“CALM: Conditional Adversarial Latent Models  for Directable Virtual Characters” by Tessler, Guo, Mannor, Chechik and Peng




    CALM: Conditional Adversarial Latent Models  for Directable Virtual Characters

Session/Category Title: Character Animation




    In this work, we present Conditional Adversarial Latent Models  (CALM), an approach for generating diverse and directable behaviors for user-controlled interactive virtual characters. Using imitation learning, CALM  learns a representation of movement that captures the complexity and diversity of human motion, and enables direct control over character movements. The approach jointly learns a control policy and a motion encoder that reconstructs key characteristics of a given motion without merely replicating it. The results show that CALM  learns a semantic motion representation, enabling control over the generated motions and style-conditioning for higher-level task training. Once trained, the character can be controlled using intuitive interfaces, akin to those found in video games.


    1. Christopher M Bishop 1995. Neural networks for pattern recognition. Oxford university press.
    2. Piotr Bojanowski and Armand Joulin. 2017. Unsupervised learning by predicting noise. In International Conference on Machine Learning. PMLR, 517–526.
    3. Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597–1607.
    4. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2020. Generative adversarial networks. Commun. ACM 63, 11 (2020), 139–144.
    5. Jonathan Ho and Stefano Ermon. 2016. Generative adversarial imitation learning. Advances in neural information processing systems 29 (2016).
    6. Jordan Juravsky, Yunrong Guo, Sanja Fidler, and Xue Bin Peng. 2022. PADL: Language-Directed Physics-Based Character Control. In SIGGRAPH Asia 2022 Conference Papers (Daegu, Republic of Korea) (SA ’22). Association for Computing Machinery, New York, NY, USA, Article 19, 9 pages. https://doi.org/10.1145/3550469.3555391
    7. Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013).
    8. Hung Yu Ling, Fabio Zinno, George Cheng, and Michiel Van De Panne. 2020. Character controllers using motion vaes. ACM Transactions on Graphics (TOG) 39, 4 (2020), 40–1.
    9. Viktor Makoviychuk, Lukasz Wawrzyniak, Yunrong Guo, Michelle Lu, Kier Storey, Miles Macklin, David Hoeller, Nikita Rudin, Arthur Allshire, Ankur Handa, and Gavriel State. 2021. Isaac Gym: High Performance GPU Based Physics Simulation For Robot Learning. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). https://openreview.net/forum?id=fgFBtYgJQX_
    10. Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018).
    11. Soohwan Park, Hoseok Ryu, Seyoung Lee, Sunmin Lee, and Jehee Lee. 2019. Learning predict-and-simulate policies from unorganized human motion data. ACM Transactions on Graphics (TOG) 38, 6 (2019), 1–11.
    12. Omkar M Parkhi, Andrea Vedaldi, and Andrew Zisserman. 2015. Deep face recognition. (2015).
    13. 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 Transactions On Graphics (TOG) 37, 4 (2018), 1–14.
    14. 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 (July 2022).
    15. Xue Bin Peng, Ze Ma, Pieter Abbeel, Sergey Levine, and Angjoo Kanazawa. 2021. Amp: Adversarial motion priors for stylized physics-based character control. ACM Transactions on Graphics (TOG) 40, 4 (2021), 1–20.
    16. Reallusion. 2022. 3D Animation and 2D Cartoons Made Simple. (2022). http://www.reallusion.com
    17. Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. 2016. Improved techniques for training gans. Advances in neural information processing systems 29 (2016).
    18. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017).
    19. Richard S Sutton, Doina Precup, and Satinder Singh. 1999. Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial intelligence 112, 1-2 (1999), 181–211.
    20. Chen Tessler, Shahar Givony, Tom Zahavy, Daniel Mankowitz, and Shie Mannor. 2017. A deep hierarchical approach to lifelong learning in minecraft. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31.
    21. Faraz Torabi, Garrett Warnell, and Peter Stone. 2018. Generative Adversarial Imitation from Observation. CoRR abs/1807.06158 (2018). http://arxiv.org/abs/1807.06158
    22. Feng Wang, Xiang Xiang, Jian Cheng, and Alan Loddon Yuille. 2017. Normface: L2 hypersphere embedding for face verification. In Proceedings of the 25th ACM international conference on Multimedia. 1041–1049.
    23. Tongzhou Wang and Phillip Isola. 2020. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In International Conference on Machine Learning. PMLR, 9929–9939.
    24. Jungdam Won, Deepak Gopinath, and Jessica Hodgins. 2022. Physics-based character controllers using conditional VAEs. ACM Transactions on Graphics (TOG) 41, 4 (2022), 1–12.
    25. Jiacheng Xu and Greg Durrett. 2018. Spherical Latent Spaces for Stable Variational Autoencoders. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 4503–4513.

ACM Digital Library Publication:

Overview Page: