Search papers, labs, and topics across Lattice.
This paper introduces GeoMAD, a novel framework for multi-view anomaly detection (MvAD) that combines geometric awareness with distributional alignment to enhance defect detection across multiple camera viewpoints. By employing a Cross-view Deformable Fusion Module (CDFM) that adapts sampling offsets on 2D feature maps and a self-supervised Distributional View Alignment (DVA) loss, GeoMAD effectively bridges local geometric correspondence and global distributional consistency without the need for complex 3D constructions or class-specific supervision. Experimental results on benchmark datasets demonstrate that GeoMAD significantly improves detection and localization performance in multi-class industrial settings.
GeoMAD achieves superior anomaly detection by seamlessly integrating geometric correspondence with distributional consistency, all while maintaining efficiency in 2D feature-space learning.
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.
