---
title: "Rotation Invariant Spatial Networks for Single-View Point Cloud Classification"
authors:
  - "Feng Luan"
  - "Jiarui Hu"
  - "Changshi Zhou"
  - "Zhipeng Wang"
  - "Jiguang Yue"
  - "Yanmin Zhou"
  - "Bin He"
doi: "10.24963/ijcai.2025/189"
url: "https://ijcai.org/proceedings/2025/189"
pdf: "https://ijcai.org/proceedings/2025/0189.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "1693-1701"
track: "Main Track"
keywords:
  - "Computer Vision: CV: Recognition (object detection, categorization)"
  - "Computer Vision: CV: Machine learning for vision"
  - "Computer Vision: CV: Scene analysis and understanding"
---

# Rotation Invariant Spatial Networks for Single-View Point Cloud Classification

Feng Luan, Jiarui Hu, Changshi Zhou, Zhipeng Wang, Jiguang Yue, Yanmin Zhou, Bin He

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 1693-1701. DOI: [10.24963/ijcai.2025/189](https://doi.org/10.24963/ijcai.2025/189)

## Abstract

Point cloud classification is critical for three-dimensional scene understanding. However, in real-world scenarios, depth cameras often capture partial, single-view point clouds of objects with different poses, making their accurate classification a challenge. In this paper, we propose a novel point cloud classification network that captures the detailed spatial structure of objects by constructing tetrahedra, which is different from point-wise operations. Specifically, we propose a RISpaNet block to extract rotation-invariant features. A rotation-invariant property generation module is designed in RISpaNet for constructing rotation-invariant tetrahedron properties (RITPs). Meanwhile, a multi-scale pooling module and a hybrid encoder are used to process RITPs to generate integrated rotation-invariant features. Further, for single-view point clouds, a complete point cloud auxiliary branch and a part-whole correlation module are jointly employed to obtain complete point cloud features from partial point clouds. Experimental results show that this network performs better than other state-of-the-art methods, evaluated on four public datasets. We achieved an overall accuracy of 94.7% (+2.0%) on ModelNet40, 93.4% (+5.9%) on MVP, 94.7% (+6.3%) on PCN and 94.8% (+1.7%) on ScanObjectNN. Our project website is https://luxurylf.github.io/RISpaNet_project/.