Deformable PV-RCNN: Improving 3D Object Detection with Learned Deformations.
Prarthana BhattacharyyaKrzysztof CzarneckiPublished in: CoRR (2020)
Keyphrases
- d objects
- three dimensional
- viewpoint
- object recognition
- pose estimation
- multi view
- multiple views
- shape descriptors
- detection method
- object detection
- range data
- physically plausible
- pose normalization
- three dimensional objects
- cad models
- integral imaging
- image registration
- control points
- line drawings
- object model
- surface patches
- object features
- image contours
- topological information
- video sequences