Audio-driven talking face generation with diverse yet realistic facial animations.
Rongliang WuYingchen YuFangneng ZhanJiahui ZhangXiaoqin ZhangShijian LuPublished in: Pattern Recognit. (2023)
Keyphrases
- human faces
- facial images
- facial animation
- facial expressions
- face images
- facial features
- emotion recognition
- facial recognition
- expression recognition
- facial expression recognition
- facial motion
- face analysis
- face recognition
- pose variations
- face model
- facial landmarks
- real world
- landmark detection
- facial pose
- multimedia
- face detection
- motion capture data
- lighting conditions
- facial feature points
- visual information
- multimodal fusion
- face databases
- audio visual
- video sequences
- object detection
- computer graphics
- face tracking
- active appearance models
- audio signals
- frontal view
- facial region
- audio signal
- face recognition systems