VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relighting.
Feitong TanSean FanelloAbhimitra MekaSergio Orts-EscolanoDanhang TangRohit PandeyJonathan TaylorPing TanYinda ZhangPublished in: SIGGRAPH (Conference Paper Track) (2022)
Keyphrases
- generative model
- high dynamic range imaging
- image capture
- probabilistic model
- lighting conditions
- human faces
- illumination conditions
- face recognition
- em algorithm
- facial expressions
- human hair
- bayesian framework
- face images
- semi supervised
- prior knowledge
- structuring elements
- feature points
- principal component analysis
- expectation maximization
- video data
- low level
- high resolution
- high quality