FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection

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.

基于图像重构的异常检测模型在工业视觉检测领域得到了广泛研究与应用探索。然而，现有模型往往面临正常样本重构保真度与异常样本重构可区分性之间的权衡难题，这会对模型整体性能造成损害。