Login / Signup
MergeTalk: Audio-Driven Talking Head Generation From Single Image With Feature Merge.
Jian Gao
Chang Shu
Ximin Zheng
Zheng Lu
Nengsheng Bao
Published in:
IEEE Signal Process. Lett. (2024)
Keyphrases
</>
single image
multiple images
d scene
shape recovery
image pairs
light source
spherical harmonics
shape from shading
partially occluded
image features
super resolution
multiresolution
intrinsic image decomposition
three dimensional
intrinsic images
vanishing points
object detection
feature extraction