用于3D形状异常检测的层次化点-面片融合与自适应面片码本
Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detection
提出层次化点-面片融合与自适应面片码本，可复用于点云异常检测与细粒度几何偏差建模；其自监督分解模块为无监督3D形状分析提供新思路。
原文依据 we propose a hierarchical point-patch anomaly scoring network that jointly models regional part features and local point features for robust anomaly reasoning.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论3D形状异常检测是工业检测和几何分析中的关键任务。现有的深度学习方法通常学习正常形状的表示，并通过分布外特征检测或基于解码器的重建来识别异常。它们往往难以泛化到多样的异常类型和尺度，例如全局几何误差（如平面偏移、角度错位），并且在训练过程中对噪声或不完整的局部点敏感。为了解决这些限制，我们提出了一种层次化点-面片异常评分网络，联合建模区域部件特征和局部点特征，以实现鲁棒的异常推理。自适应面片化模块集成了自监督分解，以捕获复杂的结构偏差。除了在公开基准（Anomaly-ShapeNet和Real3D-AD）上进行评估外，我们还发布了一个包含真实CAD模型的工业测试集，这些模型表现出平面、角度和结构缺陷。在公开和工业数据集上的实验表明，该方法在AUC-ROC和AUC-PR性能上更优，包括在新工业异常类型上点级提升超过40%，以及在Real3D-AD上平均对象级增益7%、在Anomaly-ShapeNet上增益4%，展示了强大的鲁棒性和泛化能力。
英文原文摘要 1281 字符
3D shape anomaly detection is a crucial task for industrial inspection and geometric analysis. Existing deep learning approaches typically learn representations of normal shapes and identify anomalies via out-of-distribution feature detection or decoder-based reconstruction. They often fail to generalize across diverse anomaly types and scales, such as global geometric errors (e.g., planar shifts, angle misalignments), and are sensitive to noisy or incomplete local points during training. To address these limitations, we propose a hierarchical point-patch anomaly scoring network that jointly models regional part features and local point features for robust anomaly reasoning. An adaptive patchification module integrates self-supervised decomposition to capture complex structural deviations. Beyond evaluations on public benchmarks (Anomaly-ShapeNet and Real3D-AD), we release an industrial test set with real CAD models exhibiting planar, angular, and structural defects. Experiments on public and industrial datasets show superior AUC-ROC and AUC-PR performance, including over 40% point-level improvement on the new industrial anomaly type and average object-level gains of 7% on Real3D-AD and 4% on Anomaly-ShapeNet, demonstrating strong robustness and generalization.