Position: Untrained Machine Learning for Anomaly Detection by using 3D Point Cloud Data

TL;DR

This paper introduces untrained anomaly detection methods for 3D point cloud data that do not require prior training data, offering fast and effective solutions for data-scarce industrial and healthcare applications.

Contribution

It formally defines the untrained anomaly detection problem for 3D point clouds and proposes three novel frameworks leveraging prior knowledge without training data.

Findings

Achieves up to 15-fold faster detection compared to traditional methods.

Provides competitive anomaly detection performance without training data.

Addresses data scarcity in personalized manufacturing and healthcare.

Abstract

Anomaly detection based on 3D point cloud data is an important research problem and receives more and more attention recently. Untrained anomaly detection based on only one sample is an emerging research problem motivated by real manufacturing industries such as personalized manufacturing where only one sample can be collected without any additional labels and historical datasets. Identifying anomalies accurately based on one 3D point cloud sample is a critical challenge in both industrial applications and the field of machine learning. This paper aims to provide a formal definition of the untrained anomaly detection problem based on 3D point cloud data, discuss the differences between untrained anomaly detection and current unsupervised anomaly detection problems. Unlike trained unsupervised learning, untrained unsupervised learning does not rely on any data, including unlabeled data. Instead, they leverage prior knowledge about the surfaces and anomalies. We propose three complementary methodological frameworks: the Latent Variable Inference Framework that employs probabilistic modeling to distinguish anomalies; the Decomposition Framework that separates point clouds into reference, anomaly, and noise components through sparse learning; and the Local Geometry Framework that leverages neighborhood information for anomaly identification. Experimental results demonstrate that untrained methods achieve competitive detection performance while offering significant computational advantages, demonstrating up to a 15-fold increase in execution speed. The proposed methods provide viable solutions for scenarios with extreme data scarcity, addressing critical challenges in personalized manufacturing and healthcare applications where collecting multiple samples or historical data is infeasible.