P2V-RCNN: Point to Voxel Feature Learning for 3D Object Detection From Point Clouds

P2V-RCNN: Point to Voxel Feature Learning for 3D Object Detection From Point Clouds

The most recent 3D object detectors for point clouds rely on the coarse voxel-based representation rather than the accurate point-based representation due to a higher box recall in the voxel-based Region Proposal Network (RPN). However, the detection accuracy is severely restricted by the informatio...

Full description

Bibliographic Details
Main Authors: Jiale Li, Yu Sun, Shujie Luo, Ziqi Zhu, Hang Dai, Andrey S. Krylov, Yong Ding, Ling Shao
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
3D object detection
point clouds
attention mechanism
autonomous driving
Online Access:https://ieeexplore.ieee.org/document/9474438/

Internet

https://ieeexplore.ieee.org/document/9474438/

Similar Items