Speech Driven Talking Face Generation from a Single Image and an Emotion Condition.
Sefik Emre EskimezYou ZhangZhiyao DuanPublished in: CoRR (2020)
Keyphrases
- single image
- facial expressions
- partially occluded
- emotion recognition
- multiple images
- shape recovery
- emotional state
- image pairs
- text to speech synthesis
- d scene
- human faces
- facial images
- light source
- shape from shading
- audio visual
- face images
- facial features
- indoor scenes
- intrinsic images
- computer vision
- vanishing points
- super resolution
- spherical harmonics
- face recognition
- human computer interaction
- object recognition
- high quality
- scene geometry