TL;DR基于扩散的语音驱动 3D 面部动画综合 DF-3DFace 方法,成功从语音中生成高度可变的面部形状和动作,同时实现比现有技术更逼真的面部动画。
Abstract
speech-driven 3d facial animation has gained significant attention for its
ability to create realistic and expressive facial animations in 3D space based
on speech. learning-based methods have shown promising pro