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