Eldar Insafutdinov (PhD Student)

Personal Information

Personal Website

Publications

2020

Thesis

D2IMPR-CSD4

E. Insafutdinov

“Towards Accurate Multi-Person Pose Estimation in the Wild,” Universität des Saarlandes, Saarbrücken, 2020.

@phdthesis{Insaphd2020,
TITLE = {Towards Accurate Multi-Person Pose Estimation in the Wild},
AUTHOR = {Insafutdinov, Eldar},
LANGUAGE = {eng},
URL = {urn:nbn:de:bsz:291--ds-335121},
DOI = {10.22028/D291-33512},
SCHOOL = {Universit{\"a}t des Saarlandes},
ADDRESS = {Saarbr{\"u}cken},
YEAR = {2020},
DATE = {2020},
}

Endnote

%0 Thesis
%A Insafutdinov, Eldar
%Y Schiele, Bernt
%A referee: Rosenhahn, Bodo
%A referee: Denj, Jia
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
International Max Planck Research School, 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 Towards Accurate Multi-Person Pose Estimation in the Wild : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0008-8173-4
%R 10.22028/D291-33512
%U urn:nbn:de:bsz:291--ds-335121
%F OTHER: hdl:20.500.11880/31184
%I Universit&#228;t des Saarlandes
%C Saarbr&#252;cken
%D 2020
%P 161 p.
%V phd
%9 phd
%U https://publikationen.sulb.uni-saarland.de/handle/20.500.11880/31184

2019

Conference paper

V. Lazova, E. Insafutdinov, and G. Pons-Moll

“360-Degree Textures of People in Clothing from a Single Image,” in International Conference on 3D Vision, Québec City, Canada, 2019.

@inproceedings{Lazova_3DV2019,
TITLE = {360-Degree Textures of People in Clothing from a Single Image},
AUTHOR = {Lazova, Verica and Insafutdinov, Eldar and Pons-Moll, Gerard},
LANGUAGE = {eng},
ISBN = {978-1-7281-3131-3},
DOI = {10.1109/3DV.2019.00076},
PUBLISHER = {IEEE},
YEAR = {2019},
DATE = {2019},
BOOKTITLE = {International Conference on 3D Vision},
PAGES = {643--653},
ADDRESS = {Qu{\'e}bec City, Canada},
}

Endnote

%0 Conference Proceedings
%A Lazova, Verica
%A Insafutdinov, Eldar
%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 Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T 360-Degree Textures of People in Clothing from a Single Image : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0005-46EF-0
%R 10.1109/3DV.2019.00076
%D 2019
%B International Conference on 3D Vision
%Z date of event: 2019-09-16 - 2019-09-19
%C Qu&#233;bec City, Canada
%B International Conference on 3D Vision
%P 643 - 653
%I IEEE
%@ 978-1-7281-3131-3

2018

Conference paper

E. Insafutdinov and A. Dosovitskiy

“Unsupervised Learning of Shape and Pose with Differentiable Point Clouds,” in Advances in Neural Information Processing Systems 31 (NeurIPS 2018), Montréal, Canada, 2018.

@inproceedings{insafutdinov18pointclouds,
TITLE = {Unsupervised Learning of Shape and Pose with Differentiable Point Clouds},
AUTHOR = {Insafutdinov, Eldar and Dosovitskiy, Alexey},
LANGUAGE = {eng},
PUBLISHER = {Curran Associates},
YEAR = {2018},
BOOKTITLE = {Advances in Neural Information Processing Systems 31 (NeurIPS 2018)},
EDITOR = {Bengio, S. and Wallach, H. and Larochelle, H. and Grauman, K. and Cesa-Bianchi, N. and Garnett, R.},
PAGES = {2804--2814},
ADDRESS = {Montr{\'e}al, Canada},
}

Endnote

%0 Conference Proceedings
%A Insafutdinov, Eldar
%A Dosovitskiy, Alexey
%+ Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
External Organizations
%T Unsupervised Learning of Shape and Pose with Differentiable Point Clouds : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0002-6A15-0
%D 2018
%B Thirty-second Conference on Neural Information Processing Systems
%Z date of event: 2018-12-02 - 2018-12-08
%C Montr&#233;al, Canada
%B Advances in Neural Information Processing Systems 31
%E Bengio, S.; Wallach, H.; Larochelle, H.; Grauman, K.; Cesa-Bianchi, N.; Garnett, R.
%P 2804 - 2814
%I Curran Associates
%U http://papers.nips.cc/paper/7545-unsupervised-learning-of-shape-and-pose-with-differentiable-point-clouds.pdf

Conference paper

M. Andriluka, U. Iqbal, A. Milan, E. Insafutdinov, L. Pishchulin, J. Gall, and B. Schiele

“PoseTrack: A Benchmark for Human Pose Estimation and Tracking,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, UT, USA, 2018.

@inproceedings{Andriluka_2018_CVPR,
TITLE = {{PoseTrack}: A Benchmark for Human Pose Estimation and Tracking},
AUTHOR = {Andriluka, Mykhaylo and Iqbal, Umar and Milan, Anton and Insafutdinov, Eldar and Pishchulin, Leonid and Gall, Juergen and Schiele, Bernt},
LANGUAGE = {eng},
ISBN = {978-1-5386-6420-9},
DOI = {10.1109/CVPR.2018.00542},
PUBLISHER = {IEEE},
YEAR = {2018},
BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018)},
PAGES = {5167--5176},
ADDRESS = {Salt Lake City, UT, USA},
}

Endnote

%0 Conference Proceedings
%A Andriluka, Mykhaylo
%A Iqbal, Umar
%A Milan, Anton
%A Insafutdinov, Eldar
%A Pishchulin, Leonid
%A Gall, Juergen
%A Schiele, Bernt
%+ External Organizations
External Organizations
External Organizations
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
External Organizations
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
%T PoseTrack: A Benchmark for Human Pose Estimation and Tracking : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0000-CA48-C
%R 10.1109/CVPR.2018.00542
%D 2018
%B 31st IEEE Conference on Computer Vision and Pattern Recognition 
%Z date of event: 2018-06-18 - 2018-06-22
%C Salt Lake City, UT, USA
%B IEEE/CVF Conference on Computer Vision and Pattern Recognition
%P 5167 - 5176
%I IEEE
%@ 978-1-5386-6420-9

2017

Conference paper

E. Insafutdinov, M. Andriluka, L. Pishchulin, S. Tang, E. Levinkov, B. Andres, and B. Schiele

“ArtTrack: Articulated Multi-Person Tracking in the Wild,” in 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, HI, USA, 2017.

@inproceedings{insafutdinov17cvpr,
TITLE = {ArtTrack: {A}rticulated Multi-Person Tracking in the Wild},
AUTHOR = {Insafutdinov, Eldar and Andriluka, Mykhaylo and Pishchulin, Leonid and Tang, Siyu and Levinkov, Evgeny and Andres, Bjoern and Schiele, Bernt},
LANGUAGE = {eng},
ISBN = {978-1-5386-0458-8},
DOI = {10.1109/CVPR.2017.142},
PUBLISHER = {IEEE},
YEAR = {2017},
DATE = {2017},
BOOKTITLE = {30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)},
PAGES = {1293--1301},
ADDRESS = {Honolulu, HI, USA},
}

Endnote

%0 Conference Proceedings
%A Insafutdinov, Eldar
%A Andriluka, Mykhaylo
%A Pishchulin, Leonid
%A Tang, Siyu
%A Levinkov, Evgeny
%A Andres, Bjoern
%A Schiele, Bernt
%+ Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
%T ArtTrack: Articulated Multi-Person Tracking in the Wild : 
%G eng
%U http://hdl.handle.net/11858/00-001M-0000-002C-1867-1
%R 10.1109/CVPR.2017.142
%D 2017
%B 30th IEEE Conference on Computer Vision and Pattern Recognition
%Z date of event: 2017-07-21 - 2017-07-26
%C Honolulu, HI, USA
%B 30th IEEE Conference on Computer Vision and Pattern Recognition
%P 1293 - 1301
%I IEEE
%@ 978-1-5386-0458-8

Conference paper

E. Levinkov, J. Uhrig, S. Tang, M. Omran, E. Insafutdinov, A. Kirillov, C. Rother, T. Brox, B. Schiele, and B. Andres

“Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications,” in 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, HI, USA, 2017.

@inproceedings{levinkov-2017-cvpr,
TITLE = {Joint Graph Decomposition and Node Labeling: {P}roblem, Algorithms, Applications},
AUTHOR = {Levinkov, Evgeny and Uhrig, Jonas and Tang, Siyu and Omran, Mohamed and Insafutdinov, Eldar and Kirillov, Alexander and Rother, Carsten and Brox, Thomas and Schiele, Bernt and Andres, Bjoern},
LANGUAGE = {eng},
ISBN = {978-1-5386-0458-8},
DOI = {10.1109/CVPR.2017.206},
PUBLISHER = {IEEE Computer Society},
YEAR = {2017},
DATE = {2017},
BOOKTITLE = {30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)},
PAGES = {1904--1912},
ADDRESS = {Honolulu, HI, USA},
}

Endnote

%0 Conference Proceedings
%A Levinkov, Evgeny
%A Uhrig, Jonas
%A Tang, Siyu
%A Omran, Mohamed
%A Insafutdinov, Eldar
%A Kirillov, Alexander
%A Rother, Carsten
%A Brox, Thomas
%A Schiele, Bernt
%A Andres, Bjoern
%+ Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
External Organizations
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
External Organizations
External Organizations
External Organizations
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
%T Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications : 
%G eng
%U http://hdl.handle.net/11858/00-001M-0000-002D-05DB-2
%R  10.1109/CVPR.2017.206
%D 2017
%B 30th IEEE Conference on Computer Vision and Pattern Recognition
%Z date of event: 2017-07-22 - 2017-07-25
%C Honolulu, HI, USA
%B 30th IEEE Conference on Computer Vision and Pattern Recognition
%P 1904 - 1912
%I IEEE Computer Society
%@ 978-1-5386-0458-8

2016

Conference paper

L. Pishchulin, E. Insafutdinov, S. Tang, B. Andres, M. Andriluka, P. Gehler, and B. Schiele

“DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation,” in 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), Las Vegas, NV, USA, 2016.

@inproceedings{941,
TITLE = {{DeepCut}: {Joint} Subset Partition and Labeling for Multi Person Pose Estimation},
AUTHOR = {Pishchulin, Leonid and Insafutdinov, Eldar and Tang, Siyu and Andres, Bjoern and Andriluka, Mykhaylo and Gehler, Peter and Schiele, Bernt},
LANGUAGE = {eng},
ISBN = {978-1-4673-8852-8},
DOI = {10.1109/CVPR.2016.533},
PUBLISHER = {IEEE Computer Society},
YEAR = {2016},
DATE = {2016},
BOOKTITLE = {29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016)},
PAGES = {4929--4937},
ADDRESS = {Las Vegas, NV, USA},
}

Endnote

%0 Conference Proceedings
%A Pishchulin, Leonid
%A Insafutdinov, Eldar
%A Tang, Siyu
%A Andres, Bjoern
%A Andriluka, Mykhaylo
%A Gehler, Peter
%A Schiele, Bernt
%+ Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
External Organizations
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
%T DeepCut: Joint Subset Partition and Labeling for Multi Person Pose
  Estimation : 
%G eng
%U http://hdl.handle.net/11858/00-001M-0000-0029-4B1E-3
%R 10.1109/CVPR.2016.533
%D 2016
%B 29th IEEE Conference on Computer Vision and Pattern Recognition 
%Z date of event: 2016-06-26 - 2016-07-01
%C Las Vegas, NV, USA
%B 29th IEEE Conference on Computer Vision and Pattern Recognition
%P 4929 - 4937
%I IEEE Computer Society
%@ 978-1-4673-8852-8

Article

D4D2

H. Rhodin, C. Richardt, D. Casas, E. Insafutdinov, M. Shafiei, H.-P. Seidel, B. Schiele, and C. Theobalt

“EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras,” ACM Transactions on Graphics (Proc. ACM SIGGRAPH Asia 2016), vol. 35, no. 6, 2016.

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

Endnote

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

Conference paper

E. Insafutdinov, L. Pishchulin, B. Andres, M. Andriluka, and B. Schiele

“DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model,” in Computer Vision -- ECCV 2016, Amsterdam, The Netherlands, 2016.

Abstract

The goal of this paper is to advance the state-of-the-art of articulated pose

estimation in scenes with multiple people. To that end we contribute on three

fronts. We propose (1) improved body part detectors that generate effective

bottom-up proposals for body parts; (2) novel image-conditioned pairwise terms

that allow to assemble the proposals into a variable number of consistent body

part configurations; and (3) an incremental optimization strategy that explores

the search space more efficiently thus leading both to better performance and

significant speed-up factors. We evaluate our approach on two single-person and

two multi-person pose estimation benchmarks. The proposed approach

significantly outperforms best known multi-person pose estimation results while

demonstrating competitive performance on the task of single person pose

estimation. Models and code available at pose.mpi-inf.mpg.de

BibTeX

@inproceedings{1012,
TITLE = {{DeeperCut}: {A} Deeper, Stronger, and Faster Multi-Person Pose Estimation Model},
AUTHOR = {Insafutdinov, Eldar and Pishchulin, Leonid and Andres, Bjoern and Andriluka, Mykhaylo and Schiele, Bernt},
LANGUAGE = {eng},
ISBN = {978-3-319-46465-7},
DOI = {10.1007/978-3-319-46466-4_3},
PUBLISHER = {Springer},
YEAR = {2016},
DATE = {2016},
ABSTRACT = {The goal of this paper is to advance the state-of-the-art of articulated pose estimation in scenes with multiple people. To that end we contribute on three fronts. We propose (1) improved body part detectors that generate effective bottom-up proposals for body parts; (2) novel image-conditioned pairwise terms that allow to assemble the proposals into a variable number of consistent body part configurations; and (3) an incremental optimization strategy that explores the search space more efficiently thus leading both to better performance and significant speed-up factors. We evaluate our approach on two single-person and two multi-person pose estimation benchmarks. The proposed approach significantly outperforms best known multi-person pose estimation results while demonstrating competitive performance on the task of single person pose estimation. Models and code available at http://pose.mpi-inf.mpg.de},
BOOKTITLE = {Computer Vision -- ECCV 2016},
DEBUG = {author: Matas, Jiri; author: Sebe, Nicu; author: Welling, Max},
EDITOR = {Leibe, Bastian},
PAGES = {34--50},
SERIES = {Lecture Notes in Computer Science},
VOLUME = {9910},
ADDRESS = {Amsterdam, The Netherlands},
}

Endnote

%0 Conference Proceedings
%A Insafutdinov, Eldar
%A Pishchulin, Leonid
%A Andres, Bjoern
%A Andriluka, Mykhaylo
%A Schiele, Bernt
%+ Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
External Organizations
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society
%T DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model : 
%G eng
%U http://hdl.handle.net/11858/00-001M-0000-002A-FCF9-C
%R 10.1007/978-3-319-46466-4_3
%D 2016
%B 14th European Conference on Computer Vision
%Z date of event: 2016-10-11 - 2016-10-14
%C Amsterdam, The Netherlands
%X   The goal of this paper is to advance the state-of-the-art of articulated pose
estimation in scenes with multiple people. To that end we contribute on three
fronts. We propose (1) improved body part detectors that generate effective
bottom-up proposals for body parts; (2) novel image-conditioned pairwise terms
that allow to assemble the proposals into a variable number of consistent body
part configurations; and (3) an incremental optimization strategy that explores
the search space more efficiently thus leading both to better performance and
significant speed-up factors. We evaluate our approach on two single-person and
two multi-person pose estimation benchmarks. The proposed approach
significantly outperforms best known multi-person pose estimation results while
demonstrating competitive performance on the task of single person pose
estimation. Models and code available at http://pose.mpi-inf.mpg.de

%K Computer Science, Computer Vision and Pattern Recognition, cs.CV
%B Computer Vision -- ECCV 2016
%E Leibe, Bastian; Matas, Jiri; Sebe, Nicu; Welling, Max
%P 34 - 50
%I Springer
%@ 978-3-319-46465-7
%B Lecture Notes in Computer Science
%N 9910

Paper

D4D2

H. Rhodin, C. Richardt, D. Casas, E. Insafutdinov, M. Shafiei, H.-P. Seidel, B. Schiele, and C. Theobalt

“EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras (Extended Abstract),” 2016. [Online]. Available: http://arxiv.org/abs/1701.00142.

Abstract

Marker-based and marker-less optical skeletal motion-capture methods use an

outside-in arrangement of cameras placed around a scene, with viewpoints

converging on the center. They often create discomfort by possibly needed

marker suits, and their recording volume is severely restricted and often

constrained to indoor scenes with controlled backgrounds. We therefore propose

a new method for real-time, marker-less and egocentric motion capture which

estimates the full-body skeleton pose from a lightweight stereo pair of fisheye

cameras that are attached to a helmet or virtual-reality headset. It combines

the strength of a new generative pose estimation framework for fisheye views

with a ConvNet-based body-part detector trained on a new automatically

annotated and augmented dataset. Our inside-in method captures full-body motion

in general indoor and outdoor scenes, and also crowded scenes.

BibTeX

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

Endnote

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

%K Computer Science, Computer Vision and Pattern Recognition, cs.CV