DiffTalker: Co-driven Audio-Image Diffusion for Talking Faces Via Intermediate Landmarks
arXiv (Cornell University)（2023）
关键词
Facial Landmark Detection,Audio-Visual Speech Recognition,Feature Learning,Lipreading,Representation Learning
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要