MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer.
Yunsong ZhouHongzi ZhuQuan LiuShan ChangMinyi GuoPublished in: CoRR (2023)
Keyphrases
- d objects
- pose estimation
- viewpoint
- object recognition
- cad models
- multi view
- three dimensional
- shape descriptors
- multiple views
- range data
- image sequences
- object detection
- detection method
- recognition and pose estimation
- integral imaging
- object classes
- computer vision
- line drawings
- d mesh
- geometric models
- partial matching
- image contours
- pose normalization
- control points
- surface reconstruction
- human body