Abstract
Despite substantial progress in anomaly synthesis methods, existing diffusion-based and coarse inpainting pipelines commonly suffer from structural deficiencies such as micro-structural discontinuities, limited semantic controllability, and inefficient generation. To overcome these limitations, we introduce ARAS, a language-conditioned, auto-regressive anomaly synthesis approach that precisely injects local, text-specified defects into normal images via token-anchored latent editing. Leveraging a hard-gated auto-regressive operator and a training-free, context-preserving masked sampling kernel, ARAS significantly enhances defect realism, preserves fine-grained material textures, and provides continuous semantic control over synthesized anomalies. Integrated within our Quality-Aware Re-weighted Anomaly Detection (QARAD) framework, we further propose a dynamic weighting strategy that emphasizes high-quality synthetic samples by computing an image-text similarity score with a dual-encoder model. Extensive experiments across three benchmark datasets-MVTec AD, VisA, and BTAD, demonstrate that our QARAD outperforms SOTA methods in both image- and pixel-level anomaly detection tasks, achieving improved accuracy, robustness, and a 5 times synthesis speedup compared to diffusion-based alternatives. Our complete code and synthesized dataset will be publicly available.
Abstract (translated)
尽管在异常合成方法方面取得了重大进展，现有的基于扩散和粗略修复的流程通常会遇到结构缺陷，如微观结构不连续、语义控制有限以及生成效率低下等问题。为了克服这些限制，我们引入了ARAS（条件语言自回归异常合成法），这是一种通过标记锚定潜在编辑精确注入局部、文本指定缺陷到正常图像的方法。借助硬门控的自回归运算符和无训练需求、上下文保留的掩码采样内核，ARAS显著提升了缺陷的真实感，保持了细微材料纹理，并提供了对合成异常的连续语义控制。 在我们提出的质量感知再加权异常检测（QARAD）框架中，我们进一步提出了一种动态加权策略，该策略通过双编码器模型计算图像文本相似度得分来强调高质量的合成样本。我们在三个基准数据集——MVTec AD、VisA和BTAD上进行了广泛的实验，结果表明我们的QARAD方法在图像级和像素级异常检测任务中超越了现有的最佳方法（SOTA），实现了更高的准确性和鲁棒性，并且与基于扩散的方法相比，合成速度提升了五倍。我们将公开发布完整的代码和合成数据集。
URL
https://arxiv.org/abs/2508.03539
