Nov 2026
PersonaDiff: diffusion-based style control for speech-synchronized 3D facial animation
Qualitative results show that the proposed dynamic style representation enables the generation of diverse speaker-dependent facial motions under different speaking styles and is well suited for applications such as virtual avatars, digital content creation, and other digital human systems.
Wei Li, Yu-Pu Song, Ya-Zhi Liu
· Pattern Analysis and Applica... · 0 citations