GeoMAD：基于可变形融合与分布对齐的几何感知多视图异常检测
GeoMAD: Geometry-Aware Multi-View Anomaly Detection via Deformable Fusion and Distributional Alignment
- National Taiwan University（台湾大学）
- National Taiwan Normal University（台湾师范大学）
- Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究院）
- Microsoft Taiwan Corporation（微软台湾公司）
- VinUniversity
- National Taiwan University of Science and Technology（台湾科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
GeoMAD是一种多视图多类别异常检测框架，通过跨视图可变形融合模块与分布视图对齐，实现几何感知与分布一致的高效融合，在Real-IAD等数据集上表现出色。
AI中文摘要：
多视图异常检测（MvAD）通过利用多个相机视角的互补观测来检测缺陷，核心挑战是在融合视角时具备充分的几何感知能力，同时能扩展至多类别工业场景。现有方法通常分为两个极端：基于体素的融合提供显式几何对齐，但需要昂贵的3D构建和类别特定假设；而轻量的基于块的融合效率高，但依赖离散候选匹配，缺乏连续的跨视图对应关系。本文提出GeoMAD，一个统一的多视图、多类别AD框架，以解决几何对应不足和分布不一致问题。我们的跨视图可变形融合模块（CDFM）直接在2D特征图上学习内容自适应、视图对特定的采样偏移，并将其排列在多尺度窗口金字塔中，结合图像全局参考采样，无需相机标定、体素构建或类别特定的3D监督即可实现分层跨视图对应。我们进一步引入分布视图对齐（DVA），一种自监督跨视图正则化损失，将每个视图的瓶颈分布与按实例的视图中心目标对齐，无需像素级对应即可强制全局一致性。CDFM和DVA结合，桥接了局部几何对应与全局分布一致性，在保持2D特征空间学习效率的同时，提供几何感知和分布一致的融合。在Real-IAD和MANTA-Tiny上的大量实验表明，GeoMAD在统一MvAD中实现了出色的检测和定位性能。
英文摘要：
Multi-view anomaly detection (MvAD) detects defects by exploiting complementary observations from multiple camera viewpoints. The central challenge is to fuse views with sufficient geometric awareness while remaining scalable to multi-class industrial settings. Existing methods typically fall into two extremes: voxel-based fusion provides explicit geometric alignment but requires costly 3D construction and class-specific assumptions, whereas lightweight patch-based fusion is efficient but relies on discrete candidate matching and lacks continuous cross-view correspondence. In this paper, we propose GeoMAD, a unified multi-view, multi-class AD framework that addresses both geometric correspondence deficiency and distributional inconsistency. Our \textit{Cross-view Deformable Fusion Module} (CDFM) learns content-adaptive, view-pair-specific sampling offsets directly on 2D feature maps and arranges them across a multi-scale window pyramid with image-global reference sampling, enabling hierarchical cross-view correspondence without camera calibration, voxel construction, or class-specific 3D supervision. We further introduce \textit{Distributional View Alignment} (DVA), a self-supervised cross-view regularization loss that aligns each view's bottleneck distribution against a per-instance view-centric target, enforcing global consistency without pixel-level correspondence. Together, CDFM and DVA bridge local geometric correspondence and global distributional consistency, providing geometry-aware and distribution-consistent fusion while preserving the efficiency of 2D feature-space learning. Extensive experiments on Real-IAD and MANTA-Tiny show that GeoMAD achieves strong detection and localization performance in unified MvAD.
