Image reconstruction-based anomaly detection models are widely explored in industrial visual inspection. However, existing models usually suffer from the trade-off between normal reconstruction fidelity and abnormal reconstruction distinguishability, which damages the performance. In this paper, we find that the above trade-off can be better mitigated by leveraging the distinct frequency biases between normal and abnormal reconstruction errors. To this end, we propose Frequency-aware Image Restoration (FAIR), a novel self-supervised image restoration task that restores images from their high-frequency components. It enables precise reconstruction of normal patterns while mitigating unfavorable generalization to anomalies. Using only a simple vanilla UNet, FAIR achieves state-of-the-art performance with higher efficiency on various defect detection datasets. Code: https://github.com/liutongkun/FAIR.

翻译：基于图像重构的异常检测模型在工业视觉检测中被广泛探索。然而，现有模型通常面临正常重构保真度与异常重构区分性之间的权衡，这损害了性能。在本文中，我们发现上述权衡可以通过利用正常与异常重构误差之间的频率偏差差异得到更好的缓解。为此，我们提出了频率感知图像恢复（FAIR），一种新颖的自监督图像恢复任务，该任务从图像的高频分量中恢复图像。它能够精确重构正常模式，同时抑制对异常的不良泛化。仅使用简单的普通UNet，FAIR在各种缺陷检测数据集上以更高效率实现了最先进的性能。代码：https://github.com/liutongkun/FAIR。