3D-SONAR: Self-Organizing Network for 3D Anomaly Ranking
Guodong Xu, Juan Du, Hui Yang
TL;DR
This paper tackles 3D surface anomaly detection on point clouds under data scarcity by introducing SONAR, a training-free method that treats the point cloud as a self-organizing spring–electrical network. Anomalies are identified through energy distribution: high-energy regions, amplified by local geometric asymmetry, are ranked after local normalization and a boundary-aware filtering step. The approach avoids normal-vector estimation and demonstrates superior performance on both open and closed surfaces compared with untrained baselines, validated on synthetic and real data. The work offers a physics-inspired, data-efficient pathway for industrial inspection and suggests extendability to volumetric data and repair-oriented tasks.
Abstract
Surface anomaly detection using 3D point cloud data has gained increasing attention in industrial inspection. However, most existing methods rely on deep learning techniques that are highly dependent on large-scale datasets for training, which are difficult and expensive to acquire in real-world applications. To address this challenge, we propose a novel method based on self-organizing network for 3D anomaly ranking, also named 3D-SONAR. The core idea is to model the 3D point cloud as a dynamic system, where the points are represented as an undirected graph and interact via attractive and repulsive forces. The energy distribution induced by these forces can reveal surface anomalies. Experimental results show that our method achieves superior anomaly detection performance in both open surface and closed surface without training. This work provides a new perspective on unsupervised inspection and highlights the potential of physics-inspired models in industrial anomaly detection tasks with limited data.