LipFormer: High-fidelity and Generalizable Talking Face Generation with A Pre-learned Facial Codebook.
Jiayu WangKang ZhaoShiwei ZhangYingya ZhangYujun ShenDeli ZhaoJingren ZhouPublished in: CVPR (2023)
Keyphrases
- high fidelity
- human faces
- facial images
- face images
- facial expressions
- facial features
- facial recognition
- vector quantization
- expression recognition
- real time
- facial expression recognition
- face analysis
- face recognition
- face model
- medical image compression
- feature vectors
- facial motion
- pose variations
- bag of words
- face detection
- high resolution
- high quality
- training set
- video conferencing
- visual words
- image representation
- ground truth
- age estimation
- video sequences
- keypoints
- image understanding
- multi modal
- decision makers
- principal component analysis
- facial pose