![[High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis]](ardelean2024highfidelity-400x300.jpg)
FAU > Technische Fakultät > Informatik > Lehrstuhl 15 (Digital Reality)
Andrei-Timotei Ardelean, Tim Weyrich
Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)
We propose a novel method for Zero-Shot Anomaly Localization on textures. The task refers to identifying abnormal regions in an otherwise homogeneous image. To obtain a high-fidelity localization, we leverage a bijective mapping derived from the 1-dimensional Wasserstein Distance. As opposed to using holistic distances between distributions, the proposed approach allows pinpointing the non-conformity of a pixel in a local context with increased precision. By aggregating the contribution of the pixel to the errors of all nearby patches, we obtain a reliable anomaly score estimate. 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.
Andrei-Timotei Ardelean, Tim Weyrich. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 1134–1144, January 2024.Andrei-Timotei Ardelean and Tim Weyrich. High-fidelity zero-shot texture anomaly localization using feature correspondence analysis. In Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), January 2024.Ardelean, A.-T., and Weyrich, T. 2024. High-fidelity zero-shot texture anomaly localization using feature correspondence analysis. In Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).A.-T. Ardelean and T. Weyrich, “High-fidelity zero-shot texture anomaly localization using feature correspondence analysis,” in Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan. 2024. |
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).
