SARD: Segmentation-Aware Anomaly Synthesis via Region-Constrained Diffusion with Discriminative Mask Guidance
This work addresses the need for better anomaly synthesis to enhance industrial inspection systems, representing an incremental improvement over existing diffusion-based methods.
The paper tackled the problem of synthesizing realistic and spatially precise anomalies for industrial anomaly detection by proposing SARD, a diffusion-based framework that introduces region-constrained diffusion and discriminative mask guidance, resulting in state-of-the-art performance on MVTec-AD and BTAD datasets with improved segmentation accuracy and visual quality.
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.