DOCTR: Disentangled Object-Centric Transformer for Point Scene Understanding.
Xiaoxuan YuHao WangWeiming LiQiang WangSoonYong ChoYounghun SungPublished in: CoRR (2024)
Keyphrases
- scene understanding
- object detection
- object recognition
- vision system
- object hypotheses
- d scene
- robot navigation
- scene recognition
- motion cues
- d objects
- scene categorization
- video surveillance
- scene interpretation
- scene labeling
- object model
- geometric reasoning
- indoor scenes
- image parsing
- target object
- object tracking
- support vector machine
- viewpoint
- moving objects
- training data
- three dimensional
- image processing
- computer vision