{"ID":2837332,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18766","arxiv_id":"2511.18766","title":"Unsupervised Multi-View Visual Anomaly Detection via Progressive Homography-Guided Alignment","abstract":"Unsupervised visual anomaly detection from multi-view images presents a significant challenge: distinguishing genuine defects from benign appearance variations caused by viewpoint changes. Existing methods, often designed for single-view inputs, treat multiple views as a disconnected set of images, leading to inconsistent feature representations and a high false-positive rate. To address this, we introduce ViewSense-AD (VSAD), a novel framework that learns viewpoint-invariant representations by explicitly modeling geometric consistency across views. At its core is our Multi-View Alignment Module (MVAM), which leverages homography to project and align corresponding feature regions between neighboring views. We integrate MVAM into a View-Align Latent Diffusion Model (VALDM), enabling progressive and multi-stage alignment during the denoising process. This allows the model to build a coherent and holistic understanding of the object's surface from coarse to fine scales. Furthermore, a lightweight Fusion Refiner Module (FRM) enhances the global consistency of the aligned features, suppressing noise and improving discriminative power. Anomaly detection is performed by comparing multi-level features from the diffusion model against a learned memory bank of normal prototypes. Extensive experiments on the challenging RealIAD and MANTA datasets demonstrate that VSAD sets a new state-of-the-art, significantly outperforming existing methods in pixel, view, and sample-level visual anomaly proving its robustness to large viewpoint shifts and complex textures.","short_abstract":"Unsupervised visual anomaly detection from multi-view images presents a significant challenge: distinguishing genuine defects from benign appearance variations caused by viewpoint changes. Existing methods, often designed for single-view inputs, treat multiple views as a disconnected set of images, leading to inconsist...","url_abs":"https://arxiv.org/abs/2511.18766","url_pdf":"https://arxiv.org/pdf/2511.18766v1","authors":"[\"Xintao Chen\",\"Xiaohao Xu\",\"Bozhong Zheng\",\"Yun Liu\",\"Yingna Wu\"]","published":"2025-11-24T05:01:16Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Diffusion Model\"]","has_code":false}