MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations
ACM Transactions on Graphics · 19.07.2024 · 43 (4) · 1-21
DOI: 10.1145/3658137 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 19.07.2024. Verfasst von Heyuan Yao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 103 Literaturangaben.
Abstract (Originalsprache)
In this work, we present MoConVQ, a novel unified framework for physics-based motion control leveraging scalable discrete representations. Building upon vector quantized variational autoencoders (VQ-VAE) and model-based reinforcement learning, our approach effectively learns motion embeddings from a large, unstructured dataset spanning tens of hours of motion examples. The resultant motion representation not only captures diverse motion skills but also offers a robust and intuitive interface for various applications. We demonstrate the versatility of MoConVQ through several applications: universal tracking control from various motion sources, interactive character control with latent motion representations using supervised learning, physics-based motion generation from natural language descriptions using the GPT framework, and, most interestingly, seamless integration with large language models (LLMs) with in-context learning to tackle complex and abstract tasks.
Zitieren
APA
Yao, H., Song, Z., Zhou, Y., Ao, T., Chen, B., & Liu, L. (2024). MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations. ACM Transactions on Graphics, 43(4), 1-21. https://doi.org/10.1145/3658137
Vancouver
Yao H, Song Z, Zhou Y, Ao T, Chen B, Liu L. MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations. ACM Transactions on Graphics. 2024;43(4):1-21. doi:10.1145/3658137
BibTeX
@article{Yao2024,
author = {Yao, Heyuan and Song, Zhenhua and Zhou, Yuyang and Ao, Tenglong and Chen, Baoquan and Liu, Libin},
title = {MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations},
journal = {ACM Transactions on Graphics},
year = {2024},
volume = {43},
number = {4},
pages = {1--21},
doi = {10.1145/3658137}
}
EUVIMED