VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relighting.
Feitong TanSean Ryan FanelloAbhimitra MekaSergio Orts-EscolanoDanhang TangRohit PandeyJonathan TaylorPing TanYinda ZhangPublished in: CoRR (2022)
Keyphrases
- generative model
- high dynamic range imaging
- image capture
- probabilistic model
- bayesian framework
- human hair
- illumination conditions
- human faces
- face recognition
- lighting conditions
- face images
- semi supervised
- em algorithm
- facial expressions
- prior knowledge
- machine learning
- expectation maximization
- feature points
- maximum likelihood
- digital camera
- dynamic range