MonoDETR: Depth-aware Transformer for Monocular 3D Object Detection.
Renrui ZhangHan QiuTai WangXuanzhuo XuZiyu GuoYu QiaoPeng GaoHongsheng LiPublished in: CoRR (2022)
Keyphrases
- d objects
- pose estimation
- depth cues
- viewpoint
- multi view
- shape descriptors
- multiple views
- object recognition
- range data
- cad models
- depth map
- depth images
- line drawings
- three dimensional
- detection method
- d mesh
- image contours
- object detection
- computer vision
- human body
- object classes
- image sequences
- object categories
- stereo camera
- pose parameters
- integral imaging
- pose normalization
- physically plausible