Speech Driven Talking Face Generation From a Single Image and an Emotion Condition.
Sefik Emre EskimezYou ZhangZhiyao DuanPublished in: IEEE Trans. Multim. (2022)
Keyphrases
- single image
- facial expressions
- partially occluded
- emotion recognition
- emotional state
- multiple images
- image pairs
- text to speech synthesis
- shape recovery
- d scene
- face images
- light source
- human faces
- shape from shading
- super resolution
- vanishing points
- spherical harmonics
- video sequences
- indoor scenes
- intrinsic images
- natural images
- facial images
- audio visual
- facial features
- higher order
- d morphable model
- manhattan world
- computer vision