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

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

13 Sep 2023arXiv:2309.07068archive 2025-07-28

Tongkun Liu, Bing Li, Xiao Du, Bingke Jiang, Leqi Geng, Feiyang Wang, Zhuo Zhao

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.

Paper PDF Code

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

liutongkun/fair officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly Detection Defect Detection Image Reconstruction Image Restoration

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Anomaly Detection	MVTec AD	FAIR	Detection AUROC	98.6	#55 of 148	Archive leaderboard	report
Anomaly Detection	MVTec AD	FAIR	Segmentation AUPRO	94.0	#55 of 148	Archive leaderboard	report
Anomaly Detection	MVTec AD	FAIR	Segmentation AUROC	98.2	#55 of 148	Archive leaderboard	report
Anomaly Detection	VisA	FAIRnoDTD	Detection AUROC	97.1	#17 of 50	Archive leaderboard	report
Anomaly Detection	VisA	FAIRnoDTD	Segmentation AUPRO (until 30% FPR)	91.2	#17 of 50	Archive leaderboard	report
Anomaly Detection	VisA	FAIRnoDTD	Segmentation AUROC	98.7	#17 of 50	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections