Learning Object-Centric Neural Scattering Functions for Free-viewpoint Relighting and Scene Composition.
Hong-Xing YuMichelle GuoAlireza FathiYen-Yu ChangEric Ryan ChanRuohan GaoThomas A. FunkhouserJiajun WuPublished in: CoRR (2023)
Keyphrases
- image correspondences
- learning objects
- virtual view
- free viewpoint
- multi view
- e learning
- learning object metadata
- point correspondences
- learning process
- learning object repositories
- depth map
- metadata
- image synthesis
- dynamic scenes
- scene geometry
- illumination conditions
- view synthesis
- lighting conditions
- cast shadows
- d scene
- computer graphics
- face recognition
- three dimensional