Synthesizing Photorealistic Virtual Humans Through Cross-Modal Disentanglement.
Siddarth RavichandranOndrej TexlerDimitar DinevHyun Jae KangPublished in: CVPR (2023)
Keyphrases
- photorealistic
- cross modal
- virtual humans
- virtual reality
- computer graphics
- multi modal
- hand held
- virtual environment
- multimedia retrieval
- visual recognition
- virtual world
- image retrieval
- three dimensional
- multimedia databases
- image processing
- visual data
- complex scenes
- vision system
- highly accurate
- image acquisition
- motion capture
- video camera
- multi party
- point cloud
- d scene
- viewpoint
- visual similarity