Walk Like This: Stylized Locomotion for Physics- Based Characters through Example-Driven Diffusion

5 Views

  • Thanks! Share it with your friends!

    You disliked this video. Thanks for the feedback!

cgshort
Published

We present a real-time framework for expressive legged locomotion that enables independent control over velocity and style. Unlike existing data-driven controllers, which typically require explicit style labels for training, our method efficiently leverages large-scale unstructured motion data and generalizes to unseen styles. We disentangle style from functional locomotion through a tailored sampling strategy used to train a style encoder whose output conditions an autoregressive diffusion model. During inference, the user provides a style reference clip and a joystick velocity command. The diffusion model then generates a kinematic reference tracked by a reinforcement learning controller. To improve user controllability and stylization strength, we propose an attention biasing mechanism and a velocity command correction strategy. We demonstrate our method on a physics-based humanoid character in simulation and on a physical robot, showcasing robust real-time control and continuous style modulation.
Publication link: https://la.disneyresearch.com/publication/walk-like-this-stylized-locomotion-for-physics-based-characters-through-example-driven-diffusion

Category
CG VFX & Misc

Up Next