SGG-Nets: Generic Rotation-Invariant Plugin Networks for Point Cloud Analysis

Jian Zhu, Jianrong Yan, Jiebin Huang, Yongwei Nie, Bin Sheng, Tong-Yee Lee

Abstract: Rotation invariance is a crucial requirement for the analysis of 3D point clouds. However, current methods often achieve rotation invariance by employing specific network designs. These networks, though perform well on rotationaware tasks, is inferior in general tasks such as classification and segmentation. On the other hand, many powerful point processing networks, such as PointNet++, DGCNN, etc., have general point processing abilities, but do not own the property of rotation invariance. In this paper, we propose a standalone rotation invariant convolution operator called SGGConv (Spherical Geometric Graph-based Convolution) and two ways integrating it with common point-based networks. The networks equipped with SGGConvs are called SGG-Nets which promote the rotation-invariance ability of regular point networks without modifying their network architectures much. Our contributions are three-fold. First, we propose a rotation invariant feature descriptor, namely Spherical Geometry Descriptor (SGD), which captures point-pair features in a Local Spherical Coordinate System (LSCS). Second, we propose the SGGConv based on SGD and LSCS with an efficient Graph-based Spherical Feature Passing (GSFP) mechanism. Thirdly, we define two modules S-SGGConvMdl and M-SGGConvMdl, which are used to integrate SGGConv into baseline point nets. We test SGG-Nets, such as SGG-PointNet++, SGG-DGCNN, SGG-RIConv++, on representative point cloud datasets. These models, equipped with our SGGConvs, not only enhance the rotation-invariance of the baseline network but also improve its performance on point cloud analysis tasks such as classification and part segmentation, without incurring too much computational overhead.