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

2025-11-05

AI Summary

Existing 3D anomaly detection datasets (e.g., Real3D-AD, MVTec 3D-AD) inadequately capture subtle, real-world defects—such as micro-cracks or surface irregularities—in industrial components (e.g., bearings, bolts). Method: We introduce IEC3D-AD, the first high-resolution point cloud dataset specifically designed for industrial equipment components, built via precision 3D scanning and expert-level defect annotation covering diverse real defect patterns. Concurrently, we propose GMANet, a generative geometric morphology-aware network that uniquely integrates geometric morphology analysis into a generative reconstruction framework, enhancing point-level feature alignment through spatial-difference optimization for unsupervised, fine-grained anomaly localization. Contribution/Results: Experiments demonstrate that GMANet achieves state-of-the-art performance on IEC3D-AD and exhibits strong cross-dataset generalization, significantly improving accuracy and robustness of point cloud-based anomaly detection in complex industrial scenarios.

Technology Category

• Computer Vision: 3D Computer Vision
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

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.

Problem

• Existing 3D datasets lack industrial defect complexity
• Industrial equipment components need precise anomaly detection
• Current methods struggle with subtle real-world defects

Innovation

• Dataset with high-resolution point clouds from production lines
• Generative paradigm using geometric morphological analysis
• Spatial optimization to reduce normal-abnormal feature margin