PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds. Our proposed method d...
Publications
2 shownPoint Transformer
Self-attention networks have revolutionized natural language processing and are making impressive strides in image analysis tasks such as image classification and object detecti...
Frequent Co-Authors
Researcher Info
- h-index
- 2
- Publications
- 2
- Citations
- 3,699
- Institution
- University of Hong Kong
External Links
Identifiers
- ORCID
- 0000-0001-7058-6957
Impact Metrics
h-index
2
h-index: Number of publications with at least h citations each.