StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN.
Fei YinYong ZhangXiaodong CunMingdeng CaoYanbo FanXuan WangQingyan BaiBaoyuan WuJue WangYujiu YangPublished in: CoRR (2022)
Keyphrases
- pre trained
- high resolution
- face images
- low resolution
- training data
- super resolution
- training examples
- image processing
- control signals
- viewpoint
- human faces
- facial features
- appearance variations
- facial expressions
- high quality
- neural network
- face recognition
- remote sensing
- human body
- illumination conditions
- facial images
- feature extraction
- labeled data
- principal component analysis
- state space