发表机构
School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出DeCo方法，通过解耦与重耦实现零样本工业异常生成，解决现有方法的局限，在MVTec AD和VisA数据集上训练下游检测模型分别获5.1%、8.2%的像素级AP提升，达到新最优性能。
AI 中文摘要
工业异常检测因真实异常样本稀缺而受到严重阻碍，零样本工业异常生成技术可在无需特定产品真实异常图像的情况下生成对应产品的异常，但现有方法存在两个关键局限：异常信息获取不准确、异常与产品的匹配不受控。为克服这些挑战，本文提出DeCo，其将异常结构从源产品中解耦，并明确将其与目标产品的正常纹理重耦。在异常信息获取阶段，双路流（DR-Flow）将纹理不变的异常结构绑定到异常token，而并行约束的产品不变流（PI-Flow）则防止异常token与源产品绑定；在异常-产品融合阶段，本文提出混合注入方法将获取的异常结构与目标产品重耦，还提出产品兼容性校正（PCC）以补偿异常结构与产品间的不兼容性。大量实验表明，DeCo达到了新的最优性能，在其生成的数据上训练下游检测模型，在MVTec AD数据集上像素级AP提升5.1%，在VisA数据集上提升8.2%，代码可在指定网址获取。
英文摘要
Industrial anomaly inspection is severely hindered by the scarcity of real anomalous data. Zero-shot industrial anomaly generation addresses this by generating anomalies on specific products without requiring any of their real anomalous images. However, existing methods suffer from two critical limitations, i.e., inaccurate anomaly information acquisition and uncontrolled anomaly-product fusion. To overcome these challenges, we propose DeCo, which decouples the anomaly structure from its source product, and explicitly recouples it with the normal textures of the target product. During anomaly information acquisition, Dual-Routing Flow (DR-Flow) binds the texture-invariant anomaly structure to an abnormal token, while a parallel constraint, Product-Invariant Flow (PI-Flow), prevents the abnormal token from binding the source product. During anomaly-product fusion, we propose a hybrid injection to recouple the acquired anomaly structure with the target product, and Product Compatibility Correction (PCC) to compensate for the incompatibility between the acquired anomaly structure and the product. Extensive experiments demonstrate that DeCo establishes a new state-of-the-art. Training downstream detection models on our generated data yields massive pixel AP improvements of 5.1% on MVTec AD and 8.2% on VisA. Code is available at https://github.com/HUST-SLOW/DeCo.
CommentsAccepted at ECCV2026
