MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection.
Renrui ZhangHan QiuTai WangZiyu GuoZiteng CuiYu QiaoHongsheng LiPeng GaoPublished in: ICCV (2023)
Keyphrases
- d objects
- pose estimation
- multi view
- viewpoint
- object recognition
- multiple views
- three dimensional
- depth cues
- depth images
- shape descriptors
- cad models
- depth map
- physically plausible
- object detection
- range data
- line drawings
- detection method
- d mesh
- geometric models
- object features
- surface reconstruction
- depth information
- human body
- surface patches
- machine learning
- point distribution
- pose normalization
- integral imaging
- image sequences
- optical flow
- topological information
- object representation
- stereo camera