Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance.
Qingcheng ZhaoPengyu LongQixuan ZhangDafei QinHan LiangLongwen ZhangYingliang ZhangJingyi YuLan XuPublished in: CoRR (2024)
Keyphrases
- facial animation
- multi modality
- facial expressions
- multi modal
- human faces
- medical images
- face model
- information theoretic
- facial images
- facial motion
- mutual information
- facial expression recognition
- image registration
- head motion
- temporal coherence
- multimedia
- facial features
- face recognition
- face images
- deformation field
- imaging modalities
- active appearance models
- photorealistic
- video sequences
- face tracking
- feature extraction
- image analysis
- principal component analysis
- keypoints