Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective.
Jiaxiang TangXiaokang ChenJingbo WangGang ZengPublished in: CoRR (2021)
Keyphrases
- three dimensional
- probability maps
- d scene
- scene analysis
- video sequences
- semantic context
- viewpoint
- input image
- multiple objects
- single image
- semantic information
- multiple images
- dynamic scenes
- high level
- camera pose
- semantic network
- semantic similarity
- moving objects
- natural language
- human brain
- semantic web
- color constancy
- vision system
- co occurrence
- scene categorization
- brain activation