Synthesizing training images for boosting human 3D pose estimation

Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016

Volumn , Issue , 2016, Pages 479-488

  Chen, Wenzheng ^a   Wang, Huan ^a   Li, Yangyan ^b   Su, Hao ^c   Wang, Zhenhua ^d   Tu, Changhe ^a   Lischinski, Dani ^d   Cohen Or, Daniel ^b   Chen, Baoquan ^a  

^a SHANDONG UNIVERSITY   (China)

^b TEL AVIV UNIVERSITY   (Israel)

^c STANFORD UNIVERSITY   (United States)

^d HEBREW UNIVERSITY OF JERUSALEM   (Israel)

Author keywords

Deep learning; Domain adaptation; Human 3D pose; Synthesizing training data

Indexed keywords

DEEP LEARNING; NEURAL NETWORKS;

3D POSE ESTIMATION; CONVOLUTIONAL NEURAL NETWORK; DOMAIN ADAPTATION; END-TO-END SOLUTIONS; HUMAN 3D POSE; SYNTHESIS PROCEDURE; SYNTHETIC TRAINING DATA; TRAINING DATA;

IMAGE PROCESSING;

EID: 85011301417     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/3DV.2016.58     Document Type: Conference Paper

References (58)

1. DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation., June 2016. 4322
2. A. Agarwal, and B. Triggs. Recovering 3d human pose from monocular images. TPAMI, 28(1): 44-58, Jan 2006. 4323
3. H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, and M. Marchand. Domain-Adversarial Neural Networks. ArXiv e-prints, Dec. 2014. 4323
4. I. Akhter, and M. J. Black. Pose-conditioned joint angle limits for 3d human pose reconstruction. In CVPR, pages 1446-1455, 2015
5. M. Andriluka, L. Pishchulin, P. Gehler, and B. Schiele. 2d human pose estimation: New benchmark and state of the art analysis. In CVPR, June 2014. 4322
6. D. Anguelov, P. Srinivasan, D. Koller, S. Thrun, J. Rodgers, and J. Davis. SCAPE: Shape completion and animation of people. ACM ToG, 24(3): 408-416, July 2005. 4321, 4323, 4324
7. D. Baraff, and A. Witkin. Large steps in cloth simulation. In Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH '98, pages 43-54, New York, NY, USA, 1998
8. S. Ben-David, J. Blitzer, K. Crammer, A. Kulesza, F. Pereira, and J. W. Vaughan. A theory of learning from different domains. Mach. Learn., 79(1-2): 151-175, May 2010. 4322
9. X. Chen, and A. Yuille. Articulated pose estimation by a graphical model with image dependent pairwise relations. In NIPS, pages 1736-1744, 2014
10. CMU. Cmu graphics lab motion capture database. http://mocap.cs.cmu.edu/. 4323
11. X. Fan, K. Zheng, Y. Lin, and S. Wang. Combining local appearance and holistic view: Dual-source deep neural networks for human pose estimation. In CVPR15. 4322
12. X. Fan, K. Zheng, Y. Zhou, and S. Wang. Pose locality constrained representation for 3d human pose reconstruction. In ECCV, pages 174-188. Springer, 2014
13. V. Ferrari, M. Marin-Jimenez, and A. Zisserman. Progressive search space reduction for human pose estimation. In CVPR, pages 1-8, 2008
14. Y. Ganin, and V. Lempitsky. Unsupervised domain adaptation by backpropagation. In Proceedings of the 32nd International Conference on Machine Learning (ICML-15), pages 1180-1189, 2015
15. G. Gkioxari, B. Hariharan, R. Girshick, and J. Malik. Rcnns for pose estimation and action detection. arXiv preprint arXiv: 1406.5212, 2014
16. P. Guan, L. Reiss, D. A. Hirshberg, A. Weiss, and M. J. Black. DRAPE: Dressing any person. ACM ToG, 31(4): 35: 1-35: 10, 2012
17. P. Guan, A. Weiss, A. O. Bǎlan, and M. J. Black. Estimating human shape and pose from a single image. In ICCV, pages 1381-1388. IEEE, 2009
18. D. Hogg. Model-based vision: A program to see a walking person. Image and Vision computing, 1(1): 5-20, 1983
19. C. Ionescu, J. Carreira, and C. Sminchisescu. Iterated second-order label sensitive pooling for 3d human pose estimation. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, USA, June 23-28, 2014, pages 1661-1668, 2014
20. C. Ionescu, F. Li, and C. Sminchisescu. Latent structured models for human pose estimation. In ICCV, pages 2220-2227, 2011
21. C. Ionescu, D. Papava, V. Olaru, and C. Sminchisescu. Human3.6M: Large scale datasets and predictive methods for 3d human sensing in natural environments. TPAMI, 36(7): 1325-1339, July 2014
22. A. Jain, T. Thormählen, H.-P. Seidel, and C. Theobalt. MovieReshape: Tracking and reshaping of humans in videos. ACM ToG, 29(6): 148: 1-148: 10, 2010
23. S. Johnson, and M. Everingham. Clustered pose and nonlinear appearance models for human pose estimation. In BMVC, pages 12.1-12.11, 2010
24. S. Johnson, and M. Everingham. Learning effective human pose estimation from inaccurate annotation. In CVPR, pages 1465-1472, June 2011. 4322, 4324
25. H.-J. Lee, and Z. Chen. Determination of 3d human body postures from a single view. Computer Vision, Graphics, and Image Processing, 30(2): 148-168, 1985
26. A. M. Lehrmann, P. V. Gehler, and S. Nowozin. A nonparametric bayesian network prior of human pose. In ICCV, ICCV '13, pages 1281-1288, Washington, DC, USA, 2013
27. S. Li, and A. B. Chan. 3d human pose estimation from monocular images with deep convolutional neural network. In ACCV, pages 332-347. Springer, 2014
28. S. Li, Z.-Q. Liu, and A. Chan. Heterogeneous multi-Task learning for human pose estimation with deep convolutional neural network. In CVPR14 Workshops. 4322
29. S. Li, W. Zhang, and A. B. Chan. Maximum-margin structured learning with deep networks for 3d human pose estimation. In ICCV, pages 2848-2856, 2015
30. W. Li, L. Duan, D. Xu, and I. W. Tsang. Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell., 36(6): 1134-1148, 2014
31. M. Long, Y. Cao, J. Wang, and M. I. Jordan. Learning transferable features with deep adaptation networks. In Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015, pages 97-105, 2015
32. F. Massa, B. Russell, and M. Aubry. Deep exemplar 2d-3d detection by adapting from real to rendered views. arXiv preprint arXiv: 1512.02497, 2015
33. G. Mori, and J. Malik. Estimating human body configurations using shape context matching. In ECCV, ECCV '02, pages 666-680, 2002
34. G. Mori, and J. Malik. Recovering 3d human body configurations using shape contexts. TPAMI, 28(7): 1052-1062, 2006
35. M. E. Munich, and P. Perona. Continuous dynamic time warping for translation-invariant curve alignment with applications to signature verification. In ICCV, volume 1, pages 108-115. IEEE, 1999
36. Noitom. Noitom mocap system. http://www.noitom. com/. 4326, 4327
37. D. Park, and D. Ramanan. Articulated pose estimation with tiny synthetic videos. In CVPR Workshops, pages 58-66, June 2015. 4323
38. L. Pishchulin, A. Jain, M. Andriluka, T. Thormhlen, and B. Schiele. Articulated people detection and pose estimation: Reshaping the future. In CVPR12. 4323
39. I. Radwan, A. Dhall, and R. Goecke. Monocular image 3d human pose estimation under self-occlusion. In ICCV, pages 1888-1895, Dec 2013. 4323
40. V. Ramakrishna, T. Kanade, and Y. Sheikh. Reconstructing 3D human pose from 2D image landmarks. In ECCV, ECCV? 12, pages 573-586, 2012
41. B. Sapp, and B. Taskar. MODEC: Multimodal decomposable models for human pose estimation. In CVPR, pages 3674-3681, June 2013. 4322
42. S. Schaefer, T. McPhail, and J. Warren. Image deformation using moving least squares. ACM Trans. Graph., 25(3): 533-540, July 2006. 4324
43. L. Sigal, A. O. Balan, and M. J. Black. Humaneva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated humanmotion. IJCV, 87(1): 4-27, 2009
44. H. Su, C. R. Qi, Y. Li, and L. J. Guibas. Render for CNN: viewpoint estimation in images using CNNs trained with rendered 3d model views. December 2015. 4321
45. C. J. Taylor. Reconstruction of articulated objects from point correspondences in a single uncalibrated image. Comput. Vis. Image Underst., 2000
46. B. Tekin, A. Rozantsev, V. Lepetit, and P. Fua. Direct prediction of 3d body poses from motion compensated sequences. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016. 4323
47. J. J. Tompson, A. Jain, Y. LeCun, and C. Bregler. Joint training of a convolutional network and a graphical model for human pose estimation. In NIPS. 2014. 4322
48. A. Toshev, and C. Szegedy. DeepPose: Human pose estimation via deep neural networks. In CVPR, pages 1653-1660, 2014
49. E. Tzeng, J. Hoffman, T. Darrell, and K. Saenko. Simultaneous deep transfer across domains and tasks. In ICCV, pages 4068-4076, 2015
50. E. Tzeng, J. Hoffman, N. Zhang, K. Saenko, and T. Darrell. Deep domain confusion: Maximizing for domain invariance. CoRR, abs/1412.3474, 2014
51. D. Vazquez, A. M. Lopez, J. Marin, D. Ponsa, and D. Geronimo. Virtual and real world adaptation for pedestrian detection. TPAMI, 36(4): 797-809, April 2014. 4323
52. C. Wang, Y. Wang, Z. Lin, A. L. Yuille, and W. Gao. Robust estimation of 3d human poses from a single image. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, USA, June 23-28, 2014, pages 2369-2376, 2014
53. S.-E. Wei, V. Ramakrishna, T. Kanade, and Y. Sheikh. Convolutional pose machines. In CVPR, 2016
54. A. Weiss, D. Hirshberg, and M. J. Black. Home 3D body scans from noisy image and range data. In ICCV, pages 1951-1958, 2011
55. H. Yasin, U. Iqbal, B. Krger, A.Weber, and J. Gallh. A dualsource approach for 3d pose estimation from a single image. In CVPR, 2016
56. S. Zhou, H. Fu, L. Liu, D. Cohen-Or, and X. Han. Parametric reshaping of human bodies in images. ACM ToG, 29(4): 126: 1-126: 10, July 2010. 4321, 4323
57. X. Zhou, S. Leonardos, X. Hu, and K. Daniilidis. 3d shape estimation from 2d landmarks: A convex relaxation approach. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7-12, 2015, pages 4447-4455, 2015
58. X. Zhou, M. Zhu, S. Leonardosy, K. G. Derpanisz, and K. Daniilidisy. Sparseness meets deepness: 3d human pose estimation from monocular video. In CVPR, 2016