MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer.
Kuan-Chih HuangTsung-Han WuHung-Ting SuWinston H. HsuPublished in: CVPR (2022)
Keyphrases
- d objects
- pose estimation
- multi view
- viewpoint
- object recognition
- multiple views
- three dimensional
- shape descriptors
- range data
- image sequences
- depth map
- line drawings
- cad models
- depth cues
- depth images
- d mesh
- object detection
- detection method
- human body
- object features
- object classes
- stereo camera
- geometric models
- image contours
- optical flow
- stereo vision
- depth information
- three dimensional objects
- surface patches
- integral imaging
- pose normalization
- physically plausible