DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models.
Zhiyao SunTian LvSheng YeMatthieu Gaetan LinJenny ShengYu-Hui WenMinjing YuYong-Jin LiuPublished in: CoRR (2023)
Keyphrases
- facial animation
- diffusion models
- head motion
- face model
- facial expressions
- head pose estimation
- diffusion model
- information diffusion
- human faces
- facial expression recognition
- head movements
- pose estimation
- eye tracking
- facial images
- social networks
- single camera
- active appearance models
- facial features
- temporal coherence
- pose variations
- feature points
- gaze estimation
- face images
- eye gaze
- lighting conditions
- influence maximization
- three dimensional
- image sequences
- d objects
- eye movements
- human computer interaction