“Synthesizing Physical Character-Scene Interactions” by Hassan, Guo, Wang, Black, Fidler, et al. …

  • ©Mohamed Hassan, Yunrong Guo, Tingwu Wang, Michael J. Black, Sanja Fidler, and Xuebin (Jason) Peng




    Synthesizing Physical Character-Scene Interactions

Session/Category Title: Character Animation: Interaction




    Movement is how people interact with and affect their environment. For realistic character animation, it is necessary to synthesize such interactions between virtual characters and their surroundings. Despite recent progress in character animation using machine learning, most systems focus on controlling an agent’s movements in fairly simple and homogeneous environments, with limited interactions with other objects. Furthermore, many previous approaches that synthesize human-scene interactions require significant manual labeling of the training data. In contrast, we present a system that uses adversarial imitation learning and reinforcement learning to train physically-simulated characters that perform scene interaction tasks in a natural and life-like manner. Our method learns scene interaction behaviors from large unstructured motion datasets, without manual annotation of the motion data. These scene interactions are learned using an adversarial discriminator that evaluates the realism of a motion within the context of a scene. The key novelty involves conditioning both the discriminator and the policy networks on scene context. We demonstrate the effectiveness of our approach through three challenging scene interaction tasks: carrying, sitting, and lying down, which require coordination of a character’s movements in relation to objects in the environment. Our policies learn to seamlessly transition between different behaviors like idling, walking, and sitting. By randomizing the properties of the objects and their placements during training, our method is able to generalize beyond the objects and scenarios depicted in the training dataset, producing natural character-scene interactions for a wide variety of object shapes and placements. The approach takes physics-based character motion generation a step closer to broad applicability. Please see our supplementary video for more results.


    1. Samy Bengio, Oriol Vinyals, Navdeep Jaitly, and Noam Shazeer. 2015. Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems – Volume 1 (Montreal, Canada) (NIPS’15). MIT Press, Cambridge, MA, USA, 1171–1179.
    2. Kevin Bergamin, Simon Clavet, Daniel Holden, and James Richard Forbes. 2019. DReCon: Data-Driven Responsive Control of Physics-Based Characters. ACM Trans. Graph. 38, 6, Article 206 (Nov. 2019), 11 pages. https://doi.org/10.1145/3355089.3356536
    3. Angel X. Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, Jianxiong Xiao, Li Yi, and Fisher Yu. 2015. ShapeNet: An Information-Rich 3D Model Repository. Technical Report arXiv:1512.03012 [cs.GR]. Stanford University — Princeton University — Toyota Technological Institute at Chicago.
    4. Yu-Wei Chao, Jimei Yang, Weifeng Chen, and Jia Deng. 2019. Learning to sit: Synthesizing human-chair interactions via hierarchical control. Proceedings of the AAAI Conference on Artificial Intelligence (2019).
    5. Nuttapong Chentanez, Matthias Müller, Miles Macklin, Viktor Makoviychuk, and Stefan Jeschke. 2018. Physics-Based Motion Capture Imitation with Deep Reinforcement Learning. In Proceedings of the 11th Annual International Conference on Motion, Interaction, and Games (Limassol, Cyprus) (MIG ’18). Association for Computing Machinery, New York, NY, USA, Article 1, 10 pages. https://doi.org/10.1145/3274247.3274506
    6. Stelian Coros, Philippe Beaudoin, and Michiel van de Panne. 2010. Generalized Biped Walking Control. ACM Trans. Graph. 29, 4, Article 130 (jul 2010), 9 pages. https://doi.org/10.1145/1778765.1781156
    7. P Kingma Diederik and Max Welling. 2014. Auto-encoding variational bayes. In International Conference on Learning Representations ICLR.
    8. David Eigen, Marc’Aurelio Ranzato, and Ilya Sutskever. 2014. Learning factored representations in a deep mixture of experts. In International Conference on Learning Representations ICLR.
    9. Katerina Fragkiadaki, Sergey Levine, Panna Felsen, and Jitendra Malik. 2015. Recurrent Network Models for Human Dynamics. In Proceedings of the IEEE International Conference on Computer Vision (ICCV)(ICCV ’15). IEEE Computer Society, USA, 4346–4354.
    10. Michael Gleicher. 1997. Motion Editing with Spacetime Constraints. In Proceedings of the 1997 Symposium on Interactive 3D Graphics (Providence, Rhode Island, USA) (I3D ’97). Association for Computing Machinery, New York, NY, USA, 139–ff.https://doi.org/10.1145/253284.253321
    11. F. Sebastin Grassia. 1998. Practical Parameterization of Rotations Using the Exponential Map. J. Graph. Tools 3, 3 (March 1998), 29–48. https://doi.org/10.1080/10867651.1998.10487493
    12. I. Habibie, Daniel Holden, Jonathan Schwarz, Joe Yearsley, and T. Komura. 2017. A Recurrent Variational Autoencoder for Human Motion Synthesis. In BMVC.
    13. Mohamed Hassan, Duygu Ceylan, Ruben Villegas, Jun Saito, Jimei Yang, Yi Zhou, and Michael Black. 2021. Stochastic Scene-Aware Motion Prediction. In Proceedings of the International Conference on Computer Vision 2021.
    14. Nicolas Heess, Dhruva TB, Srinivasan Sriram, Jay Lemmon, Josh Merel, Greg Wayne, Yuval Tassa, Tom Erez, Ziyu Wang, SM Eslami, 2017. Emergence of locomotion behaviours in rich environments. arXiv preprint arXiv:1707.02286 (2017).
    15. Jonathan Ho and Stefano Ermon. 2016. Generative Adversarial Imitation Learning. In Advances in Neural Information Processing Systems, D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R. Garnett (Eds.). Vol. 29. Curran Associates, Inc.https://proceedings.neurips.cc/paper/2016/file/cc7e2b878868cbae992d1fb743995d8f-Paper.pdf
    16. Daniel Holden, Taku Komura, and Jun Saito. 2017. Phase-Functioned Neural Networks for Character Control. ACM Trans. Graph. 36, 4, Article 42 (July 2017), 13 pages. https://doi.org/10.1145/3072959.3073663
    17. Daniel Holden, Jun Saito, and Taku Komura. 2016. A deep learning framework for character motion synthesis and editing. ACM Trans. Graph. 35, 4 (2016), 1–11.
    18. Shiyu Huang, Wenze Chen, Longfei Zhang, Ziyang Li, Fengming Zhu, Deheng Ye, Ting Chen, and Jun Zhu. 2021. TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations. arXiv preprint arXiv:2110.04507 (2021).
    19. R. A. Jacobs, M. I. Jordan, S. J. Nowlan, and G. E. Hinton. 1991. Adaptive Mixtures of Local Experts. Neural Computation 3, 1 (1991), 79–87. https://doi.org/10.1162/neco.1991.3.1.79
    20. Jehee Lee and Sung Yong Shin. 1999. A Hierarchical Approach to Interactive Motion Editing for Human-like Figures. In Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques(SIGGRAPH ’99). ACM Press/Addison-Wesley Publishing Co., USA, 39–48. https://doi.org/10.1145/311535.311539
    21. Libin Liu and Jessica Hodgins. 2018. Learning Basketball Dribbling Skills Using Trajectory Optimization and Deep Reinforcement Learning. ACM Trans. Graph. 37, 4, Article 142 (jul 2018), 14 pages. https://doi.org/10.1145/3197517.3201315
    22. Libin Liu, KangKang Yin, Michiel van de Panne, Tianjia Shao, and Weiwei Xu. 2010. Sampling-based Contact-rich Motion Control. ACM Transctions on Graphics 29, 4 (2010), Article 128.
    23. Siqi Liu, Guy Lever, Zhe Wang, Josh Merel, SM Eslami, Daniel Hennes, Wojciech M Czarnecki, Yuval Tassa, Shayegan Omidshafiei, Abbas Abdolmaleki, 2021. From motor control to team play in simulated humanoid football. arXiv preprint arXiv:2105.12196 (2021).
    24. Viktor Makoviychuk, Lukasz Wawrzyniak, Yunrong Guo, Michelle Lu, Kier Storey, Miles Macklin, David Hoeller, Nikita Rudin, Arthur Allshire, Ankur Handa, 2021. Isaac gym: High performance gpu-based physics simulation for robot learning. arXiv preprint arXiv:2108.10470 (2021).
    25. Julieta Martinez, Michael J Black, and Javier Romero. 2017. On human motion prediction using recurrent neural networks. In Proceedings IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR). 2891–2900.
    26. Josh Merel, Saran Tunyasuvunakool, Arun Ahuja, Yuval Tassa, Leonard Hasenclever, Vu Pham, Tom Erez, Greg Wayne, and Nicolas Heess. 2020. Catch & Carry: Reusable Neural Controllers for Vision-Guided Whole-Body Tasks. ACM Trans. Graph. 39, 4, Article 39 (July 2020), 14 pages. https://doi.org/10.1145/3386569.3392474
    27. Lars Mescheder, Andreas Geiger, and Sebastian Nowozin. 2018. Which Training Methods for GANs do actually Converge?. In Proceedings of the 35th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 80), Jennifer Dy and Andreas Krause (Eds.). PMLR, Stockholmsmässan, Stockholm Sweden, 3481–3490. http://proceedings.mlr.press/v80/mescheder18a.html
    28. Igor Mordatch, Emanuel Todorov, and Zoran Popović. 2012. Discovery of Complex Behaviors through Contact-Invariant Optimization. ACM Trans. Graph. 31, 4, Article 43 (jul 2012), 8 pages. https://doi.org/10.1145/2185520.2185539
    29. Xue Bin Peng, Pieter Abbeel, Sergey Levine, and Michiel van de Panne. 2018. DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills. ACM Trans. Graph. 37, 4, Article 143 (jul 2018), 14 pages. https://doi.org/10.1145/3197517.3201311
    30. Xue Bin Peng, Michael Chang, Grace Zhang, Pieter Abbeel, and Sergey Levine. 2019. MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies. Curran Associates Inc., Red Hook, NY, USA.
    31. Xue Bin Peng, Yunrong Guo, Lina Halper, Sergey Levine, and Sanja Fidler. 2022. ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters. ACM Trans. Graph. 41, 4, Article 94 (jul 2022), 17 pages. https://doi.org/10.1145/3528223.3530110
    32. Xue Bin Peng, Ze Ma, Pieter Abbeel, Sergey Levine, and Angjoo Kanazawa. 2021. AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control. ACM Trans. Graph. 40, 4, Article 144 (jul 2021), 20 pages. https://doi.org/10.1145/3450626.3459670
    33. Marc H. Raibert and Jessica K. Hodgins. 1991. Animation of Dynamic Legged Locomotion. In Proceedings of the 18th Annual Conference on Computer Graphics and Interactive Techniques(SIGGRAPH ’91). Association for Computing Machinery, New York, NY, USA, 349–358. https://doi.org/10.1145/122718.122755
    34. Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 (2017).
    35. Kihyuk Sohn, Honglak Lee, and Xinchen Yan. 2015. Learning Structured Output Representation using Deep Conditional Generative Models. In Advances in Neural Information Processing Systems 28. Curran Associates, Inc., 3483–3491. http://papers.nips.cc/paper/5775-learning-structured-output-representation-using-deep-conditional-generative-models.pdf
    36. Sebastian Starke, Ian Mason, and Taku Komura. 2022. DeepPhase: Periodic Autoencoders for Learning Motion Phase Manifolds. ACM Transactions on Graphics (TOG) 41, 4 (2022).
    37. Sebastian Starke, He Zhang, Taku Komura, and Jun Saito. 2019. Neural State Machine for Character-Scene Interactions. ACM Trans. Graph. 38, 6, Article 209 (Nov. 2019), 14 pages. https://doi.org/10.1145/3355089.3356505
    38. Sebastian Starke, Yiwei Zhao, Taku Komura, and Kazi Zaman. 2020. Local Motion Phases for Learning Multi-Contact Character Movements. ACM Trans. Graph. 39, 4, Article 54 (July 2020), 14 pages. https://doi.org/10.1145/3386569.3392450
    39. Shinjiro Sueda, Andrew Kaufman, and Dinesh K. Pai. 2008. Musculotendon Simulation for Hand Animation. In ACM SIGGRAPH 2008 Papers (Los Angeles, California) (SIGGRAPH ’08). Association for Computing Machinery, New York, NY, USA, Article 83, 8 pages. https://doi.org/10.1145/1399504.1360682
    40. Graham W. Taylor and Geoffrey E. Hinton. 2009. Factored Conditional Restricted Boltzmann Machines for Modeling Motion Style. In Proceedings of the 26th Annual International Conference on Machine Learning (Montreal, Quebec, Canada) (ICML ’09). Association for Computing Machinery, New York, NY, USA, 1025–1032. https://doi.org/10.1145/1553374.1553505
    41. Jingbo Wang, Yu Rong, Jingyuan Liu, Sijie Yan, Dahua Lin, and Bo Dai. 2022. Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 20460–20469.
    42. Jiashun Wang, Huazhe Xu, Jingwei Xu, Sifei Liu, and Xiaolong Wang. 2021. Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9401–9411.
    43. Jack M. Wang, David J. Fleet, and Aaron Hertzmann. 2009. Optimizing Walking Controllers. ACM Trans. Graph. 28, 5 (dec 2009), 1–8. https://doi.org/10.1145/1618452.1618514
    44. Tingwu Wang, Yunrong Guo, Maria Shugrina, and Sanja Fidler. 2020. UniCon: Universal Neural Controller For Physics-based Character Motion. arxiv:2011.15119 [cs.GR]
    45. Nkenge Wheatland, Yingying Wang, Huaguang Song, Michael Neff, Victor Zordan, and Sophie Jörg. 2015. State of the art in hand and finger modeling and animation. In Computer Graphics Forum, Vol. 34. Wiley Online Library, 735–760.
    46. Jungdam Won, Deepak Gopinath, and Jessica Hodgins. 2020. A Scalable Approach to Control Diverse Behaviors for Physically Simulated Characters. ACM Trans. Graph. 39, 4, Article 33 (jul 2020), 12 pages. https://doi.org/10.1145/3386569.3392381
    47. Jungdam Won, Deepak Gopinath, and Jessica Hodgins. 2022. Physics-Based Character Controllers Using Conditional VAEs. ACM Trans. Graph. 41, 4, Article 96 (jul 2022), 12 pages. https://doi.org/10.1145/3528223.3530067
    48. Pei Xu and Ioannis Karamouzas. 2021. A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character Control. Proceedings of the ACM on Computer Graphics and Interactive Techniques 4, 3 (2021), 1–22.
    49. Yuting Ye and C. Karen Liu. 2012. Synthesis of Detailed Hand Manipulations Using Contact Sampling. ACM Trans. Graph. 31, 4, Article 41 (jul 2012), 10 pages. https://doi.org/10.1145/2185520.2185537
    50. He Zhang, Yuting Ye, Takaaki Shiratori, and Taku Komura. 2021. ManipNet: Neural Manipulation Synthesis with a Hand-Object Spatial Representation. ACM Trans. Graph. 40, 4, Article 121 (jul 2021), 14 pages. https://doi.org/10.1145/3450626.3459830
    51. Xiaohan Zhang, Bharat Lal Bhatnagar, Sebastian Starke, Vladimir Guzov, and Gerard Pons-Moll. 2022. COUCH: Towards Controllable Human-Chair Interactions. In Computer Vision – ECCV 2022, Shai Avidan, Gabriel Brostow, Moustapha Cissé, Giovanni Maria Farinella, and Tal Hassner (Eds.). Springer Nature Switzerland, Cham, 518–535.
    52. Yan Zhang and Siyu Tang. 2022. The Wanderings of Odysseus in 3D Scenes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 20481–20491.

Additional Images:

©Mohamed Hassan, Yunrong Guo, Tingwu Wang, Michael J. Black, Sanja Fidler, and Xuebin (Jason) Peng

ACM Digital Library Publication:

Overview Page: