发表机构
Shenzhen University（深圳大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对三维点云异常检测定位不精确的问题，提出AT3D-AD框架，通过物理驱动参数化异常合成、层级全局-局部对齐和语义-几何分类模块，实现联合检测、定位与分类，在四个基准上达到最先进性能。
AI 中文摘要
检测和定位三维点云缺陷对于工业检测至关重要。然而，现有方法由于缺乏异常监督且依赖单一粒度的表示，常常导致定位不精确。为解决这些局限性，我们提出了异常类型感知三维异常检测（AT3D-AD），这是一个用于联合检测、定位和分类的统一框架。具体而言，我们首先设计了物理驱动的参数化异常合成（PDPAS）模块，该模块采用多个参数化函数生成合成异常，提供明确的异常监督。然后，我们提出了层级全局-局部异常对齐（HiGLA）模块，在正常组和异常组内对齐全局和局部表示。最后，我们提出了语义-几何异常分类（SGAC）模块，以联合学习定位和分类，生成空间精确且类型可区分的异常表示。大量实验在全部四个基准上确立了新的最先进性能。AT3D-AD在Anomaly-ShapeNet上取得了98.1%/98.9%的对象/点AUROC分数，在Real3D-AD上取得了95.0%/95.2%的分数，同时在Real3D-AD上实现了74.2%的Macro-F1异常类型识别分数。
英文摘要
Detecting and localizing 3D point-cloud defects is essential for industrial inspection. However, existing methods often suffer from imprecise localization due to the lack of anomaly supervision and reliance on single-granularity representations. To address these limitations, we propose Anomaly Type-Aware 3D Anomaly Detection (AT3D-AD), a unified framework for joint detection, localization, and classification. Specifically, we first design the Physics-Driven Parametric Anomaly Synthesis (PDPAS) module employing multiple parametric functions to generate synthetic anomalies, providing explicit anomaly supervision. Then, we propose the Hierarchical Global-Local Anomaly Alignment (HiGLA) module to align global and local representations within the normal and anomalous groups. Finally, we propose the Semantic-Geometric Anomaly Classification (SGAC) module to jointly learn localization and classification, yielding spatially precise and type-discriminative anomaly representations. Extensive experiments establish new state-of-the-art performance on all four benchmarks. AT3D-AD achieves Object/Point AUROC scores of 98.1\%/98.9\% on Anomaly-ShapeNet and 95.0\%/95.2\% on Real3D-AD, while reaching 74.2\% Macro-F1 for anomaly-type recognition on Real3D-AD.
