融合2D图像与3D点云，提升工业缺陷检测精度
2D_3D Feature Fusion via Cross-Modal Latent Synthesis and Attention Guided Restoration for Industrial Anomaly Detection
- 用共享编码器合成统一潜在空间，再通过注意力引导解码
- 在MVTec 3D-AD上达0.972的I-AUROC，领先现有方法
- 适合需要高精度缺陷定位的工业质检场景
工业异常检测（IAD）日益依赖2D与3D数据融合，但跨模态融合仍具挑战。本文提出一种新型无监督框架MAFR，通过共享融合编码器从RGB图像与点云中合成统一潜在空间，并采用注意力引导的模态特定解码器进行重建。异常通过输入特征与恢复特征间的重建误差定位。在MVTec 3D-AD和Eyecandies基准测试中，MAFR分别取得0.972和0.901的平均I-AUROC，性能达当前最优。该框架在少样本学习设置下也表现优异，消融实验验证了融合架构与复合损失的关键作用。MAFR为视觉与几何信息融合提供了系统性解决方案，显著提升工业异常检测的鲁棒性与准确性。代码已开源。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。