2D_3D特征融合：基于跨模态潜在合成与注意力引导重建的工业异常检测
2D_3D Feature Fusion via Cross-Modal Latent Synthesis and Attention Guided Restoration for Industrial Anomaly Detection
AI总结：
提出MAFR无监督框架，通过共享融合编码器和注意力引导解码器融合2D与3D数据，在MVTec 3D-AD和Eyecandies上取得SOTA结果，平均I-AUROC达0.972和0.901。
摘要：
工业异常检测（IAD）日益受益于2D和3D数据的整合，但稳健的跨模态融合仍具挑战性。我们提出了一种新颖的无监督框架——多模态注意力驱动融合重建（MAFR），该框架通过共享融合编码器从RGB图像和点云中合成统一潜在空间，随后采用注意力引导的模态特定解码器。通过测量输入特征与其重建对应物之间的重建误差来定位异常。在MVTec 3D-AD和Eyecandies基准上的评估表明，MAFR达到了最先进的结果，平均I-AUROC分别为0.972和0.901。该框架在少样本学习设置中也表现出强劲性能，消融研究证实了融合架构和复合损失的关键作用。MAFR为融合视觉和几何信息提供了一种原则性方法，推进了工业异常检测的鲁棒性和准确性。代码可在https://github.com/adabrh/MAFR获取。
英文摘要：
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
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。
