ST3D++: Denoised Self-Training for Unsupervised Domain Adaptation on 3D Object Detection.
Jihan YangShaoshuai ShiZhe WangHongsheng LiXiaojuan QiPublished in: IEEE Trans. Pattern Anal. Mach. Intell. (2023)
Keyphrases
- d objects
- viewpoint
- multi view
- object recognition
- pose estimation
- range data
- three dimensional
- denoising
- shape descriptors
- cad models
- multiple views
- d mesh
- real world objects
- object classes
- physically plausible
- object features
- line drawings
- detection method
- object model
- control points
- three dimensional objects
- object detection
- object views
- pose normalization
- single view
- computer graphics
- image contours
- topological information
- training set
- geometric invariants
- machine learning