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