1 Hit in 1.3 sec

RBGNet: Ray-based Grouping for 3D Object Detection [article]

Haiyang Wang, Shaoshuai Shi, Ze Yang, Rongyao Fang, Qi Qian, Hongsheng Li, Bernt Schiele, Liwei Wang
2022 arXiv   pre-print
In this paper, we propose the RBGNet framework, a voting-based 3D detector for accurate 3D object detection from point clouds.  ...  In order to learn better representations of object shape to enhance cluster features for predicting 3D boxes, we propose a ray-based feature grouping module, which aggregates the point-wise features on  ...  Ray-based Feature Grouping VoteNet [29] has shown tremendous success for 3D object detection.  ... 
arXiv:2204.02251v1 fatcat:5h4akemozjhblggyrm3r4uz3xi