Learning Discriminative Signed Distance Functions from Multi-scale Level-of-detail Features for 3D Anomaly Detection

TL;DR

This paper introduces a surface-based 3D anomaly detection method that learns a discriminative signed distance function from multi-scale features, improving accuracy on benchmark datasets.

Contribution

It proposes a novel multi-scale feature learning framework with noise generation and implicit surface discrimination for enhanced 3D anomaly detection.

Findings

Achieves 92.1% object-level AUROC on Anomaly-ShapeNet

Achieves 85.9% object-level AUROC on Real3D-AD

Outperforms previous methods by 2.1% and 3.6% on respective datasets.

Abstract

Detecting anomalies from 3D point clouds has received increasing attention in the field of computer vision, with some group-based or point-based methods achieving impressive results in recent years. However, learning accurate point-wise representations for 3D anomaly detection faces great challenges due to the large scale and sparsity of point clouds. In this study, a surface-based method is proposed for 3D anomaly detection, which learns a discriminative signed distance function using multi-scale level-of-detail features. We first present a Noisy Points Generation (NPG) module to generate different types of noise, thereby facilitating the learning of discriminative features by exposing abnormal points. Then, we introduce a Multi-scale Level-of-detail Feature (MLF) module to capture multi-scale information from a point cloud, which provides both fine-grained local and coarse-grained global feature information. Finally, we design an Implicit Surface Discrimination (ISD) module that leverages the extracted multi-scale features to learn an implicit surface representation of point clouds, which effectively trains a signed distance function to distinguish between abnormal and normal points. Experimental results demonstrate that the proposed method achieves an average object-level AUROC of 92.1\% and 85.9\% on the Anomaly-ShapeNet and Real3D-AD datasets, outperforming the current best approach by 2.1\% and 3.6\%, respectively. Codes are available at https://anonymous.4open.science/r/DLF-3AD-DA61.