Multimodal Industrial Anomaly Detection via Geometric Prior

TL;DR

This paper introduces GPAD, a novel multimodal anomaly detection network that leverages geometric priors and 3D shape information to improve detection accuracy of complex industrial defects.

Contribution

The paper proposes a new geometric prior-based network with a point cloud expert model and a two-stage fusion strategy for enhanced multimodal anomaly detection.

Findings

Outperforms state-of-the-art methods on MVTec-3D AD and Eyecandies datasets.

Achieves higher detection accuracy for complex geometric defects.

Effectively utilizes geometric prior and multimodal data fusion.

Abstract

The purpose of multimodal industrial anomaly detection is to detect complex geometric shape defects such as subtle surface deformations and irregular contours that are difficult to detect in 2D-based methods. However, current multimodal industrial anomaly detection lacks the effective use of crucial geometric information like surface normal vectors and 3D shape topology, resulting in low detection accuracy. In this paper, we propose a novel Geometric Prior-based Anomaly Detection network (GPAD). Firstly, we propose a point cloud expert model to perform fine-grained geometric feature extraction, employing differential normal vector computation to enhance the geometric details of the extracted features and generate geometric prior. Secondly, we propose a two-stage fusion strategy to efficiently leverage the complementarity of multimodal data as well as the geometric prior inherent in 3D points. We further propose attention fusion and anomaly regions segmentation based on geometric prior, which enhance the model's ability to perceive geometric defects. Extensive experiments show that our multimodal industrial anomaly detection model outperforms the State-of-the-art (SOTA) methods in detection accuracy on both MVTec-3D AD and Eyecandies datasets.