Context and Geometry Aware Voxel Transformer for Semantic Scene Completion.
Zhu YuRunmin ZhangJiacheng YingJunchen YuXiaohai HuLun LuoSi-Yuan CaoHui-Liang ShenPublished in: CoRR (2024)
Keyphrases
- three dimensional
- semantic context
- visual context
- context dependent
- d scene
- natural language
- knowledge retrieval
- image sequences
- contextual information
- scene geometry
- real scenes
- high level
- geometric constraints
- semantic information
- visual scene
- multiple images
- geometric information
- surface geometry
- context aware
- semantic web
- video sequences
- object geometry