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. Code will be available at https://github.com/Haiyang-W/RBGNet.

本文提出了 RBGNet 框架，一种基于投票的 3D 检测器，用于从点云中精确检测 3D 物体。该框架使用基于射线的特征分组模块来聚合物体表面的点特征，以了解物体的形状以增强聚类特征，从而预测 3D 边界框。此外，作者还提出了一种新颖的前景偏置采样策略，以在下采样过程中采样更多物体表面上的点，并显着提高检测性能。

RBGNet：基于射线分组的3D目标检测