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

arXiv: https://arxiv.org/abs/1803.04249 · HTML: https://mlsanity.com/paper/1803.04249/

## Key facts

- Cited by 210 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2018.

## Built on by (most cited first, 30 of 210)

- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://mlsanity.com/paper/2101.02691/) (2021)
- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://mlsanity.com/paper/2103.14635/) (2021)
- [Geometric Transformer for Fast and Robust Point Cloud Registration](https://mlsanity.com/paper/2202.06688/) (2022)
- [CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding](https://mlsanity.com/paper/2203.00680/) (2022)
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://mlsanity.com/paper/2109.00179/) (2021)
- [Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis](https://mlsanity.com/paper/2105.01288/) (2021)
- [CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration](https://mlsanity.com/paper/2110.14076/) (2021)
- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders](https://mlsanity.com/paper/2212.06785/) (2022)
- [PointGPT: Auto-regressively Generative Pre-training from Point Clouds](https://mlsanity.com/paper/2305.11487/) (2023)
- [Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks](https://mlsanity.com/paper/2105.02358/) (2021)
- [GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer](https://mlsanity.com/paper/2308.03768/) (2023)
- [Equivariant Point Network for 3D Point Cloud Analysis](https://mlsanity.com/paper/2103.14147/) (2021)
- [Learning to Stylize Novel Views](https://mlsanity.com/paper/2105.13509/) (2021)
- [Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy](https://mlsanity.com/paper/2403.06467/) (2024)
- [PointMixer: MLP-Mixer for Point Cloud Understanding](https://mlsanity.com/paper/2111.11187/) (2021)
- [Adaptive Graph Convolution for Point Cloud Analysis](https://mlsanity.com/paper/2108.08035/) (2021)
- [DeepI2P: Image-to-Point Cloud Registration via Deep Classification](https://mlsanity.com/paper/2104.03501/) (2021)
- [PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis](https://mlsanity.com/paper/2112.04903/) (2021)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2108.06230/) (2021)
- [Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2202.13589/) (2022)
- [Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning](https://mlsanity.com/paper/2107.01886/) (2021)
- [Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training](https://mlsanity.com/paper/2302.14007/) (2023)
- [Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling](https://mlsanity.com/paper/2107.02389/) (2021)
- [Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning](https://mlsanity.com/paper/2201.00785/) (2022)
- [CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence](https://mlsanity.com/paper/2207.05483/) (2022)

## Abstract (arXiv)

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