Bavarian AI Chair for Mathematical Foundations of Artificial Intelligence

Breadcrumb Navigation



Matlab Toolbox for Shearlets

ShearLab is a MATLAB library developed for processing two- and three dimensional data with a certain class of basis functions named shearlets. Such shearlet systems are particularly well adapted to represent anisotropic features (such as curves) that are often crucial in multidimensional data. The resulting representation has proven well-suited for image processing tasks such as inpainting, denoising or image separation. On this website we provide the full MATLAB code, a framework for numerical tests as well as general information on shearlets.

The ShearLab 3D Toolbox (Ver. 1.0) and older versions of ShearLab can be downloaded from Further, you can find ShearLab3D on the webpage of the Oberwolfach References on Mathematical Software here and on swMATH here.

This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.

If you have questions or comments, please contact Hector Andrade Loarca.



The CartoonX method was introduced in Cartoon Explanation of Image Classifiers - S.Kolek. et al. ECCV 2022 (oral presentation) as an explanation method for black-box image classifiers, such as deep neural networks. CartoonX extracts the piece-wise smooth relevant part of an image by optimizing an optimization mask in the wavelet domain of an image. The code repository for the CartoonX method (implemented in PyTorch) can be found at

If you have any questions contact Stefan Kolek.