Sign in
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation.
Wenxuan Zhang
Xiaodong Cun
Xuan Wang
Yong Zhang
Xi Shen
Yu Guo
Ying Shan
Fei Wang
Published in:
CoRR (2022)
Keyphrases
</>
single image
multiple images
partially occluded
image pairs
three dimensional
light source
shape recovery
multiscale
d scene
computer vision
feature extraction
object recognition
optical flow
shape from shading