Toward Unsupervised 3D Point Cloud Anomaly Detection using Variational Autoencoder

TL;DR

This paper introduces a novel unsupervised anomaly detection method for 3D point clouds using a variational autoencoder, demonstrating superior performance on the ShapeNet dataset.

Contribution

It is the first to address unsupervised anomaly detection on general 3D object point clouds with a specialized autoencoder and anomaly score.

Findings

Outperforms baseline methods in experiments

Effective on ShapeNet dataset

Provides both quantitative and qualitative results

Abstract

In this paper, we present an end-to-end unsupervised anomaly detection framework for 3D point clouds. To the best of our knowledge, this is the first work to tackle the anomaly detection task on a general object represented by a 3D point cloud. We propose a deep variational autoencoder-based unsupervised anomaly detection network adapted to the 3D point cloud and an anomaly score specifically for 3D point clouds. To verify the effectiveness of the model, we conducted extensive experiments on the ShapeNet dataset. Through quantitative and qualitative evaluation, we demonstrate that the proposed method outperforms the baseline method. Our code is available at https://github.com/llien30/point_cloud_anomaly_detection.