mlsanityData to 7 Oct 2026

S3I-PointHop: SO(3)-Invariant PointHop for 3D Point Cloud Classification

arXiv 2302.11506 ↗First posted 22 Feb 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Many point cloud classification methods are developed under the assumption that all point clouds in the dataset are well aligned with the canonical axes so that the 3D Cartesian point coordinates can be employed to learn features. When input point clouds are not aligned, the classification performance drops significantly. In this work, we focus on a mathematically transparent point cloud classification method called PointHop, analyze its reason for failure due to pose variations, and solve the problem by replacing its pose dependent modules with rotation invariant counterparts. The proposed method is named SO(3)-Invariant PointHop (or S3I-PointHop in short). We also significantly simplify the PointHop pipeline using only one single hop along with multiple spatial aggregation techniques. The idea of exploiting more spatial information is novel. Experiments on the ModelNet40 dataset demonstrate the superiority of S3I-PointHop over traditional PointHop-like methods.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 22 of its 29 references that are in the map. First posted on arXiv 22 Feb 2023.

Builds on

22 of 29 references.

References · 22

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  4. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  5. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  6. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 180
  7. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 140
  8. 2021Equivariant Point Network for 3D Point Cloud Analysiscited by 81
  9. 2020A Rotation-Invariant Framework for Deep Point Cloud Analysiscited by 62
  10. 2018Interpretable Convolutional Neural Networks via Feedforward Designcited by 49
  11. 2019PointHop: An Explainable Machine Learning Method for Point Cloud Classificationcited by 46
  12. 2021Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimationcited by 45
10 more
  1. 2020PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classificationcited by 37
  2. 2022Green Learning: Introduction, Examples and Outlookcited by 30
  3. 2021R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Methodcited by 26
  4. 2022On Supervised Feature Selection from High Dimensional Feature Spacescited by 23
  5. 2020PointHop++: A Lightweight Learning Model on Point Sets for 3D Classificationcited by 22
  6. 2020Unsupervised Point Cloud Registration via Salient Points Analysis (SPA)cited by 19
  7. 2020Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentationcited by 17
  8. 2021GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Cloudscited by 7
  9. 2021GreenPCO: An Unsupervised Lightweight Point Cloud Odometry Methodcited by 4
  10. 2022PCRP: Unsupervised Point Cloud Object Retrieval and Pose Estimationcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 3.

3 papers.

  1. 2023Enhancing Edge Intelligence with Highly Discriminant LNT Featurescited by 3
  2. 2023PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Cloudscited by 1
  3. 2023A Tiny Machine Learning Model for Point Cloud Object Classificationcited by 0