Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective.
Jiaxiang TangXiaokang ChenJingbo WangGang ZengPublished in: AAAI (2022)
Keyphrases
- three dimensional
- semantic context
- image sequences
- multiple images
- d scene
- domain specific
- semantic web
- single image
- viewpoint
- image correspondences
- scene understanding
- video sequences
- virtual camera
- scene analysis
- complex scenes
- connected components
- semantic information
- dynamic scenes
- semantic network
- real scenes
- semantic similarity
- line features
- input image
- natural language
- relative position
- scene classification
- scene images