RBGNet: Ray-Based Grouping for 3D Object Detection

Haiyang Wang, Shaoshuai Shi, Ze Yang, Rongyao Fang, Qi Qian, Hongsheng Li, Bernt Schiele, Liwei Wang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 1110-1119

Abstract


As a fundamental problem in computer vision, 3D object detection is experiencing rapid growth. To extract the point-wise features from the irregularly and sparsely distributed points, previous methods usually take a feature grouping module to aggregate the point features to an object candidate. However, these methods have not yet leveraged the surface geometry of foreground objects to enhance grouping and 3D box generation. 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 object surfaces using a group of determined rays uniformly emitted from cluster centers. Considering the fact that foreground points are more meaningful for box estimation, we design a novel foreground biased sampling strategy in downsample process to sample more points on object surfaces and further boost the detection performance. Our model achieves state-of-the-art 3D detection performance on ScanNet V2 and SUN RGB-D with remarkable performance gains.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Haiyang and Shi, Shaoshuai and Yang, Ze and Fang, Rongyao and Qian, Qi and Li, Hongsheng and Schiele, Bernt and Wang, Liwei}, title = {RBGNet: Ray-Based Grouping for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1110-1119} }