Industrial anomaly segmentation relies heavily on pixel-level annotations, yet real-world anomalies are often scarce, diverse, and costly to label. Segmentation-oriented industrial anomaly synthesis (SIAS) has emerged as a promising alternative; however, existing methods struggle to balance sampling efficiency and generation quality. Moreover, most approaches treat all spatial regions uniformly, overlooking the distinct statistical differences between anomaly and background areas. This uniform treatment hinders the synthesis of controllable, structure-specific anomalies tailored for segmentation tasks. In this paper, we propose FAST, a foreground-aware diffusion framework featuring two novel modules: the Anomaly-Informed Accelerated Sampling (AIAS) and the Foreground-Aware Reconstruction Module (FARM). AIAS is a training-free sampling algorithm specifically designed for segmentation-oriented industrial anomaly synthesis, which accelerates the reverse process through coarse-to-fine aggregation and enables the synthesis of state-of-the-art segmentation-oriented anomalies in as few as 10 steps. Meanwhile, FARM adaptively adjusts the anomaly-aware noise within the masked foreground regions at each sampling step, preserving localized anomaly signals throughout the denoising trajectory. Extensive experiments on multiple industrial benchmarks demonstrate that FAST consistently outperforms existing anomaly synthesis methods in downstream segmentation tasks. We release the code at: https://github.com/Chhro123/fast-foreground-aware-anomaly-synthesis.

翻译：工业异常分割严重依赖于像素级标注，然而现实世界中的异常往往稀缺、多样且标注成本高昂。面向分割的工业异常合成（SIAS）已成为一种有前景的替代方案；然而，现有方法难以在采样效率与生成质量之间取得平衡。此外，大多数方法对所有空间区域进行统一处理，忽略了异常区域与背景区域之间显著的统计差异。这种统一处理阻碍了为分割任务量身定制的、可控的、结构特异性异常的合成。本文提出FAST，一种前景感知扩散框架，包含两个新颖模块：异常信息加速采样（AIAS）和前景感知重建模块（FARM）。AIAS是一种专为面向分割的工业异常合成设计的免训练采样算法，它通过从粗到细的聚合加速逆向过程，并能在少至10步内合成最先进的面向分割的异常。同时，FARM在每一步采样中自适应地调整掩码前景区域内的异常感知噪声，在整个去噪轨迹中保留局部化的异常信号。在多个工业基准数据集上的大量实验表明，FAST在下游分割任务中始终优于现有的异常合成方法。代码发布于：https://github.com/Chhro123/fast-foreground-aware-anomaly-synthesis。