SO-Net: Self-Organizing Network for Point Cloud Analysis

Jiaxin Li, Ben M. Chen, Gim Hee Lee
3/12/2018
cs.CV

Official code: lijx10/SO-Net (345 stars, MIT, last commit 2021-02-24).

Abstract

This paper presents SO-Net, a permutation invariant architecture for deep learning with orderless point clouds. The SO-Net models the spatial distribution of point cloud by building a Self-Organizing Map (SOM). Based on the SOM, SO-Net performs hierarchical feature extraction on individual points and SOM nodes, and ultimately represents the input point cloud by a single feature vector. The receptive field of the network can be systematically adjusted by conducting point-to-node k nearest neighbor search. In recognition tasks such as point cloud reconstruction, classification, object part segmentation and shape retrieval, our proposed network demonstrates performance that is similar with or better than state-of-the-art approaches. In addition, the training speed is significantly faster than existing point cloud recognition networks because of the parallelizability and simplicity of the proposed architecture. Our code is available at the project website. https://github.com/lijx10/SO-Net

View on arXivView PDF

Code Implementations(1)

lijx10/SO-NetOfficial100%
MIT

SO-Net: Self-Organizing Network for Point Cloud Analysis, CVPR2018

34581C++, CudaFeb 28, 20185 years agoMIT
3dautonomous-drivingcomputer-visioncvprdeep-learning+1 more

Similar Papers

PCT: Point cloud transformer

89% match1 repo7232020

Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification

86% match1 repo152024

Nearest Neighbors Meet Deep Neural Networks for Point Cloud Analysis

86% match2023

A Systematic Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation

85% match1 repo62026

RoCNet: 3D Robust Registration of Point-Clouds using Deep Learning

85% match2023

Multi-view Structural Convolution Network for Domain-Invariant Point Cloud Recognition of Autonomous Vehicles

84% match1 repo2025

Cite this paper

@article{li2018sonet,
  title  = {SO-Net: Self-Organizing Network for Point Cloud Analysis},
  author = {Jiaxin Li and Ben M. Chen and Gim Hee Lee},
  year   = {2018},
  eprint = {1803.04249},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1803.04249}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1803.04249.svg)](https://codeofpaper.com/paper/1803.04249)

Discussion