通过分层点面融合与自适应编码，提升3D形状异常检测的泛化能力。
Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detection
- 分层建模局部点特征与区域块特征，增强异常推理能力
- 在工业数据集上点级性能提升超40%，对象级平均提升4%-7%
- 适用于复杂几何缺陷检测，尤其适合工业质检场景
3D形状异常检测在工业质检和几何分析中至关重要。现有深度学习方法通常学习正常形状表征，通过分布外特征或解码器重建识别异常，但难以跨多种异常类型和尺度泛化，对训练时噪声或不完整局部点敏感。为此，我们提出一种分层点-块异常评分网络，联合建模区域部件特征与局部点特征，实现鲁棒异常推理。自适应块划分模块结合自监督分解，捕捉复杂结构偏差。除了在公开基准（Anomaly-ShapeNet 和 Real3D-AD）上的评估，我们还发布了包含真实CAD模型的工业测试集，涵盖平面、角度及结构缺陷。实验表明，在公共与工业数据集上均取得更优的AUC-ROC与AUC-PR表现，点级性能在新工业异常类型上提升超过40%，对象级平均提升在Real3D-AD上达7%，Anomaly-ShapeNet上达4%，展现出强鲁棒性与泛化能力。
原文摘要 · Abstract (English)
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.
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。