DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions.
Geumbyeol HwangSunwon HongSeunghyun LeeSungwoo ParkGyeongsu ChaePublished in: ICASSP (2023)
Keyphrases
- facial expressions
- head motion
- head movements
- facial actions
- head pose estimation
- person independent
- face pose
- video sequences
- facial expression recognition
- real time
- facial features
- facial animation
- multimedia
- eye tracking
- emotion recognition
- human faces
- single camera
- face images
- eye gaze
- frontal face
- gaze direction
- expression recognition
- face recognition
- gaze estimation
- facial feature points
- recognize faces
- pose variations
- recognition of facial expressions
- pose estimation
- face model
- visual data
- spatial and temporal
- facial appearance
- motion patterns
- video data
- illumination variations
- tracking accuracy
- manifold learning
- lighting conditions
- human computer interaction
- low level
- image sequences