Latent Dynamics for Full Body Avatar Animation
Researchers have developed a new method for animating full-body avatars, particularly focusing on the realistic deformation of loose clothing. Their approach augments a pose-conditioned 3D Gaussian avatar with a transformer-based decoder and a dynamics residual latent. This latent component captures temporal variations beyond simple pose, evolving based on history, inertia, and contact forces to produce coherent and history-dependent motion rollouts with minimal computational overhead. AI
IMPACT Introduces a novel approach to avatar animation, improving realism for dynamic elements like clothing, which could enhance virtual environments and digital content creation.