Real-IAD MVN：一种多视角法向量数据集和基准，用于高保真工业异常检测
Real-IAD MVN: A Multi-View Normal Vector Dataset and Benchmark for High-Fidelity Industrial Anomaly Detection
AI总结：
本文提出Real-IAD-MVN数据集，通过多视角法向量捕捉微细几何缺陷，验证密集多视角伪3D数据在工业异常检测中的优越性能。
摘要：
工业异常检测（IAD）对质量控制至关重要，但现有方法难以检测细微几何缺陷。标准2D（RGB）图像对纹理和光照敏感，常遗漏细小几何异常。3D点云能捕捉宏观形状，但通常过于稀疏，无法检测如划痕或凹坑等微缺陷。我们通过升级采集系统，引入Real-IAD-MVN（多视角法向量）大规模工业数据集，捕获五种不同视角的高保真表面法向量图，取代稀疏3D数据。这提供了微细级别的全面几何表示，使之前不可见的侧壁和遮挡缺陷得以显式检测。实验表明，结合密集多视角伪3D（法向量）的数据比使用稀疏3D点云数据检测性能显著更好。为进一步验证数据集并提供强基准，我们引入基于重建的基线方法，学习从图像和法向量图流中提取跨模态统一原型。证明统一原型方法超越现有多模态融合方法，凸显新数据集在推进几何异常检测中的潜力。
英文摘要：
Industrial Anomaly Detection (IAD) is critical for quality control, but existing methods struggle with subtle, geometric defects. Standard 2D (RGB) images are sensitive to texture and lighting but often miss fine geometric anomalies. While 3D point clouds capture macro-shape, they are typically too sparse to detect micro-defects like scratches or pits. We address this fundamental data limitation by introducing Real-IAD-MVN (Multi-View Normal), a large-scale industrial dataset. By upgrading our acquisition system, Real-IAD-MVN captures high-fidelity surface normal maps from five distinct viewpoints, replacing sparse 3D data entirely. This provides a comprehensive geometric representation at a micro-detail level, making previously invisible side-wall and occluded defects explicitly detectable. Our experiments, conducted on this new dataset, first provide evidence that incorporating dense, multi-view pseudo-3D (surface normals) yields significantly better detection performance than using sparse 3D point cloud data. To further validate the dataset and provide a strong benchmark, we introduce a baseline method based on reconstruction, which learns to extract cross-modal unified prototypes from the image and normal map streams. We demonstrate that this unified prototype approach surpasses existing state-of-the-art multimodal fusion methods, highlighting the rich potential of our new dataset for advancing geometric anomaly detection.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
