用区域约束扩散和判别掩码引导，生成更精准的工业缺陷图像。
SARD: Segmentation-Aware Anomaly Synthesis via Region-Constrained Diffusion with Discriminative Mask Guidance
- 通过冻结背景只更新前景区域，提升异常位置控制力。
- 在MVTec-AD和BTAD上达到最新像素级合成精度。
- 适合需要高精度异常数据增强的工业质检场景。
真实且空间精确的异常合成对提升工业异常检测系统的鲁棒性至关重要。尽管基于扩散的方法在建模复杂缺陷模式方面表现出色，但往往缺乏空间可控性，难以保持细粒度区域保真度。为此，我们提出SARD（基于区域约束扩散与判别掩码引导的分割感知异常合成），一种专为异常生成设计的新型扩散框架。该方法引入区域约束扩散（RCD）过程，在反向去噪阶段冻结背景，仅选择性更新前景异常区域，从而有效减少背景伪影。此外，我们在判别器中集成判别掩码引导（DMG）模块，实现对全局真实性和局部异常保真度的联合评估，借助像素级掩码进行引导。在MVTec-AD和BTAD数据集上的大量实验表明，SARD在分割准确率和视觉质量上均优于现有方法，实现了像素级异常合成的新基准。
原文摘要 · Abstract (English)
Synthesizing realistic and spatially precise anomalies is essential for enhancing the robustness of industrial anomaly detection systems. While recent diffusion-based methods have demonstrated strong capabilities in modeling complex defect patterns, they often struggle with spatial controllability and fail to maintain fine-grained regional fidelity. To overcome these limitations, we propose SARD (Segmentation-Aware anomaly synthesis via Region-constrained Diffusion with discriminative mask Guidance), a novel diffusion-based framework specifically designed for anomaly generation. Our approach introduces a Region-Constrained Diffusion (RCD) process that preserves the background by freezing it and selectively updating only the foreground anomaly regions during the reverse denoising phase, thereby effectively reducing background artifacts. Additionally, we incorporate a Discriminative Mask Guidance (DMG) module into the discriminator, enabling joint evaluation of both global realism and local anomaly fidelity, guided by pixel-level masks. Extensive experiments on the MVTec-AD and BTAD datasets show that SARD surpasses existing methods in segmentation accuracy and visual quality, setting a new state-of-the-art for pixel-level anomaly synthesis.
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。