Learning character-agnostic motion for motion retargeting in 2D

Abstract

Analyzing human motion is a challenging task with a wide variety of applications in computer vision and in graphics. One such application, of particular importance in computer animation, is the retargeting of motion from one performer to another. While humans move in three dimensions, the vast majority of human motions are captured using video, requiring 2D-to-3D pose and camera recovery, before existing retargeting approaches may be applied. In this paper, we present a new method for retargeting video-captured motion between different human performers, without the need to explicitly reconstruct 3D poses and/or camera parameters.

In order to achieve our goal, we learn to extract, directly from a video, a high-level latent motion representation, which is invariant to the skeleton geometry and the camera view. Our key idea is to train a deep neural network to decompose temporal sequences of 2D poses into three components: motion, skeleton, and camera view-angle. Having extracted such a representation, we are able to re-combine motion with novel skeletons and camera views, and decode a retargeted temporal sequence, which we compare to a ground truth from a synthetic dataset.

We demonstrate that our framework can be used to robustly extract human motion from videos, bypassing 3D reconstruction, and outperforming existing retargeting methods, when applied to videos in-the-wild. It also enables additional applications, such as performance cloning, video-driven cartoons, and motion retrieval.

References

1. Kfir Aberman, Mingyi Shi, Jing Liao, Dani Lischinski, Baoquan Chen, and Daniel Cohen-Or. 2018. Deep Video-Based Performance Cloning. arXiv preprint arXiv:1808.06847 (2018).
2. Adobe Systems Inc. 2018. Mixamo. https://www.mixamo.com. https://www.mixamo.com Accessed: 2018-12-27.
3. Andreas Aristidou, Daniel Cohen-Or, Jessica K. Hodgins, Yiorgos Chrysanthou, and Ariel Shamir. 2018. Deep Motifs and Motion Signatures. ACM Trans. Graph. 37, 6, Article 187 (Nov. 2018), 13 pages.
4. Jürgen Bernard, Eduard Dobermann, Anna Vögele, Björn Krüger, Jörn Kohlhammer, and Dieter Fellner. 2017. Visual-interactive semi-supervised labeling of human motion capture data. Electronic Imaging 2017, 1 (2017), 34--45.
5. Jürgen Bernard, Nils Wilhelm, Björn Krüger, Thorsten May, Tobias Schreck, and Jörn Kohlhammer. 2013. Motionexplorer: Exploratory search in human motion capture data based on hierarchical aggregation. IEEE TVCG 19, 12 (2013), 2257--2266.
6. Zhe Cao, Tomas Simon, Shih-En Wei, and Yaser Sheikh. 2016. Realtime multi-person 2d pose estimation using part affinity fields. arXiv preprint arXiv:1611.08050 (2016).
7. Caroline Chan, Shiry Ginosar, Tinghui Zhou, and Alexei A Efros. 2018. Everybody dance now. arXiv preprint arXiv.1808.07371 (2018).
8. Songle Chen, Zhengxing Sun, and Yan Zhang. 2015. Scalable Organization of Collections of Motion Capture Data via Quantitative and Qualitative Analysis. In Proc. 5th ACM International Conference on Multimedia Retrieval. ACM, 411--418.
9. Kwang-Jin Choi and Hyeong-Seok Ko. 2000. Online motion retargetting. The Journal of Visualization and Computer Animation 11, 5 (2000), 223--235.
10. Michael Gleicher. 1998. Retargetting motion to new characters. In Proc. 25th annual conference on computer graphics and interactive techniques. ACM, 33--42.
11. Daniel Holden, Jun Saito, and Taku Komura. 2016. A deep learning framework for character motion synthesis and editing. ACM Transactions on Graphics (TOG) 35, 4 (2016), 138.
12. Daniel Holden, Jun Saito, Taku Komura, and Thomas Joyce. 2015. Learning motion manifolds with convolutional autoencoders. In SIGGRAPH Asia 2015 Technical Briefs. ACM, 18.
13. Eugene Hsu, Kari Pulli, and Jovan Popović. 2005. Style translation for human motion. In ACM Transactions on Graphics (TOG), Vol. 24. ACM, 1082--1089.
14. Yueqi Hu, Shuangyuan Wu, Shihong Xia, Jinghua Fu, and Wei Chen. 2010. Motion track: Visualizing variations of human motion data.. In PacificVis. 153--160.
15. Angjoo Kanazawa, Michael J Black, David W Jacobs, and Jitendra Malik. 2018. End-to-end recovery of human shape and pose. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
16. Leonard Kaufman and Peter J Rousseeuw. 2009. Finding groups in data: an introduction to cluster analysis. Vol. 344. John Wiley & Sons.
17. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv.1412.6980 (2014).
18. Lucas Kovar and Michael Gleicher. 2004. Automated extraction and parameterization of motions in large data sets. In ACM Transactions on Graphics (ToG), Vol. 23. ACM, 559--568.
19. Tejas D Kulkarni, William F Whitney, Pushmeet Kohli, and Josh Tenenbaum. 2015. Deep convolutional inverse graphics network. In Advances in neural information processing systems. 2539--2547.
20. Jehee Lee and Sung Yong Shin. 1999. A hierarchical approach to interactive motion editing for human-like figures. In Proc. 26th annual conference on computer graphics and interactive techniques. ACM Press/Addison-Wesley Publishing Co., 39--48.
21. Lingjie Liu, Weipeng Xu, Michael Zollhoefer, Hyeongwoo Kim, Florian Bernard, Marc Habermann, Wenping Wang, and Christian Theobalt. 2018. Neural Animation and Reenactment of Human Actor Videos. arXiv preprint arXiv:1809.03658 (2018).
22. Liqian Ma, Qianru Sun, Stamatios Georgoulis, Luc Van Gool, Bernt Schiele, and Mario Fritz. 2018. Disentangled person image generation. In Proc. IEEE CVPR. 99--108.
23. Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, Nov (2008), 2579--2605.
24. Dushyant Mehta, Srinath Sridhar, Oleksandr Sotnychenko, Helge Rhodin, Mohammad Shafiei, Hans-Peter Seidel, Weipeng Xu, Dan Casas, and Christian Theobalt. 2017. Vnect: Real-time 3d human pose estimation with a single rgb camera. ACM Transactions on Graphics (TOG) 36, 4 (2017), 44.
25. Jianyuan Min, Huajun Liu, and Jinxiang Chai. 2010. Synthesis and editing of personalized stylistic human motion. In Proc. 2010 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games. ACM, 39--46.
26. Lee Montgomery. 2012. Tradigital Maya: A CG Animator's Guide to Applying the Classical Principles of Animation. Focal Press.
27. Meinard Müller, Andreas Baak, and Hans-Peter Seidel. 2009. Efficient and robust annotation of motion capture data. In Proc. 2009 ACM SIGGRAPH/Eurographics Symposium on Computer Animation. ACM, 17--26.
28. Augustus Odena, Vincent Dumoulin, and Chris Olah. 2016. Deconvolution and Checker-board Artifacts. Distill (2016).
29. Xi Peng, Xiang Yu, Kihyuk Sohn, Dimitris N Metaxas, and Manmohan Chandraker. 2017. Reconstruction-based disentanglement for pose-invariant face recognition. intervals 20 (2017), 12.
30. Xue Bin Peng, Angjoo Kanazawa, Jitendra Malik, Pieter Abbeel, and Sergey Levine. 2018. SFV: reinforcement learning of physical skills from videos. ACM Trans. Graph. 37, 6 (November 2018), Article 178.
31. Sashank J Reddi, Satyen Kale, and Sanjiv Kumar. 2018. On the convergence of adam and beyond. (2018).
32. Charles F Rose III, Peter-Pike J Sloan, and Michael F Cohen. 2001. Artist-directed inverse-kinematics using radial basis function interpolation. In Computer Graphics Forum, Vol. 20. Wiley Online Library, 239--250.
33. Tomas Simon, Hanbyul Joo, Iain Matthews, and Yaser Sheikh. 2017. Hand Keypoint Detection in Single Images using Multiview Bootstrapping. In CVPR.
34. Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012).
35. Seyoon Tak and Hyeong-Seok Ko. 2005. A physically-based motion retargeting filter. ACM Transactions on Graphics (TOG) 24, 1 (2005), 98--117.
36. Sergey Tulyakov, Ming-Yu Liu, Xiaodong Yang, and Jan Kautz. 2017. Mocogan: Decomposing motion and content for video generation. arXiv preprint arXiv:1707.04993 (2017).
37. Ruben Villegas, Jimei Yang, Duygu Ceylan, and Honglak Lee. 2018. Neural Kinematic Networks for Unsupervised Motion Retargetting. In Proc. IEEE CVPR. 8639--8648.
38. Shuangyuan Wu, Zhaoqi Wang, and Shihong Xia. 2009. Indexing and retrieval of human motion data by a hierarchical tree. In Proc. 16th ACM Symposium on Virtual Reality Software and Technology. ACM, 207--214.
39. Shihong Xia, Congyi Wang, Jinxiang Chai, and Jessica Hodgins. 2015. Realtime style transfer for unlabeled heterogeneous human motion. ACM Transactions on Graphics (TOG) 34, 4 (2015), 119.
40. Weiyu Zhang, Menglong Zhu, and Konstantinos G Derpanis. 2013. From actemes to action: A strongly-supervised representation for detailed action understanding. In Proceedings of the IEEE International Conference on Computer Vision. 2248--2255.

Index Terms

• Computing methodologies

  • Computer graphics

    • Animation

      • Motion processing

  • Machine learning

    • Machine learning approaches

      • Neural networks