用分阶段扩散模型生成更真实的工业缺陷图像，提升异常检测效果
OSAGEN: Object-Aware Mask Priors and Multistage Decoupled Diffusion for Industrial Anomaly Generation
- 分三阶段学习正常、缺陷与掩码校准，实现更精细的缺陷控制
- 在MVTec AD上达到88.1的AP-P，VisA上达68.5，性能领先
- 适合需要高质量合成缺陷数据的研究者和工业质检场景
工业异常检测与定位受限于真实异常样本稀缺及像素级标注不足，合成图像-掩码对可缓解此问题。但现有少样本掩码引导生成方法存在过度跟随掩码几何、缺陷表现弱或条件掩码与当前物体实例不兼容等问题。我们提出OSAGEN，结合对象感知掩码先验与多阶段解耦扩散模型。其三阶段适配依次学习正常外观、粗粒度缺陷外观及细粒度掩码校准，提升缺陷表征与局部控制能力。QBG从匹配的正常图像注入对象结构至掩码扩散，生成对象感知先验；ISC在采样过程中限制异常传播并保留正常内容。轻量级材质化步骤恢复与实际缺陷对齐的像素级标签。在MVTec AD和VisA数据集上，OSAGEN在统一下游定位协议下分别取得88.1/82.2和68.5/66.1的AP-P/F1-P分数。代码将在接受后发布。
原文摘要 · Abstract (English)
Industrial anomaly detection and localization are limited by scarce real anomalies and pixel-level annotations, a bottleneck that synthetic image-mask pairs can alleviate. However, existing few-shot mask-guided generation may over-follow mask geometry, produce weak anomalies, or use condition masks incompatible with the current object instance. We propose OSAGEN, which combines object-aware mask priors with multistage decoupled diffusion. Its three-stage adaptation sequentially learns normal appearance, defect appearance under coarse conditions, and fine-grained mask calibration, improving defect realization and local control. QBG injects object structure from a matched normal image into mask diffusion to produce object-aware priors, while ISC restricts anomaly propagation and preserves normal content during sampling. A lightweight materialization step recovers pixel-level labels aligned with the realized defects. On MVTec AD and VisA, OSAGEN achieves AP-P/F1-P scores of 88.1/82.2 and 68.5/66.1, respectively, under a unified downstream localization protocol. The code will be released upon acceptance.
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。