Existing 3D anomaly detection methods are built on a rigid prior: normal geometry is pose-invariant and can be canonicalized through registration or alignment. This prior does not hold for articulated objects with hinge or sliding joints, where valid pose changes induce structured geometric variations that cannot be collapsed to a single canonical template, causing pose-induced deformations to be misidentified as anomalies while true structural defects are obscured. No existing benchmark addresses this challenge. We introduce ArtiAD, the first large-scale benchmark for articulated 3D anomaly detection, comprising 15,229 point clouds across 39 object categories with dense joint-angle variations and six structural anomaly types. Each sample is annotated with its joint configuration and part-level motion labels, enabling explicit disentanglement of pose-induced geometry from structural defects. ArtiAD also provides a seen/unseen articulation split to evaluate both interpolation and extrapolation to novel joint configurations. We propose Shape-Pose-Aware Signed Distance Field (SPA-SDF), a baseline that replaces the rigid prior with a continuous pose-conditioned implicit field, factorized into an articulation-independent structural prior and a Fourier-encoded joint embedding. At inference, the articulation state is recovered by minimizing reconstruction energy, and anomalies are identified as point-wise deviations from the learned manifold. SPA-SDF achieves 0.884 object-level AUROC on seen configurations and 0.874 on unseen configurations, substantially outperforming all rigid-based baselines. Our code and benchmark will be publicly released to facilitate future research.

翻译：现有三维异常检测方法建立在刚性先验之上：正常几何形状具有姿态不变性，可通过配准或对齐进行归一化。然而，对于具有铰链或滑动关节的可动关节物体，这一先验并不成立——合理的姿态变化会引发结构化几何形变，这类形变无法压缩至单一标准模板，导致姿态诱发的形变被误判为异常，而真实的结构缺陷却被掩盖。目前尚无基准数据集能应对这一挑战。我们提出ArtiAD——首个面向可动关节三维异常检测的大规模基准数据集，包含39个物体类别的15,229个点云，涵盖密集关节角度变化与六类结构异常。每个样本均标注了关节构型与部件级运动标签，从而显式解耦姿态诱发几何形变与结构缺陷。ArtiAD还提供"可见/不可见关节运动"划分，以评估对新型关节构型的插值与外推能力。我们提出形状-姿态感知符号距离场（SPA-SDF）作为基线方法，该方法以连续姿态条件隐式场替代刚性先验，分解为与关节运动无关的结构先验与傅里叶编码的关节嵌入。推理阶段通过最小化重建能量恢复关节状态，并将异常识别为点云相对于学习流形的逐点偏差。SPA-SDF在可见与不可见构型上分别达到0.884与0.874的物体级AUROC，显著优于所有基于刚性先验的基线方法。代码与基准数据集将公开以推动后续研究。