High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis

Abstract

We propose a novel method for Zero-Shot Anomaly Localization that leverages a bidirectional mapping derived from the 1-dimensional Wasserstein Distance. The proposed approach allows pinpointing the anomalous regions in a texture with increased precision by aggregating the contribution of a pixel to the errors of all nearby patches. We validate our solution on several datasets and obtain more than a 40% reduction in error over the previous state of the art on the MVTec AD dataset in a zero-shot setting.

Citation Style:    Display Alpha ACM SIGGRAPH IEEEtran Publication

High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis. Andrei-Timotei Ardelean, Tim Weyrich. arXiv, 2304.06433, 12 pages, April 2023.Andrei-Timotei Ardelean and Tim Weyrich. High-fidelity zero-shot texture anomaly localization using feature correspondence analysis, 2023.Ardelean, A.-T., and Weyrich, T., 2023. High-fidelity zero-shot texture anomaly localization using feature correspondence analysis.A.-T. Ardelean and T. Weyrich, “High-fidelity zero-shot texture anomaly localization using feature correspondence analysis,” 2023. PDF (12 MB) Low-res PDF (3.6 MB) BibTeX

Acknowledgments

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 956585 (PRIME ITN).