arXiv 2511.032672025-11-05cs.CV

IEC3D-AD：面向无监督点云异常检测的工业设备部件三维数据集

IEC3D-AD: A 3D Dataset of Industrial Equipment Components for Unsupervised Point Cloud Anomaly Detection

Software College, Northeastern University（东北大学软件学院）；Shenzhen Audencia Financial Technology Institute, Shenzhen University（深圳Audencia金融技术研究院）；National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University（深圳大学大数据系统计算技术国家工程实验室）

Bingyang Guo, Hongjie Li, Ruiyun Yu, Hanzhe Liang, Jinbao Wang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文针对工业设备部件三维异常检测中现有数据集复杂度不足的问题，构建了高分辨率、细粒度标注的 IEC3D-AD 数据集，并提出基于几何形态分析与空间差异优化的 GMANet 范式，在多个数据集上验证了其有效性。

摘要：

三维异常检测（3D-AD）在工业制造中发挥着关键作用，尤其是在确保核心设备部件的可靠性和安全性方面。尽管现有的三维数据集（如 Real3D-AD 和 MVTec 3D-AD）提供了广泛的应用支持，但它们在捕捉真实工业环境中存在的复杂性和细微缺陷方面仍显不足。这一局限性阻碍了精确异常检测研究，尤其是针对轴承、环和螺栓等工业设备部件（IEC）的研究。为应对这一挑战，我们开发了一个专门面向真实工业场景的点云异常检测数据集（IEC3D-AD）。该数据集直接采集自实际生产线，确保了高保真度和相关性。与现有数据集相比，IEC3D-AD 在点云分辨率和缺陷标注粒度方面均有显著提升，从而能够支持更具挑战性的异常检测任务。此外，受生成式二维异常检测方法的启发，我们在 IEC3D-AD 上引入了一种新颖的三维异常检测范式（GMANet）。该范式基于几何形态分析生成合成点云样本，然后通过空间差异优化来缩小正常与异常点级特征之间的间隔并增大其重叠程度。大量实验证明了我们的方法在 IEC3D-AD 及其他数据集上的有效性。

英文摘要：

3D anomaly detection (3D-AD) plays a critical role in industrial manufacturing, particularly in ensuring the reliability and safety of core equipment components. Although existing 3D datasets like Real3D-AD and MVTec 3D-AD offer broad application support, they fall short in capturing the complexities and subtle defects found in real industrial environments. This limitation hampers precise anomaly detection research, especially for industrial equipment components (IEC) such as bearings, rings, and bolts. To address this challenge, we have developed a point cloud anomaly detection dataset (IEC3D-AD) specific to real industrial scenarios. This dataset is directly collected from actual production lines, ensuring high fidelity and relevance. Compared to existing datasets, IEC3D-AD features significantly improved point cloud resolution and defect annotation granularity, facilitating more demanding anomaly detection tasks. Furthermore, inspired by generative 2D-AD methods, we introduce a novel 3D-AD paradigm (GMANet) on IEC3D-AD. This paradigm generates synthetic point cloud samples based on geometric morphological analysis, then reduces the margin and increases the overlap between normal and abnormal point-level features through spatial discrepancy optimization. Extensive experiments demonstrate the effectiveness of our method on both IEC3D-AD and other 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。