Communications in Information and Systems

Volume 22 (2022)

Number 1

Learning point cloud shapes with geometric and topological structures

Pages: 103 – 129

DOI: https://dx.doi.org/10.4310/CIS.2022.v22.n1.a5

Authors

Yijie Zhu (State Key Lab. of CAD & CG, Zhejiang University, Hangzhou, China)

Zhetong Dong (School of Mathematical Sciences, Zhejiang University, Hangzhou, China)

Chi Zhou (School of Mathematical Sciences, Zhejiang University, Hangzhou, China)

Hongwei Lin (State Key Lab. of CAD & CG, School of Mathematical Sciences, Zhejiang University, Hangzhou, China)

Abstract

3D point cloud semantic analysis is challenging due to irregular locations and ill-posed sparse representations. In this study, we explore the intrinsic structures of point clouds, which assist convolutional neural networks in classification and segmentation tasks. The network is referred to as a geometric and topological structures based convolutional neural network (GTS-CNN). Firstly, the method extracts meaningful geometric adjacency for each surface point as well as the topological persistence information for the whole point cloud. Then the GTS-CNN processes this information with a multi-head mechanism. There are three branches within the network executing graph neighborhood message passing, point position-related inference, and persistence image feature embedding, respectively. In this way, an expressive descriptor is obtained with a combination of three kinds of features, leading to a robust and finely grained representation. Experiments on standard benchmarks, such as ModelNet40 and ShapeNet, show that our network achieves promising performance compared to state-of-the-art methods.

Received 15 July 2020

Published 7 February 2022