CoChat
Sign Up
Cited by 498Human Pose and Action RecognitionFace recognition and analysis3D Shape Modeling and Analysis

Neural Body Fitting: Unifying Deep Learning and Model Based Human Pose and Shape Estimation

Open access
Omran, Mohamed, Lassner, Christoph, Pons-Moll, Gerard, Gehler, Peter, Schiele, Bernt·2018·2018 International Conference on 3D Vision (3DV)
DOI 10.1109/3dv.2018.00062
Open this paper in CoChat — free accountOpen PDF

Abstract

Direct prediction of 3D body pose and shape remains a challenge even for highly parameterized deep learning models. Mapping from the 2D image space to the prediction space is difficult: perspective ambiguities make the loss function noisy and training data is scarce. In this paper, we propose a novel approach (Neural Body Fitting (NBF)). It integrates a statistical body model within a CNN, leveraging reliable bottom-up semantic body part segmentation and robust top-down body model constraints. NBF is fully differentiable and can be trained using 2D and 3D annotations. In detailed experiments, we analyze how the components of our model affect performance, especially the use ofpart segmentations as an explicit intermediate representation, and present a robust, efficiently trainable framework for 3D human pose estimation from 2D images with competitive results on standard benchmarks. Code will be made available at http://github.com/mohomran/ neural_body_fitting.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/3dv.2018.00062

Cites

50 of 50 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 29

  1. T. Alldieck, M. Magnor, W. Xu, C. Theobalt, and G. Pons-Moll. Video based reconstruction of 3d peo- ple models. In IEEE Conference on Computer Vision and Pattern Recognition, June 2018. 3
  2. F. Bogo, A. Kanazawa, C. Lassner, P. Gehler, J. Romero, and M. J. Black. Keep it SMPL: Automatic estimation of 3D human pose and shape from a single image. In European Conference on Computer Vision (ECCV), 2016. 1, 2, 7
  3. L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille. Deeplab: Semantic image seg- mentation with deep convolutional nets, atrous con- volution, and fully connected crfs. arXiv preprint arXiv:1606.00915, 2016. 6 · arXiv
  4. D. M. Gavrila and L. S. Davis. 3-d model-based track- ing of humans in action: a multi-view approach. In Proc. CVPR, pages 73-80. IEEE, 1996. 2
  5. R. A. Güler, N. Neverova, and I. Kokkinos. Dense- pose: Dense human pose estimation in the wild. arXiv preprint arXiv:1802.00434, 2018. 3 · arXiv
  6. E. Insafutdinov, L. Pishchulin, B. Andres, M. An- driluka, and B. Schiele. Deepercut: A deeper, stronger, and faster multi-person pose estimation model. In Eu- ropean Conference on Computer Vision (ECCV), 2016. 5
  7. H. Joo, T. Simon, and Y. Sheikh. Total capture: A 3d deformation model for tracking faces, hands, and bod- ies. arXiv preprint arXiv:1801.01615, 2018. 2 · arXiv
  8. A. Kanazawa, M. J. Black, D. W. Jacobs, and J. Malik. End-to-end recovery of human shape and pose. In Pro- ceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018. 1, 2, 3, 7, 8
  9. S. Li and A. B. Chan. 3d human pose estimation from monocular images with deep convolutional neu- ral network. In Asian Conference on Computer Vision (ACCV), pages 332-347, 2014. 3
  10. M. M. Loper, N. Mahmood, and M. J. Black. MoSh: Motion and shape capture from sparse markers. ACM Transactions on Graphics, (Proc. SIGGRAPH Asia), 33(6):220:1-220:13, Nov. 2014. 5
  11. D. Mehta, S. Sridhar, O. Sotnychenko, H. Rhodin, M. Shafiei, H.-P. Seidel, W. Xu, D. Casas, and C. Theobalt. Vnect: Real-time 3d human pose esti- mation with a single rgb camera. ACM Transactions on Graphics, 36(4), July 2017. 3
  12. D. Metaxas and D. Terzopoulos. Shape and non- rigid motion estimation through physics-based synthe- sis. IEEE Trans. PAMI, 15(6):580-591, 1993. 2
  13. G. Pavlakos, X. Zhou, and K. Daniilidis. Ordinal depth supervision for 3d human pose estimation. In Proceedings of the IEEE Conference on Computer Vi- sion and Pattern Recognition, 2018. 3
  14. G. Pavlakos, L. Zhu, X. Zhou, and K. Daniilidis. Learning to estimate 3D human pose and shape from a single color image. In Proceedings of the IEEE Con- ference on Computer Vision and Pattern Recognition, 2018. 1, 3, 4, 7
  15. G. Pons-Moll, J. Romero, N. Mahmood, and M. J. Black. Dyna: a model of dynamic human shape in mo- tion. ACM Transactions on Graphics (TOG), 34:120, 2015. 2
  16. G. Pons-Moll and B. Rosenhahn. Model-Based Pose Estimation, chapter 9, pages 139-170. Springer, 2011. 2
  17. V. Ramakrishna, T. Kanade, and Y. Sheikh. Recon- structing 3d human pose from 2d image landmarks. In European Conference on Computer Vision, pages 573- 586. Springer, 2012. 7
  18. G. Rogez and C. Schmid. Mocap-guided data aug- mentation for 3d pose estimation in the wild. In Advances in Neural Information Processing Systems, pages 3108-3116, 2016. 3
  19. G. Rogez, P. Weinzaepfel, and C. Schmid. Lcr-net++: Multi-person 2d and 3d pose detection in natural im- ages. arXiv preprint arXiv:1803.00455, 2018. 3 · arXiv
  20. K. Simonyan and A. Zisserman. Very deep con- volutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014. 6 · arXiv
  21. X. Sun, J. Shang, S. Liang, and Y. Wei. Com- positional human pose regression. arXiv preprint arXiv:1704.00159, 2017. 3 · arXiv
  22. J. K. V. Tan, I. Budvytis, and R. Cipolla. Indirect deep structured learning for 3d human body shape and pose prediction. In BMVC, volume 3, page 6, 2017. 1
  23. B. Tekin, I. Katircioglu, M. Salzmann, V. Lepetit, and P. Fua. Structured Prediction of 3D Human Pose with Deep Neural Networks. In British Machine Vision Con- ference (BMVC), 2016. 3
  24. H.-Y. Tung, H.-W. Tung, E. Yumer, and K. Fragki- adaki. Self-supervised learning of motion capture. In Advances in Neural Information Processing Systems, pages 5242-5252, 2017. 1, 3, 7
  25. G. Varol, D. Ceylan, B. Russell, J. Yang, E. Yumer, I. Laptev, and C. Schmid. Bodynet: Volumetric in- ference of 3d human body shapes. arXiv preprint arXiv:1804.04875, 2018. 3 · arXiv
  26. G. Varol, J. Romero, X. Martin, N. Mahmood, M. J. Black, I. Laptev, and C. Schmid. Learning from Syn- thetic Humans. In CVPR, 2017. 3
  27. X. Zhou, M. Zhu, S. Leonardos, K. Derpanis, and K. Daniilidis. Sparseness Meets Deepness: 3D Hu- man Pose Estimation from Monocular Video. In IEEE Conference on Computer Vision and Pattern Recogni- tion (CVPR), 2015. 3
  28. X. Zhou, M. Zhu, G. Pavlakos, S. Leonardos, K. G. Derpanis, and K. Daniilidis. Monocap: Monocular hu- man motion capture using a cnn coupled with a geo- metric prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018. 3
  29. G. Lin and I. R. Anton Milan, Chunhua Shen. Re- finenet: Multi-path refinement networks for high- resolution semantic segmentation. In Computer Vision and Pattern Recognition (CVPR), 2017.

Cited by

Sorted by citations

Related

Authors
Omran, M., Lassner, C., Pons-Moll, G., Gehler, P., & Schiele, B.
Affiliations
Max Planck Society (DE)
ORCID
Venue
2018 International Conference on 3D Vision (3DV)
Publisher
IEEE
Published
2018-09
Pages
484-494
DOI
10.1109/3dv.2018.00062
OpenAlex
W2885729320
Cited by
498
References
50
Citations by year
2026: 8 · 2025: 32 · 2024: 37 · 2023: 67 · 2022: 76 · 2021: 108 · 2020: 86 · 2019: 77 · 2018: 6 · 2017: 1
FWCI
20.55
Type
conference paper
Language
en
Open access
Locations
  • International Conference on 3D Vision (3DV) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Max Planck Digital Library (submittedVersion)
  • MPG.PuRe (Max Planck Society) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
  • Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
Keywords
3D human pose estimation, 3D human shape estimation, body part segmentation, 2D-to-3D mapping

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review