用正常点云生成多样化伪异常，提升无监督3D缺陷检测效果
Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detection
- 基于局部PCA框架的参数化形变模型，可控制空间衰减与方向性
- 在AnomalyShapeNet和Real3D-AD上实现对象级与点级检测精度提升
- 模块化设计，适配多种无监督3D异常检测方法，代码开源
3D点云缺陷检测面临异常样本稀缺且多样性的挑战，而训练通常仅使用正常数据。本文提出Anomaly Factory 3D（AF3AD），一种模块化框架，通过从正常点云中合成多样化伪异常来扩展训练数据，用于依赖伪异常的无监督3D异常检测方法。AF3AD采用基于局部PCA帧的中心条件参数化形变模型，结合核控空间衰减、各向异性、方向门控及法向/切向位移场，支持多种几何缺陷预设。实验表明，将AF3AD集成至偏移预测检测器和基于重建的方法中，均能显著提升检测与定位性能。在AnomalyShapeNet和Real3D-AD数据集上，对象级与点级指标持续改进，消融实验验证了不同预设组的有效性，并展示了对噪声的鲁棒性。AF3AD作为独立合成工具，可跨检测范式复用，代码已开源。
原文摘要 · Abstract (English)
Detecting and localizing defects in 3D point clouds is challenging because abnormal samples are scarce and diverse, while training is often limited to normal data. We propose Anomaly Factory 3D (AF3AD), a modular framework that synthesizes diverse pseudo-anomalies from normal point clouds to expand the training data for unsupervised 3D anomaly detection methods that rely on pseudo-anomalies. AF3AD uses a center-conditioned parametric deformation model defined in local PCA frames, with kernel-controlled spatial falloff, anisotropy, directional gating, and normal/tangential displacement fields, enabling a broad set of geometric defect presets. We demonstrate its ease-of-use and effectiveness by integrating AF3AD with an offset-prediction detector and a reconstruction-based anomaly detection method, showing that AF3AD transfers across detection paradigms. Experiments on AnomalyShapeNet and Real3D-AD show consistent improvements in object- and point-level detection and localization, supported by ablations on preset groups and robustness under noise. AF3AD is designed as a standalone synthesis tool to facilitate adoption across different 3D anomaly detection paradigms. Code is available at github.com/vpc-ccg/AF3AD.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。