arXiv 2603.227572026-03-24cs.CV

基于几何先验的多模态工业异常检测

Multimodal Industrial Anomaly Detection via Geometric Prior

Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）；Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences)（教育部计算功率网络与信息安全重点实验室，山东计算机科学中心（济南国家超算中心），齐鲁工业大学（山东省科学院））；Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science（山东省计算功率互联网与服务计算重点实验室，山东省计算机科学基础研究中心）

Min Li, Jinghui He, Gang Li, Jiachen Li, Jin Wan, Delong Han

备注：: Accepted for publication in IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
DOI：: 10.1109/TCSVT.2025.3613708

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出基于几何先验的异常检测网络GPAD，通过点云专家模型提取细粒度几何特征，并结合两阶段融合策略和几何先验实现高效多模态数据融合，提升几何缺陷检测精度。

摘要：

多模态工业异常检测的目标是检测难以用2D方法检测的复杂几何形状缺陷，如细微表面变形和不规则轮廓。然而，当前方法缺乏对关键几何信息如表面法向量和3D形状拓扑的有效利用，导致检测精度低下。本文提出Geometric Prior-based Anomaly Detection网络（GPAD）。首先，我们提出点云专家模型进行细粒度几何特征提取，利用微分法向量计算增强提取特征的几何细节并生成几何先验。其次，我们提出两阶段融合策略，高效利用多模态数据的互补性以及3D点固有的几何先验。我们进一步提出基于几何先验的注意力融合和异常区域分割，增强模型感知几何缺陷的能力。大量实验表明，我们的多模态工业异常检测模型在MVTec-3D AD和Eyecandies数据集上均优于现有最先进方法。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。