High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis
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 MVTec AD dataset in a zero-shot setting.
READ FULL TEXT