SSD-MonoDTR: Supervised Scale-constrained Deformable Transformer for Monocular 3D Object Detection.
Xuan HeFan YangJiacheng LinHaolong FuJin YuanKailun YangZhiyong LiPublished in: CoRR (2023)
Keyphrases
- d objects
- pose estimation
- object recognition
- viewpoint
- multi view
- multiple views
- three dimensional
- range data
- detection method
- object classes
- cad models
- shape descriptors
- line drawings
- object detection
- deformable models
- d mesh
- pose parameters
- human body
- surface patches
- geometric models
- optical flow
- object views
- integral imaging