MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer.
Yunsong ZhouHongzi ZhuQuan LiuShan ChangMinyi GuoPublished in: CVPR (2023)
Keyphrases
- d objects
- pose estimation
- multi view
- viewpoint
- object recognition
- range data
- three dimensional
- cad models
- multiple views
- shape descriptors
- image contours
- object classes
- human body
- physically plausible
- geometric models
- line drawings
- detection method
- d mesh
- topological information
- image sequences
- machine learning
- object detection
- target detection
- object features
- integral imaging
- shape matching
- optical flow
- three dimensional objects
- surface points
- video sequences
- object views
- face detection