only edit the transcript, and an optimization strategy then chooses segments of the input corpus as base material. The annotated parameters corresponding to the selected segments are seamlessly stitched together and used to produce an intermediate video representation in which the lower half of the face is rendered with a parametric face model. Finally, a recurrent video generation network transforms this representation to a photorealistic video that matches the edited transcript. We demonstrate a large variety of edits, such as the addition, removal, and alteration of words, as well as convincing language translation and full sentence synthesis.
Export
BibTeX
@online{Fried_arXiv1906.01524, TITLE = {Text-based Editing of Talking-head Video}, AUTHOR = {Fried, Ohad and Tewari, Ayush and Zollh{\"o}fer, Michael and Finkelstein, Adam and Shechtman, Eli and Goldman, Dan B. and Genova, Kyle and Jin, Zeyu and Theobalt, Christian and Agrawala, Maneesh}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1906.01524}, EPRINT = {1906.01524}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Editing talking-head video to change the speech content or to remove filler words is challenging. We propose a novel method to edit talking-head video based on its transcript to produce a realistic output video in which the dialogue of the speaker has been modified, while maintaining a seamless audio-visual flow (i.e. no jump cuts). Our method automatically annotates an input talking-head video with phonemes, visemes, 3D face pose and geometry, reflectance, expression and scene illumination per frame. To edit a video, the user has to only edit the transcript, and an optimization strategy then chooses segments of the input corpus as base material. The annotated parameters corresponding to the selected segments are seamlessly stitched together and used to produce an intermediate video representation in which the lower half of the face is rendered with a parametric face model. Finally, a recurrent video generation network transforms this representation to a photorealistic video that matches the edited transcript. We demonstrate a large variety of edits, such as the addition, removal, and alteration of words, as well as convincing language translation and full sentence synthesis.}, }
Endnote
%0 Report %A Fried, Ohad %A Tewari, Ayush %A Zollhöfer, Michael %A Finkelstein, Adam %A Shechtman, Eli %A Goldman, Dan B. %A Genova, Kyle %A Jin, Zeyu %A Theobalt, Christian %A Agrawala, Maneesh %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T Text-based Editing of Talking-head Video : %G eng %U http://hdl.handle.net/21.11116/0000-0003-FE15-8 %U http://arxiv.org/abs/1906.01524 %D 2019 %X Editing talking-head video to change the speech content or to remove filler words is challenging. We propose a novel method to edit talking-head video based on its transcript to produce a realistic output video in which the dialogue of the speaker has been modified, while maintaining a seamless audio-visual flow (i.e. no jump cuts). Our method automatically annotates an input talking-head video with phonemes, visemes, 3D face pose and geometry, reflectance, expression and scene illumination per frame. To edit a video, the user has to only edit the transcript, and an optimization strategy then chooses segments of the input corpus as base material. The annotated parameters corresponding to the selected segments are seamlessly stitched together and used to produce an intermediate video representation in which the lower half of the face is rendered with a parametric face model. Finally, a recurrent video generation network transforms this representation to a photorealistic video that matches the edited transcript. We demonstrate a large variety of edits, such as the addition, removal, and alteration of words, as well as convincing language translation and full sentence synthesis. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Graphics, cs.GR,Computer Science, Learning, cs.LG
Golyanik, V., Jonas, A., Stricker, D., and Theobalt, C. 2019b. Intrinsic Dynamic Shape Prior for Fast, Sequential and Dense Non-Rigid Structure from Motion with Detection of Temporally-Disjoint Rigidity. http://arxiv.org/abs/1909.02468.
(arXiv: 1909.02468)
Abstract
While dense non-rigid structure from motion (NRSfM) has been extensively studied from the perspective of the reconstructability problem over the recent years, almost no attempts have been undertaken to bring it into the practical realm. The reasons for the slow dissemination are the severe ill-posedness, high sensitivity to motion and deformation cues and the difficulty to obtain reliable point tracks in the vast majority of practical scenarios. To fill this gap, we propose a hybrid approach that extracts prior shape knowledge from an input sequence with NRSfM and uses it as a dynamic shape prior for sequential surface recovery in scenarios with recurrence. Our Dynamic Shape Prior Reconstruction (DSPR) method can be combined with existing dense NRSfM techniques while its energy functional is optimised with stochastic gradient descent at real-time rates for new incoming point tracks. The proposed versatile framework with a new core NRSfM approach outperforms several other methods in the ability to handle inaccurate and noisy point tracks, provided we have access to a representative (in terms of the deformation variety) image sequence. Comprehensive experiments highlight convergence properties and the accuracy of DSPR under different disturbing effects. We also perform a joint study of tracking and reconstruction and show applications to shape compression and heart reconstruction under occlusions. We achieve state-of-the-art metrics (accuracy and compression ratios) in different scenarios.
Export
BibTeX
@online{, TITLE = {Intrinsic Dynamic Shape Prior for Fast, Sequential and Dense Non-Rigid Structure from Motion with Detection of Temporally-Disjoint Rigidity}, AUTHOR = {Golyanik, Vladislav and Jonas, Andr{\'e} and Stricker, Didier and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1909.02468}, DOI = {Golyanik_arXiv1909.02468}, EPRINT = {1909.02468}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {While dense non-rigid structure from motion (NRSfM) has been extensively studied from the perspective of the reconstructability problem over the recent years, almost no attempts have been undertaken to bring it into the practical realm. The reasons for the slow dissemination are the severe ill-posedness, high sensitivity to motion and deformation cues and the difficulty to obtain reliable point tracks in the vast majority of practical scenarios. To fill this gap, we propose a hybrid approach that extracts prior shape knowledge from an input sequence with NRSfM and uses it as a dynamic shape prior for sequential surface recovery in scenarios with recurrence. Our Dynamic Shape Prior Reconstruction (DSPR) method can be combined with existing dense NRSfM techniques while its energy functional is optimised with stochastic gradient descent at real-time rates for new incoming point tracks. The proposed versatile framework with a new core NRSfM approach outperforms several other methods in the ability to handle inaccurate and noisy point tracks, provided we have access to a representative (in terms of the deformation variety) image sequence. Comprehensive experiments highlight convergence properties and the accuracy of DSPR under different disturbing effects. We also perform a joint study of tracking and reconstruction and show applications to shape compression and heart reconstruction under occlusions. We achieve state-of-the-art metrics (accuracy and compression ratios) in different scenarios.}, }
Endnote
%0 Report %A Golyanik, Vladislav %A Jonas, André %A Stricker, Didier %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Intrinsic Dynamic Shape Prior for Fast, Sequential and Dense Non-Rigid Structure from Motion with Detection of Temporally-Disjoint Rigidity : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7D9A-2 %U http://arxiv.org/abs/1909.02468 %R Golyanik_arXiv1909.02468 %D 2019 %X While dense non-rigid structure from motion (NRSfM) has been extensively studied from the perspective of the reconstructability problem over the recent years, almost no attempts have been undertaken to bring it into the practical realm. The reasons for the slow dissemination are the severe ill-posedness, high sensitivity to motion and deformation cues and the difficulty to obtain reliable point tracks in the vast majority of practical scenarios. To fill this gap, we propose a hybrid approach that extracts prior shape knowledge from an input sequence with NRSfM and uses it as a dynamic shape prior for sequential surface recovery in scenarios with recurrence. Our Dynamic Shape Prior Reconstruction (DSPR) method can be combined with existing dense NRSfM techniques while its energy functional is optimised with stochastic gradient descent at real-time rates for new incoming point tracks. The proposed versatile framework with a new core NRSfM approach outperforms several other methods in the ability to handle inaccurate and noisy point tracks, provided we have access to a representative (in terms of the deformation variety) image sequence. Comprehensive experiments highlight convergence properties and the accuracy of DSPR under different disturbing effects. We also perform a joint study of tracking and reconstruction and show applications to shape compression and heart reconstruction under occlusions. We achieve state-of-the-art metrics (accuracy and compression ratios) in different scenarios. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV
Golyanik, V. and Theobalt, C. 2019b. A Quantum Computational Approach to Correspondence Problems on Point Sets. http://arxiv.org/abs/1912.12296.
(arXiv: 1912.12296)
Abstract
Modern adiabatic quantum computers (AQC) are already used to solve difficult combinatorial optimisation problems in various domains of science. Currently, only a few applications of AQC in computer vision have been demonstrated. We review modern AQC and derive the first algorithm for transformation estimation and point set alignment suitable for AQC. Our algorithm has a subquadratic computational complexity of state preparation. We perform a systematic experimental analysis of the proposed approach and show several examples of successful point set alignment by simulated sampling. With this paper, we hope to boost the research on AQC for computer vision.
Export
BibTeX
@online{Golyanik_arXiv1912.12296, TITLE = {A Quantum Computational Approach to Correspondence Problems on Point Sets}, AUTHOR = {Golyanik, Vladislav and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1912.12296}, EPRINT = {1912.12296}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Modern adiabatic quantum computers (AQC) are already used to solve difficult combinatorial optimisation problems in various domains of science. Currently, only a few applications of AQC in computer vision have been demonstrated. We review modern AQC and derive the first algorithm for transformation estimation and point set alignment suitable for AQC. Our algorithm has a subquadratic computational complexity of state preparation. We perform a systematic experimental analysis of the proposed approach and show several examples of successful point set alignment by simulated sampling. With this paper, we hope to boost the research on AQC for computer vision.}, }
Endnote
%0 Report %A Golyanik, Vladislav %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T A Quantum Computational Approach to Correspondence Problems on Point Sets : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7DF0-0 %U http://arxiv.org/abs/1912.12296 %D 2019 %X Modern adiabatic quantum computers (AQC) are already used to solve difficult combinatorial optimisation problems in various domains of science. Currently, only a few applications of AQC in computer vision have been demonstrated. We review modern AQC and derive the first algorithm for transformation estimation and point set alignment suitable for AQC. Our algorithm has a subquadratic computational complexity of state preparation. We perform a systematic experimental analysis of the proposed approach and show several examples of successful point set alignment by simulated sampling. With this paper, we hope to boost the research on AQC for computer vision. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,cs.ET,Quantum Physics, quant-ph
Habibie, I., Xu, W., Mehta, D., Pons-Moll, G., and Theobalt, C. 2019b. In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations. http://arxiv.org/abs/1904.03289.
(arXiv: 1904.03289)
Abstract
Convolutional Neural Network based approaches for monocular 3D human pose estimation usually require a large amount of training images with 3D pose annotations. While it is feasible to provide 2D joint annotations for large corpora of in-the-wild images with humans, providing accurate 3D annotations to such in-the-wild corpora is hardly feasible in practice. Most existing 3D labelled data sets are either synthetically created or feature in-studio images. 3D pose estimation algorithms trained on such data often have limited ability to generalize to real world scene diversity. We therefore propose a new deep learning based method for monocular 3D human pose estimation that shows high accuracy and generalizes better to in-the-wild scenes. It has a network architecture that comprises a new disentangled hidden space encoding of explicit 2D and 3D features, and uses supervision by a new learned projection model from predicted 3D pose. Our algorithm can be jointly trained on image data with 3D labels and image data with only 2D labels. It achieves state-of-the-art accuracy on challenging in-the-wild data.
Export
BibTeX
@online{, TITLE = {In the Wild Human Pose Estimation Using Explicit {2D} Features and Intermediate {3D} Representations}, AUTHOR = {Habibie, Ikhsanul and Xu, Weipeng and Mehta, Dushyant and Pons-Moll, Gerard and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1904.03289}, EPRINT = {1904.03289}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Convolutional Neural Network based approaches for monocular 3D human pose estimation usually require a large amount of training images with 3D pose annotations. While it is feasible to provide 2D joint annotations for large corpora of in-the-wild images with humans, providing accurate 3D annotations to such in-the-wild corpora is hardly feasible in practice. Most existing 3D labelled data sets are either synthetically created or feature in-studio images. 3D pose estimation algorithms trained on such data often have limited ability to generalize to real world scene diversity. We therefore propose a new deep learning based method for monocular 3D human pose estimation that shows high accuracy and generalizes better to in-the-wild scenes. It has a network architecture that comprises a new disentangled hidden space encoding of explicit 2D and 3D features, and uses supervision by a new learned projection model from predicted 3D pose. Our algorithm can be jointly trained on image data with 3D labels and image data with only 2D labels. It achieves state-of-the-art accuracy on challenging in-the-wild data.}, }
Endnote
%0 Report %A Habibie, Ikhsanul %A Xu, Weipeng %A Mehta, Dushyant %A Pons-Moll, Gerard %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 Machine Learning, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations : %G eng %U http://hdl.handle.net/21.11116/0000-0003-F76E-C %U http://arxiv.org/abs/1904.03289 %D 2019 %X Convolutional Neural Network based approaches for monocular 3D human pose estimation usually require a large amount of training images with 3D pose annotations. While it is feasible to provide 2D joint annotations for large corpora of in-the-wild images with humans, providing accurate 3D annotations to such in-the-wild corpora is hardly feasible in practice. Most existing 3D labelled data sets are either synthetically created or feature in-studio images. 3D pose estimation algorithms trained on such data often have limited ability to generalize to real world scene diversity. We therefore propose a new deep learning based method for monocular 3D human pose estimation that shows high accuracy and generalizes better to in-the-wild scenes. It has a network architecture that comprises a new disentangled hidden space encoding of explicit 2D and 3D features, and uses supervision by a new learned projection model from predicted 3D pose. Our algorithm can be jointly trained on image data with 3D labels and image data with only 2D labels. It achieves state-of-the-art accuracy on challenging in-the-wild data. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV
Jiang, C., Tang, C., Seidel, H.-P., Chen, R., and Wonka, P. 2019. Computational Design of Lightweight Trusses. http://arxiv.org/abs/1901.05637.
(arXiv: 1901.05637)
Abstract
Trusses are load-carrying light-weight structures consisting of bars connected at joints ubiquitously applied in a variety of engineering scenarios. Designing optimal trusses that satisfy functional specifications with a minimal amount of material has interested both theoreticians and practitioners for more than a century. In this paper, we introduce two main ideas to improve upon the state of the art. First, we formulate an alternating linear programming problem for geometry optimization. Second, we introduce two sets of complementary topological operations, including a novel subdivision scheme for global topology refinement inspired by Michell's famed theoretical study. Based on these two ideas, we build an efficient computational framework for the design of lightweight trusses. \AD{We illustrate our framework with a variety of functional specifications and extensions. We show that our method achieves trusses with smaller volumes and is over two orders of magnitude faster compared with recent state-of-the-art approaches.
Export
BibTeX
@online{Jiang_arXIv1901.05637, TITLE = {Computational Design of Lightweight Trusses}, AUTHOR = {Jiang, Caigui and Tang, Chengcheng and Seidel, Hans-Peter and Chen, Renjie and Wonka, Peter}, URL = {http://arxiv.org/abs/1901.05637}, EPRINT = {1901.05637}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Trusses are load-carrying light-weight structures consisting of bars connected at joints ubiquitously applied in a variety of engineering scenarios. Designing optimal trusses that satisfy functional specifications with a minimal amount of material has interested both theoreticians and practitioners for more than a century. In this paper, we introduce two main ideas to improve upon the state of the art. First, we formulate an alternating linear programming problem for geometry optimization. Second, we introduce two sets of complementary topological operations, including a novel subdivision scheme for global topology refinement inspired by Michell's famed theoretical study. Based on these two ideas, we build an efficient computational framework for the design of lightweight trusses. \AD{We illustrate our framework with a variety of functional specifications and extensions. We show that our method achieves trusses with smaller volumes and is over two orders of magnitude faster compared with recent state-of-the-art approaches.}, }
Endnote
%0 Report %A Jiang, Caigui %A Tang, Chengcheng %A Seidel, Hans-Peter %A Chen, Renjie %A Wonka, 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 External Organizations %T Computational Design of Lightweight Trusses : %U http://hdl.handle.net/21.11116/0000-0003-A7E9-A %U http://arxiv.org/abs/1901.05637 %D 2019 %X Trusses are load-carrying light-weight structures consisting of bars connected at joints ubiquitously applied in a variety of engineering scenarios. Designing optimal trusses that satisfy functional specifications with a minimal amount of material has interested both theoreticians and practitioners for more than a century. In this paper, we introduce two main ideas to improve upon the state of the art. First, we formulate an alternating linear programming problem for geometry optimization. Second, we introduce two sets of complementary topological operations, including a novel subdivision scheme for global topology refinement inspired by Michell's famed theoretical study. Based on these two ideas, we build an efficient computational framework for the design of lightweight trusses. \AD{We illustrate our framework with a variety of functional specifications and extensions. We show that our method achieves trusses with smaller volumes and is over two orders of magnitude faster compared with recent state-of-the-art approaches. %K Computer Science, Graphics, cs.GR
Liu, L., Xu, W., Zollhöfer, M., et al. 2019. Neural Animation and Reenactment of Human Actor Videos. ACM Transactions on Graphics 38.
Abstract
4
Export
BibTeX
@misc{Liu_2019, TITLE = {Neural Animation and Reenactment of Human Actor Videos}, AUTHOR = {Liu, Lingjie and Xu, Weipeng and Zollh{\"o}fer, Michael and Kim, Hyeongwoo and Bernard, Florian and Habermann, Marc and Wang, Wenping and Theobalt, Christian}, LANGUAGE = {eng}, ISSN = {0730-0301}, DOI = {10.1145/3333002}, PUBLISHER = {Association for Computing Machinery}, ADDRESS = {New York, NY}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {4}, JOURNAL = {ACM Transactions on Graphics}, VOLUME = {38}, ISSUE = {5}, EID = {139}, }
Endnote
%0 Report %A Liu, Lingjie %A Xu, Weipeng %A Zollhöfer, Michael %A Kim, Hyeongwoo %A Bernard, Florian %A Habermann, Marc %A Wang, Wenping %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 External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Neural Animation and Reenactment of Human Actor Videos : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7B28-5 %R 10.1145/3333002 %D 2019 %X 4 %K 4 %J ACM Transactions on Graphics %V 38 %N 5 %Z sequence number: 139 %@ false
Mehta, D., Kim, K.I., and Theobalt, C. 2019c. Implicit Filter Sparsification In Convolutional Neural Networks. http://arxiv.org/abs/1905.04967.
(arXiv: 1905.04967)
Abstract
We show implicit filter level sparsity manifests in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularization or weight decay. Through an extensive empirical study (Mehta et al., 2019) we hypothesize the mechanism behind the sparsification process, and find surprising links to certain filter sparsification heuristics proposed in literature. Emergence of, and the subsequent pruning of selective features is observed to be one of the contributing mechanisms, leading to feature sparsity at par or better than certain explicit sparsification / pruning approaches. In this workshop article we summarize our findings, and point out corollaries of selective-featurepenalization which could also be employed as heuristics for filter pruning
Export
BibTeX
@online{Mehta_arXiv1905.04967, TITLE = {Implicit Filter Sparsification In Convolutional Neural Networks}, AUTHOR = {Mehta, Dushyant and Kim, Kwang In and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1905.04967}, EPRINT = {1905.04967}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We show implicit filter level sparsity manifests in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularization or weight decay. Through an extensive empirical study (Mehta et al., 2019) we hypothesize the mechanism behind the sparsification process, and find surprising links to certain filter sparsification heuristics proposed in literature. Emergence of, and the subsequent pruning of selective features is observed to be one of the contributing mechanisms, leading to feature sparsity at par or better than certain explicit sparsification / pruning approaches. In this workshop article we summarize our findings, and point out corollaries of selective-featurepenalization which could also be employed as heuristics for filter pruning}, }
Endnote
%0 Report %A Mehta, Dushyant %A Kim, Kwang In %A Theobalt, Christian %+ Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T Implicit Filter Sparsification In Convolutional Neural Networks : %G eng %U http://hdl.handle.net/21.11116/0000-0003-FE07-8 %U http://arxiv.org/abs/1905.04967 %D 2019 %X We show implicit filter level sparsity manifests in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularization or weight decay. Through an extensive empirical study (Mehta et al., 2019) we hypothesize the mechanism behind the sparsification process, and find surprising links to certain filter sparsification heuristics proposed in literature. Emergence of, and the subsequent pruning of selective features is observed to be one of the contributing mechanisms, leading to feature sparsity at par or better than certain explicit sparsification / pruning approaches. In this workshop article we summarize our findings, and point out corollaries of selective-featurepenalization which could also be employed as heuristics for filter pruning %K Computer Science, Learning, cs.LG,Computer Science, Computer Vision and Pattern Recognition, cs.CV,Statistics, Machine Learning, stat.ML
Mehta, D., Sotnychenko, O., Mueller, F., et al. 2019d. XNect: Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera. http://arxiv.org/abs/1907.00837.
(arXiv: 1907.00837)
Abstract
We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates in generic scenes and is robust to difficult occlusions both by other people and objects. Our method operates in subsequent stages. The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals. We contribute a new architecture for this CNN, called SelecSLS Net, that uses novel selective long and short range skip connections to improve the information flow allowing for a drastically faster network without compromising accuracy. In the second stage, a fully-connected neural network turns the possibly partial (on account of occlusion) 2D pose and 3D pose features for each subject into a complete 3D pose estimate per individual. The third stage applies space-time skeletal model fitting to the predicted 2D and 3D pose per subject to further reconcile the 2D and 3D pose, and enforce temporal coherence. Our method returns the full skeletal pose in joint angles for each subject. This is a further key distinction from previous work that neither extracted global body positions nor joint angle results of a coherent skeleton in real time for multi-person scenes. The proposed system runs on consumer hardware at a previously unseen speed of more than 30 fps given 512x320 images as input while achieving state-of-the-art accuracy, which we will demonstrate on a range of challenging real-world scenes.
Export
BibTeX
@online{Mehta_arXiv1907.00837, TITLE = {{XNect}: Real-time Multi-person {3D} Human Pose Estimation with a Single {RGB} Camera}, AUTHOR = {Mehta, Dushyant and Sotnychenko, Oleksandr and Mueller, Franziska and Xu, Weipeng and Elgharib, Mohamed and Fua, Pascal and Seidel, Hans-Peter and Rhodin, Helge and Pons-Moll, Gerard and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1907.00837}, EPRINT = {1907.00837}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates in generic scenes and is robust to difficult occlusions both by other people and objects. Our method operates in subsequent stages. The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals. We contribute a new architecture for this CNN, called SelecSLS Net, that uses novel selective long and short range skip connections to improve the information flow allowing for a drastically faster network without compromising accuracy. In the second stage, a fully-connected neural network turns the possibly partial (on account of occlusion) 2D pose and 3D pose features for each subject into a complete 3D pose estimate per individual. The third stage applies space-time skeletal model fitting to the predicted 2D and 3D pose per subject to further reconcile the 2D and 3D pose, and enforce temporal coherence. Our method returns the full skeletal pose in joint angles for each subject. This is a further key distinction from previous work that neither extracted global body positions nor joint angle results of a coherent skeleton in real time for multi-person scenes. The proposed system runs on consumer hardware at a previously unseen speed of more than 30 fps given 512x320 images as input while achieving state-of-the-art accuracy, which we will demonstrate on a range of challenging real-world scenes.}, }
Endnote
%0 Report %A Mehta, Dushyant %A Sotnychenko, Oleksandr %A Mueller, Franziska %A Xu, Weipeng %A Elgharib, Mohamed %A Fua, Pascal %A Seidel, Hans-Peter %A Rhodin, Helge %A Pons-Moll, Gerard %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 External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society %T XNect: Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera : %G eng %U http://hdl.handle.net/21.11116/0000-0003-FE21-A %U http://arxiv.org/abs/1907.00837 %D 2019 %X We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates in generic scenes and is robust to difficult occlusions both by other people and objects. Our method operates in subsequent stages. The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals. We contribute a new architecture for this CNN, called SelecSLS Net, that uses novel selective long and short range skip connections to improve the information flow allowing for a drastically faster network without compromising accuracy. In the second stage, a fully-connected neural network turns the possibly partial (on account of occlusion) 2D pose and 3D pose features for each subject into a complete 3D pose estimate per individual. The third stage applies space-time skeletal model fitting to the predicted 2D and 3D pose per subject to further reconcile the 2D and 3D pose, and enforce temporal coherence. Our method returns the full skeletal pose in joint angles for each subject. This is a further key distinction from previous work that neither extracted global body positions nor joint angle results of a coherent skeleton in real time for multi-person scenes. The proposed system runs on consumer hardware at a previously unseen speed of more than 30 fps given 512x320 images as input while achieving state-of-the-art accuracy, which we will demonstrate on a range of challenging real-world scenes. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Graphics, cs.GR
Shimada, S., Golyanik, V., Theobalt, C., and Stricker, D. 2019c. IsMo-GAN: Adversarial Learning for Monocular Non-Rigid 3D Reconstruction. http://arxiv.org/abs/1904.12144.
(arXiv: 1904.12144)
Abstract
The majority of the existing methods for non-rigid 3D surface regression from monocular 2D images require an object template or point tracks over multiple frames as an input, and are still far from real-time processing rates. In this work, we present the Isometry-Aware Monocular Generative Adversarial Network (IsMo-GAN) - an approach for direct 3D reconstruction from a single image, trained for the deformation model in an adversarial manner on a light-weight synthetic dataset. IsMo-GAN reconstructs surfaces from real images under varying illumination, camera poses, textures and shading at over 250 Hz. In multiple experiments, it consistently outperforms several approaches in the reconstruction accuracy, runtime, generalisation to unknown surfaces and robustness to occlusions. In comparison to the state-of-the-art, we reduce the reconstruction error by 10-30% including the textureless case and our surfaces evince fewer artefacts qualitatively.
Export
BibTeX
@online{Shimada_arXiv1904.12144, TITLE = {{IsMo}-{GAN}: Adversarial Learning for Monocular Non-Rigid {3D} Reconstruction}, AUTHOR = {Shimada, Soshi and Golyanik, Vladislav and Theobalt, Christian and Stricker, Didier}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1904.12144}, EPRINT = {1904.12144}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {The majority of the existing methods for non-rigid 3D surface regression from monocular 2D images require an object template or point tracks over multiple frames as an input, and are still far from real-time processing rates. In this work, we present the Isometry-Aware Monocular Generative Adversarial Network (IsMo-GAN) -- an approach for direct 3D reconstruction from a single image, trained for the deformation model in an adversarial manner on a light-weight synthetic dataset. IsMo-GAN reconstructs surfaces from real images under varying illumination, camera poses, textures and shading at over 250 Hz. In multiple experiments, it consistently outperforms several approaches in the reconstruction accuracy, runtime, generalisation to unknown surfaces and robustness to occlusions. In comparison to the state-of-the-art, we reduce the reconstruction error by 10-30% including the textureless case and our surfaces evince fewer artefacts qualitatively.}, }
Endnote
%0 Report %A Shimada, Soshi %A Golyanik, Vladislav %A Theobalt, Christian %A Stricker, Didier %+ External Organizations Computer Graphics, MPI for Informatics, Max Planck Society Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T IsMo-GAN: Adversarial Learning for Monocular Non-Rigid 3D Reconstruction : %G eng %U http://hdl.handle.net/21.11116/0000-0003-FE04-B %U http://arxiv.org/abs/1904.12144 %D 2019 %X The majority of the existing methods for non-rigid 3D surface regression from monocular 2D images require an object template or point tracks over multiple frames as an input, and are still far from real-time processing rates. In this work, we present the Isometry-Aware Monocular Generative Adversarial Network (IsMo-GAN) - an approach for direct 3D reconstruction from a single image, trained for the deformation model in an adversarial manner on a light-weight synthetic dataset. IsMo-GAN reconstructs surfaces from real images under varying illumination, camera poses, textures and shading at over 250 Hz. In multiple experiments, it consistently outperforms several approaches in the reconstruction accuracy, runtime, generalisation to unknown surfaces and robustness to occlusions. In comparison to the state-of-the-art, we reduce the reconstruction error by 10-30% including the textureless case and our surfaces evince fewer artefacts qualitatively. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV
Shimada, S., Golyanik, V., Tretschk, E., Stricker, D., and Theobalt, C. 2019d. DispVoxNets: Non-Rigid Point Set Alignment with Supervised Learning Proxies. http://arxiv.org/abs/1907.10367.
(arXiv: 1907.10367)
Abstract
We introduce a supervised-learning framework for non-rigid point set alignment of a new kind - Displacements on Voxels Networks (DispVoxNets) - which abstracts away from the point set representation and regresses 3D displacement fields on regularly sampled proxy 3D voxel grids. Thanks to recently released collections of deformable objects with known intra-state correspondences, DispVoxNets learn a deformation model and further priors (e.g., weak point topology preservation) for different object categories such as cloths, human bodies and faces. DispVoxNets cope with large deformations, noise and clustered outliers more robustly than the state-of-the-art. At test time, our approach runs orders of magnitude faster than previous techniques. All properties of DispVoxNets are ascertained numerically and qualitatively in extensive experiments and comparisons to several previous methods.
Export
BibTeX
@online{Shimada_arXiv1907.10367, TITLE = {{DispVoxNets}: {N}on-Rigid Point Set Alignment with Supervised Learning Proxies}, AUTHOR = {Shimada, Soshi and Golyanik, Vladislav and Tretschk, Edgar and Stricker, Didier and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1907.10367}, EPRINT = {1907.10367}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We introduce a supervised-learning framework for non-rigid point set alignment of a new kind -- Displacements on Voxels Networks (DispVoxNets) - which abstracts away from the point set representation and regresses 3D displacement fields on regularly sampled proxy 3D voxel grids. Thanks to recently released collections of deformable objects with known intra-state correspondences, DispVoxNets learn a deformation model and further priors (e.g., weak point topology preservation) for different object categories such as cloths, human bodies and faces. DispVoxNets cope with large deformations, noise and clustered outliers more robustly than the state-of-the-art. At test time, our approach runs orders of magnitude faster than previous techniques. All properties of DispVoxNets are ascertained numerically and qualitatively in extensive experiments and comparisons to several previous methods.}, }
Endnote
%0 Report %A Shimada, Soshi %A Golyanik, Vladislav %A Tretschk, Edgar %A Stricker, Didier %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 %T DispVoxNets: Non-Rigid Point Set Alignment with Supervised Learning Proxies : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7D04-B %U http://arxiv.org/abs/1907.10367 %D 2019 %X We introduce a supervised-learning framework for non-rigid point set alignment of a new kind - Displacements on Voxels Networks (DispVoxNets) - which abstracts away from the point set representation and regresses 3D displacement fields on regularly sampled proxy 3D voxel grids. Thanks to recently released collections of deformable objects with known intra-state correspondences, DispVoxNets learn a deformation model and further priors (e.g., weak point topology preservation) for different object categories such as cloths, human bodies and faces. DispVoxNets cope with large deformations, noise and clustered outliers more robustly than the state-of-the-art. At test time, our approach runs orders of magnitude faster than previous techniques. All properties of DispVoxNets are ascertained numerically and qualitatively in extensive experiments and comparisons to several previous methods. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Computational Geometry, cs.CG
Thies, J., Elgharib, M., Tewari, A., Theobalt, C., and Nießner, M. 2019b. Neural Voice Puppetry: Audio-driven Facial Reenactment. http://arxiv.org/abs/1912.05566.
(arXiv: 1912.05566)
Abstract
We present Neural Voice Puppetry, a novel approach for audio-driven facial video synthesis. Given an audio sequence of a source person or digital assistant, we generate a photo-realistic output video of a target person that is in sync with the audio of the source input. This audio-driven facial reenactment is driven by a deep neural network that employs a latent 3D face model space. Through the underlying 3D representation, the model inherently learns temporal stability while we leverage neural rendering to generate photo-realistic output frames. Our approach generalizes across different people, allowing us to synthesize videos of a target actor with the voice of any unknown source actor or even synthetic voices that can be generated utilizing standard text-to-speech approaches. Neural Voice Puppetry has a variety of use-cases, including audio-driven video avatars, video dubbing, and text-driven video synthesis of a talking head. We demonstrate the capabilities of our method in a series of audio- and text-based puppetry examples. Our method is not only more general than existing works since we are generic to the input person, but we also show superior visual and lip sync quality compared to photo-realistic audio- and video-driven reenactment techniques.
Export
BibTeX
@online{Thies_arXiv1912.05566, TITLE = {Neural Voice Puppetry: Audio-driven Facial Reenactment}, AUTHOR = {Thies, Justus and Elgharib, Mohamed and Tewari, Ayush and Theobalt, Christian and Nie{\ss}ner, Matthias}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1912.05566}, EPRINT = {1912.05566}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We present Neural Voice Puppetry, a novel approach for audio-driven facial video synthesis. Given an audio sequence of a source person or digital assistant, we generate a photo-realistic output video of a target person that is in sync with the audio of the source input. This audio-driven facial reenactment is driven by a deep neural network that employs a latent 3D face model space. Through the underlying 3D representation, the model inherently learns temporal stability while we leverage neural rendering to generate photo-realistic output frames. Our approach generalizes across different people, allowing us to synthesize videos of a target actor with the voice of any unknown source actor or even synthetic voices that can be generated utilizing standard text-to-speech approaches. Neural Voice Puppetry has a variety of use-cases, including audio-driven video avatars, video dubbing, and text-driven video synthesis of a talking head. We demonstrate the capabilities of our method in a series of audio- and text-based puppetry examples. Our method is not only more general than existing works since we are generic to the input person, but we also show superior visual and lip sync quality compared to photo-realistic audio- and video-driven reenactment techniques.}, }
Endnote
%0 Report %A Thies, Justus %A Elgharib, Mohamed %A Tewari, Ayush %A Theobalt, Christian %A Nießner, Matthias %+ 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 External Organizations %T Neural Voice Puppetry: Audio-driven Facial Reenactment : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7DE3-F %U http://arxiv.org/abs/1912.05566 %D 2019 %X We present Neural Voice Puppetry, a novel approach for audio-driven facial video synthesis. Given an audio sequence of a source person or digital assistant, we generate a photo-realistic output video of a target person that is in sync with the audio of the source input. This audio-driven facial reenactment is driven by a deep neural network that employs a latent 3D face model space. Through the underlying 3D representation, the model inherently learns temporal stability while we leverage neural rendering to generate photo-realistic output frames. Our approach generalizes across different people, allowing us to synthesize videos of a target actor with the voice of any unknown source actor or even synthetic voices that can be generated utilizing standard text-to-speech approaches. Neural Voice Puppetry has a variety of use-cases, including audio-driven video avatars, video dubbing, and text-driven video synthesis of a talking head. We demonstrate the capabilities of our method in a series of audio- and text-based puppetry examples. Our method is not only more general than existing works since we are generic to the input person, but we also show superior visual and lip sync quality compared to photo-realistic audio- and video-driven reenactment techniques. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Graphics, cs.GR
Tretschk, E., Tewari, A., Zollhöfer, M., Golyanik, V., and Theobalt, C. 2019. DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects. http://arxiv.org/abs/1905.10290.
(arXiv: 1905.10290)
Abstract
Mesh autoencoders are commonly used for dimensionality reduction, sampling and mesh modeling. We propose a general-purpose DEep MEsh Autoencoder (DEMEA) which adds a novel embedded deformation layer to a graph-convolutional mesh autoencoder. The embedded deformation layer (EDL) is a differentiable deformable geometric proxy which explicitly models point displacements of non-rigid deformations in a lower dimensional space and serves as a local rigidity regularizer. DEMEA decouples the parameterization of the deformation from the final mesh resolution since the deformation is defined over a lower dimensional embedded deformation graph. We perform a large-scale study on four different datasets of deformable objects. Reasoning about the local rigidity of meshes using EDL allows us to achieve higher-quality results for highly deformable objects, compared to directly regressing vertex positions. We demonstrate multiple applications of DEMEA, including non-rigid 3D reconstruction from depth and shading cues, non-rigid surface tracking, as well as the transfer of deformations over different meshes.
Export
BibTeX
@online{Tretschk_arXIv1905.10290, TITLE = {{DEMEA}: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects}, AUTHOR = {Tretschk, Edgar and Tewari, Ayush and Zollh{\"o}fer, Michael and Golyanik, Vladislav and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1905.10290}, EPRINT = {1905.10290}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Mesh autoencoders are commonly used for dimensionality reduction, sampling and mesh modeling. We propose a general-purpose DEep MEsh Autoencoder (DEMEA) which adds a novel embedded deformation layer to a graph-convolutional mesh autoencoder. The embedded deformation layer (EDL) is a differentiable deformable geometric proxy which explicitly models point displacements of non-rigid deformations in a lower dimensional space and serves as a local rigidity regularizer. DEMEA decouples the parameterization of the deformation from the final mesh resolution since the deformation is defined over a lower dimensional embedded deformation graph. We perform a large-scale study on four different datasets of deformable objects. Reasoning about the local rigidity of meshes using EDL allows us to achieve higher-quality results for highly deformable objects, compared to directly regressing vertex positions. We demonstrate multiple applications of DEMEA, including non-rigid 3D reconstruction from depth and shading cues, non-rigid surface tracking, as well as the transfer of deformations over different meshes.}, }
Endnote
%0 Report %A Tretschk, Edgar %A Tewari, Ayush %A Zollhöfer, Michael %A Golyanik, Vladislav %A Theobalt, Christian %+ 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 DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects : %G eng %U http://hdl.handle.net/21.11116/0000-0003-FE0C-3 %U http://arxiv.org/abs/1905.10290 %D 2019 %X Mesh autoencoders are commonly used for dimensionality reduction, sampling and mesh modeling. We propose a general-purpose DEep MEsh Autoencoder (DEMEA) which adds a novel embedded deformation layer to a graph-convolutional mesh autoencoder. The embedded deformation layer (EDL) is a differentiable deformable geometric proxy which explicitly models point displacements of non-rigid deformations in a lower dimensional space and serves as a local rigidity regularizer. DEMEA decouples the parameterization of the deformation from the final mesh resolution since the deformation is defined over a lower dimensional embedded deformation graph. We perform a large-scale study on four different datasets of deformable objects. Reasoning about the local rigidity of meshes using EDL allows us to achieve higher-quality results for highly deformable objects, compared to directly regressing vertex positions. We demonstrate multiple applications of DEMEA, including non-rigid 3D reconstruction from depth and shading cues, non-rigid surface tracking, as well as the transfer of deformations over different meshes. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Graphics, cs.GR
Xu, L., Xu, W., Golyanik, V., Habermann, M., Fang, L., and Theobalt, C. 2019b. EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Camera. http://arxiv.org/abs/1908.11505.
(arXiv: 1908.11505)
Abstract
The high frame rate is a critical requirement for capturing fast human motions. In this setting, existing markerless image-based methods are constrained by the lighting requirement, the high data bandwidth and the consequent high computation overhead. In this paper, we propose EventCap --- the first approach for 3D capturing of high-speed human motions using a single event camera. Our method combines model-based optimization and CNN-based human pose detection to capture high-frequency motion details and to reduce the drifting in the tracking. As a result, we can capture fast motions at millisecond resolution with significantly higher data efficiency than using high frame rate videos. Experiments on our new event-based fast human motion dataset demonstrate the effectiveness and accuracy of our method, as well as its robustness to challenging lighting conditions.
Export
BibTeX
@online{, TITLE = {{EventCap}: Monocular {3D} Capture of High-Speed Human Motions using an Event Camera}, AUTHOR = {Xu, Lan and Xu, Weipeng and Golyanik, Vladislav and Habermann, Marc and Fang, Lu and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1908.11505}, DOI = {Xu_arXiv1908.11505}, EPRINT = {1908.11505}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {The high frame rate is a critical requirement for capturing fast human motions. In this setting, existing markerless image-based methods are constrained by the lighting requirement, the high data bandwidth and the consequent high computation overhead. In this paper, we propose EventCap --- the first approach for 3D capturing of high-speed human motions using a single event camera. Our method combines model-based optimization and CNN-based human pose detection to capture high-frequency motion details and to reduce the drifting in the tracking. As a result, we can capture fast motions at millisecond resolution with significantly higher data efficiency than using high frame rate videos. Experiments on our new event-based fast human motion dataset demonstrate the effectiveness and accuracy of our method, as well as its robustness to challenging lighting conditions.}, }
Endnote
%0 Report %A Xu, Lan %A Xu, Weipeng %A Golyanik, Vladislav %A Habermann, Marc %A Fang, Lu %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 External Organizations Computer Graphics, MPI for Informatics, Max Planck Society %T EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Camera : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7D7B-6 %U http://arxiv.org/abs/1908.11505 %R Xu_arXiv1908.11505 %D 2019 %X The high frame rate is a critical requirement for capturing fast human motions. In this setting, existing markerless image-based methods are constrained by the lighting requirement, the high data bandwidth and the consequent high computation overhead. In this paper, we propose EventCap --- the first approach for 3D capturing of high-speed human motions using a single event camera. Our method combines model-based optimization and CNN-based human pose detection to capture high-frequency motion details and to reduce the drifting in the tracking. As a result, we can capture fast motions at millisecond resolution with significantly higher data efficiency than using high frame rate videos. Experiments on our new event-based fast human motion dataset demonstrate the effectiveness and accuracy of our method, as well as its robustness to challenging lighting conditions. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Graphics, cs.GR
Yenamandra, T., Bernard, F., Wang, J., Mueller, F., and Theobalt, C. 2019b. Convex Optimisation for Inverse Kinematics. http://arxiv.org/abs/1910.11016.
(arXiv: 1910.11016)
Abstract
We consider the problem of inverse kinematics (IK), where one wants to find the parameters of a given kinematic skeleton that best explain a set of observed 3D joint locations. The kinematic skeleton has a tree structure, where each node is a joint that has an associated geometric transformation that is propagated to all its child nodes. The IK problem has various applications in vision and graphics, for example for tracking or reconstructing articulated objects, such as human hands or bodies. Most commonly, the IK problem is tackled using local optimisation methods. A major downside of these approaches is that, due to the non-convex nature of the problem, such methods are prone to converge to unwanted local optima and therefore require a good initialisation. In this paper we propose a convex optimisation approach for the IK problem based on semidefinite programming, which admits a polynomial-time algorithm that globally solves (a relaxation of) the IK problem. Experimentally, we demonstrate that the proposed method significantly outperforms local optimisation methods using different real-world skeletons.
Export
BibTeX
@online{Yenamandra_arXiv1910.11016, TITLE = {Convex Optimisation for Inverse Kinematics}, AUTHOR = {Yenamandra, Tarum and Bernard, Florian and Wang, Jiayi and Mueller, Franziska and Theobalt, Christian}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1910.11016}, EPRINT = {1910.11016}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We consider the problem of inverse kinematics (IK), where one wants to find the parameters of a given kinematic skeleton that best explain a set of observed 3D joint locations. The kinematic skeleton has a tree structure, where each node is a joint that has an associated geometric transformation that is propagated to all its child nodes. The IK problem has various applications in vision and graphics, for example for tracking or reconstructing articulated objects, such as human hands or bodies. Most commonly, the IK problem is tackled using local optimisation methods. A major downside of these approaches is that, due to the non-convex nature of the problem, such methods are prone to converge to unwanted local optima and therefore require a good initialisation. In this paper we propose a convex optimisation approach for the IK problem based on semidefinite programming, which admits a polynomial-time algorithm that globally solves (a relaxation of) the IK problem. Experimentally, we demonstrate that the proposed method significantly outperforms local optimisation methods using different real-world skeletons.}, }
Endnote
%0 Report %A Yenamandra, Tarum %A Bernard, Florian %A Wang, Jiayi %A Mueller, Franziska %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 Convex Optimisation for Inverse Kinematics : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7DA8-2 %U http://arxiv.org/abs/1910.11016 %D 2019 %X We consider the problem of inverse kinematics (IK), where one wants to find the parameters of a given kinematic skeleton that best explain a set of observed 3D joint locations. The kinematic skeleton has a tree structure, where each node is a joint that has an associated geometric transformation that is propagated to all its child nodes. The IK problem has various applications in vision and graphics, for example for tracking or reconstructing articulated objects, such as human hands or bodies. Most commonly, the IK problem is tackled using local optimisation methods. A major downside of these approaches is that, due to the non-convex nature of the problem, such methods are prone to converge to unwanted local optima and therefore require a good initialisation. In this paper we propose a convex optimisation approach for the IK problem based on semidefinite programming, which admits a polynomial-time algorithm that globally solves (a relaxation of) the IK problem. Experimentally, we demonstrate that the proposed method significantly outperforms local optimisation methods using different real-world skeletons. %K Computer Science, Learning, cs.LG,Computer Science, Computer Vision and Pattern Recognition, cs.CV,Statistics, Machine Learning, stat.ML
Proceedings
Egger, B., Smith, W., Theobalt, C., and Vetter, T. 2019b. 3D Morphable Models. Schloss Dagstuhl.
Export
BibTeX
@proceedings{Egger_2019, TITLE = {3D Morphable Models}, AUTHOR = {Egger, Bernhard and Smith, William and Theobalt, Christian and Vetter, Thomas}, LANGUAGE = {eng}, URL = {urn:nbn:de:0030-drops-112894}, DOI = {10.4230/DagRep.9.3.16}, PUBLISHER = {Schloss Dagstuhl}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, SERIES = {Dagstuhl Reports}, VOLUME = {9}, ISSUE = {3}, PAGES = {16--38}, ADDRESS = {Dagstuhl, Germany}, }
Endnote
%0 Conference Proceedings %A Egger, Bernhard %A Smith, William %A Theobalt, Christian %A Vetter, Thomas %+ External Organizations External Organizations Computer Graphics, MPI for Informatics, Max Planck Society External Organizations %T 3D Morphable Models : %G eng %U http://hdl.handle.net/21.11116/0000-0005-7DF9-7 %U urn:nbn:de:0030-drops-112894 %R 10.4230/DagRep.9.3.16 %I Schloss Dagstuhl %D 2019 %B Dagstuhl Seminar 17201 "3D Morphable Models" %Z date of event: - %C Dagstuhl, Germany %S Dagstuhl Reports %V 9 %P 16 - 38 %U http://drops.dagstuhl.de/opus/volltexte/2019/11289/
Thesis
Leimkühler, T. 2019. Artificial Intelligence for Efficient Image-based View Synthesis. .
Abstract
Synthesizing novel views from image data is a widely investigated topic in both computer graphics and computer vision, and has many applications like stereo or multi-view rendering for virtual reality, light field reconstruction, and image post-processing. While image-based approaches have the advantage of reduced computational load compared to classical model-based rendering, efficiency is still a major concern. This thesis demonstrates how concepts and tools from artificial intelligence can be used to increase the efficiency of image-based view synthesis algorithms. In particular it is shown how machine learning can help to generate point patterns useful for a variety of computer graphics tasks, how path planning can guide image warping, how sparsity-enforcing optimization can lead to significant speedups in interactive distribution effect rendering, and how probabilistic inference can be used to perform real-time 2D-to-3D conversion.
Export
BibTeX
@phdthesis{Leimphd2019, TITLE = {Artificial Intelligence for Efficient Image-based View Synthesis}, AUTHOR = {Leimk{\"u}hler, Thomas}, LANGUAGE = {eng}, DOI = {10.22028/D291-28379}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, ABSTRACT = {Synthesizing novel views from image data is a widely investigated topic in both computer graphics and computer vision, and has many applications like stereo or multi-view rendering for virtual reality, light field reconstruction, and image post-processing. While image-based approaches have the advantage of reduced computational load compared to classical model-based rendering, efficiency is still a major concern. This thesis demonstrates how concepts and tools from artificial intelligence can be used to increase the efficiency of image-based view synthesis algorithms. In particular it is shown how machine learning can help to generate point patterns useful for a variety of computer graphics tasks, how path planning can guide image warping, how sparsity-enforcing optimization can lead to significant speedups in interactive distribution effect rendering, and how probabilistic inference can be used to perform real-time 2D-to-3D conversion.}, }
Endnote
%0 Thesis %A Leimkühler, Thomas %Y Seidel, Hans-Peter %A referee: Ritschel, Tobias %A referee: Lensch, Hendrik %A referee: Drettakis, George %+ Computer Graphics, MPI for Informatics, Max Planck Society International Max Planck Research School, 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 Artificial Intelligence for Efficient Image-based View Synthesis : %G eng %U http://hdl.handle.net/21.11116/0000-0004-A589-7 %R 10.22028/D291-28379 %I Universität des Saarlandes %C Saarbrücken %D 2019 %P 136 p. %V phd %9 phd %X Synthesizing novel views from image data is a widely investigated topic in both computer graphics and computer vision, and has many applications like stereo or multi-view rendering for virtual reality, light field reconstruction, and image post-processing. While image-based approaches have the advantage of reduced computational load compared to classical model-based rendering, efficiency is still a major concern. This thesis demonstrates how concepts and tools from artificial intelligence can be used to increase the efficiency of image-based view synthesis algorithms. In particular it is shown how machine learning can help to generate point patterns useful for a variety of computer graphics tasks, how path planning can guide image warping, how sparsity-enforcing optimization can lead to significant speedups in interactive distribution effect rendering, and how probabilistic inference can be used to perform real-time 2D-to-3D conversion. %U https://publikationen.sulb.uni-saarland.de/handle/20.500.11880/27664
Robertini, N. 2019. Model-based Human Performance Capture in Outdoor Scenes. urn:nbn:de:bsz:291--ds-285887.
Abstract
Technologies for motion and performance capture of real actors have enabled the creation of realisticlooking virtual humans through detail and deformation transfer at the cost of extensive manual work and sophisticated in-studio marker-based systems. This thesis pushes the boundaries of performance capture by proposing automatic algorithms for robust 3D skeleton and detailed surface tracking in less constrained multi-view outdoor scenarios. Contributions include new multi-layered human body representations designed for effective model-based time-consistent reconstruction in complex dynamic environments with varying illumination, from a set of vision cameras. We design dense surface refinement approaches to enable smooth silhouette-free model-to-image alignment, as well as coarse-to-fine tracking techniques to enable joint estimation of skeleton motion and finescale surface deformations in complicated scenarios. High-quality results attained on challenging application scenarios confirm the contributions and show great potential for the automatic creation of personalized 3D virtual humans.
Export
BibTeX
@phdthesis{Robertini_PhD2019, TITLE = {Model-based Human Performance Capture in Outdoor Scenes}, AUTHOR = {Robertini, Nadia}, LANGUAGE = {eng}, URL = {urn:nbn:de:bsz:291--ds-285887}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, DATE = {2019}, ABSTRACT = {Technologies for motion and performance capture of real actors have enabled the creation of realisticlooking virtual humans through detail and deformation transfer at the cost of extensive manual work and sophisticated in-studio marker-based systems. This thesis pushes the boundaries of performance capture by proposing automatic algorithms for robust 3D skeleton and detailed surface tracking in less constrained multi-view outdoor scenarios. Contributions include new multi-layered human body representations designed for effective model-based time-consistent reconstruction in complex dynamic environments with varying illumination, from a set of vision cameras. We design dense surface refinement approaches to enable smooth silhouette-free model-to-image alignment, as well as coarse-to-fine tracking techniques to enable joint estimation of skeleton motion and finescale surface deformations in complicated scenarios. High-quality results attained on challenging application scenarios confirm the contributions and show great potential for the automatic creation of personalized 3D virtual humans.}, }
Endnote
%0 Thesis %A Robertini, Nadia %Y Theobalt, Christian %A referee: Seidel, Hans-Peter %+ Computer Graphics, MPI for Informatics, Max Planck Society International Max Planck Research School, 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 Human Performance Capture in Outdoor Scenes : %G eng %U http://hdl.handle.net/21.11116/0000-0004-9B2E-B %U urn:nbn:de:bsz:291--ds-285887 %F OTHER: hdl:20.500.11880/27667 %I Universität des Saarlandes %C Saarbrücken %D 2019 %P XIX, 136, XI p. %V phd %9 phd %X Technologies for motion and performance capture of real actors have enabled the creation of realisticlooking virtual humans through detail and deformation transfer at the cost of extensive manual work and sophisticated in-studio marker-based systems. This thesis pushes the boundaries of performance capture by proposing automatic algorithms for robust 3D skeleton and detailed surface tracking in less constrained multi-view outdoor scenarios. Contributions include new multi-layered human body representations designed for effective model-based time-consistent reconstruction in complex dynamic environments with varying illumination, from a set of vision cameras. We design dense surface refinement approaches to enable smooth silhouette-free model-to-image alignment, as well as coarse-to-fine tracking techniques to enable joint estimation of skeleton motion and finescale surface deformations in complicated scenarios. High-quality results attained on challenging application scenarios confirm the contributions and show great potential for the automatic creation of personalized 3D virtual humans. %U https://scidok.sulb.uni-saarland.de/handle/20.500.11880/27667