MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement.
Alexander RichardMichael ZollhöferYandong WenFernando De la TorreYaser SheikhPublished in: ICCV (2021)
Keyphrases
- facial animation
- facial expressions
- human faces
- speech recognition
- temporal coherence
- face model
- affect sensing
- speech synthesis
- language acquisition
- face recognition
- head motion
- stereo vision
- facial images
- speech signal
- active appearance models
- emotion recognition
- computer animation
- pose normalization
- motion capture
- spoken dialogue systems
- neural network
- computer graphics
- pattern recognition
- three dimensional