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

TL;DR

SO-Net introduces a permutation invariant deep learning architecture for point clouds that models spatial distribution using a Self-Organizing Map, enabling efficient hierarchical feature extraction and achieving competitive recognition performance.

Contribution

The paper proposes SO-Net, a novel architecture that leverages Self-Organizing Maps for effective and fast point cloud analysis, improving upon existing methods.

Findings

Achieves comparable or superior accuracy in recognition tasks

Faster training speed due to architecture simplicity and parallelization

Demonstrates effective hierarchical feature extraction

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