{"ID":2852541,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.21793","arxiv_id":"2510.21793","title":"2D_3D Feature Fusion via Cross-Modal Latent Synthesis and Attention Guided Restoration for Industrial Anomaly Detection","abstract":"Industrial anomaly detection (IAD) increasingly benefits from integrating 2D and 3D data, but robust cross-modal fusion remains challenging. We propose a novel unsupervised framework, Multi-Modal Attention-Driven Fusion Restoration (MAFR), which synthesises a unified latent space from RGB images and point clouds using a shared fusion encoder, followed by attention-guided, modality-specific decoders. Anomalies are localised by measuring reconstruction errors between input features and their restored counterparts. Evaluations on the MVTec 3D-AD and Eyecandies benchmarks demonstrate that MAFR achieves state-of-the-art results, with a mean I-AUROC of 0.972 and 0.901, respectively. The framework also exhibits strong performance in few-shot learning settings, and ablation studies confirm the critical roles of the fusion architecture and composite loss. MAFR offers a principled approach for fusing visual and geometric information, advancing the robustness and accuracy of industrial anomaly detection. Code is available at https://github.com/adabrh/MAFR","short_abstract":"Industrial anomaly detection (IAD) increasingly benefits from integrating 2D and 3D data, but robust cross-modal fusion remains challenging. We propose a novel unsupervised framework, Multi-Modal Attention-Driven Fusion Restoration (MAFR), which synthesises a unified latent space from RGB images and point clouds using...","url_abs":"https://arxiv.org/abs/2510.21793","url_pdf":"https://arxiv.org/pdf/2510.21793v1","authors":"[\"Usman Ali\",\"Ali Zia\",\"Abdul Rehman\",\"Umer Ramzan\",\"Zohaib Hassan\",\"Talha Sattar\",\"Jing Wang\",\"Wei Xiang\"]","published":"2025-10-20T03:57:50Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"eess.IV\"]","methods":"[]","has_code":false,"code_links":[{"ID":608003,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2852541,"paper_url":"https://arxiv.org/abs/2510.21793","paper_title":"2D_3D Feature Fusion via Cross-Modal Latent Synthesis and Attention Guided Restoration for Industrial Anomaly Detection","repo_url":"https://github.com/adabrh/MAFR","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}