no code implementations • 16 Oct 2023 • Heyuan Yao, Zhenhua Song, Yuyang Zhou, Tenglong Ao, Baoquan Chen, Libin Liu
In this work, we present MoConVQ, a novel unified framework for physics-based motion control leveraging scalable discrete representations.
no code implementations • 12 Oct 2022 • Heyuan Yao, Zhenhua Song, Baoquan Chen, Libin Liu
Our framework can learn a rich and flexible latent representation of skills and a skill-conditioned generative control policy from a diverse set of unorganized motion sequences, which enables the generation of realistic human behaviors by sampling in the latent space and allows high-level control policies to reuse the learned skills to accomplish a variety of downstream tasks.