Up-to-Down Network: Fusing Multi-Scale Context for 3D Semantic Scene Completion.
Hao ZouXuemeng YangTianxin HuangChujuan ZhangYong LiuWanlong LiFeng WenHongbo ZhangPublished in: IROS (2021)
Keyphrases
- multiscale
- semantic context
- visual context
- d scene
- context dependent
- three dimensional
- video sequences
- knowledge retrieval
- network structure
- network model
- wavelet transform
- contextual information
- complex networks
- dynamic scenes
- communication networks
- computer networks
- image representation
- context aware
- moving objects
- neural network
- object recognition
- domain ontology
- single image
- multiple objects
- natural language
- complex scenes
- scene understanding
- visual scene
- low level
- wireless sensor networks