Point Cloud Novelty Detection Based on Latent Representations of a General Feature Extractor

TL;DR

This paper introduces an unsupervised 3D point cloud novelty detection method that uses a general feature extractor and one-class classifier on latent vectors, outperforming existing coordinate-based approaches.

Contribution

The paper presents a novel latent space-based novelty detection approach that eliminates the need for retraining on new categories and improves detection accuracy.

Findings

Outperforms existing methods on ShapeNet datasets

Eliminates need for autoencoder re-training on new categories

Uses shape features condensed in latent representations

Abstract

We propose an effective unsupervised 3D point cloud novelty detection approach, leveraging a general point cloud feature extractor and a one-class classifier. The general feature extractor consists of a graph-based autoencoder and is trained once on a point cloud dataset such as a mathematically generated fractal 3D point cloud dataset that is independent of normal/abnormal categories. The input point clouds are first converted into latent vectors by the general feature extractor, and then one-class classification is performed on the latent vectors. Compared to existing methods measuring the reconstruction error in 3D coordinate space, our approach utilizes latent representations where the shape information is condensed, which allows more direct and effective novelty detection. We confirm that our general feature extractor can extract shape features of unseen categories, eliminating the need for autoencoder re-training and reducing the computational burden. We validate the performance of our method through experiments on several subsets of the ShapeNet dataset and demonstrate that our latent-based approach outperforms the existing methods.