Removing Anomalies as Noises for Industrial Defect Localization

Fanbin Lu, Xufeng Yao, Chi-Wing Fu, Jiaya Jia; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 16166-16175


Unsupervised anomaly detection aims to train models with only anomaly-free images to detect and localize unseen anomalies. Previous reconstruction-based methods have been limited by inaccurate reconstruction results. This work presents a denoising model to detect and localize the anomalies with a generative diffusion model. In particular, we introduce random noise to overwhelm the anomalous pixels and obtain pixel-wise precise anomaly scores from the intermediate denoising process. We find that the KL divergence of the diffusion model serves as a better anomaly score compared with the traditional RGB space score. Furthermore, we reconstruct the features from a pre-trained deep feature extractor as our feature level score to improve localization performance. Moreover, we propose a gradient denoising process to smoothly transform an anomalous image into a normal one. Our denoising model outperforms the state-of-the-art reconstruction-based anomaly detection methods for precise anomaly localization and high-quality normal image reconstruction on the MVTec-AD benchmark.

Related Material

@InProceedings{Lu_2023_ICCV, author = {Lu, Fanbin and Yao, Xufeng and Fu, Chi-Wing and Jia, Jiaya}, title = {Removing Anomalies as Noises for Industrial Defect Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16166-16175} }