DiffDub: Person-Generic Visual Dubbing Using Inpainting Renderer with Diffusion Auto-Encoder.

Tao Liu Chenpeng Du Shuai Fan Feilong Chen Kai Yu

Published in: ICASSP (2024)

Keyphrases

visual features
image restoration
visual information
visual perception
low level
low complexity
high level
denoising
bit rate
anisotropic diffusion
diffusion process
domain specific
visual cues
diffusion processes