Stefan Roth

Assistant Professor, Department of Computer Science, TU Darmstadt

Sample menu:

• Home
• Publications
• Group
• Research
• Fields of Experts
• Denoising results
• Inpainting results
• Downloads
• Optical Flow
• Code
• Teaching
• Bio & CV
• Contact

Image data for training and testing

Note: The image data available here is provided for research and educational purposes only. The copyright and distribution terms of the original copyright holder apply.

Training data. We used a subset of the training images of the Berkeley Segmentation Database in order to train the FoE model. This database is itself a subset of the Corel image database.

• Download images from UC Berkeley website: Berkeley Segmentation Database images
• List of file names of training images used [txt, 1kB]
• Image patches used for training as MATLAB V6 matrix [mat, 3.43MB], [mat.gz, 1.43MB]

Test data for denoising. We used a subset of the test section of the Berkeley Segmentation Database to evaluate the denoising performance of the trained FoE model. We also measured the denoising performance on a standard set of images commonly used in the image processing community (Lena, Boats, etc.).

• Download images from UC Berkeley website: Berkeley Segmentation Database images (same file as for training images)
• List of file names of test images used [txt, 1kB]
• Standard test image set available from Javier Portilla's website.

Test data for inpainting. The images we used for image inpainting are available from Marcelo Bertalmío's website.

Example Code and Models

Note: The code and model data provided here underlies the copyright and licensing terms of Brown University. The code and data may be used for non-commercial purposes only. See the licensing terms included in the source package for more details.

We have a set of MATLAB functions available that illustrate how to use the Fields of Experts model for image denoising and image inpainting. The package includes trained FoE models with cliques of size 3x3 (with 8 filters) and 5x5 (with 24 filters). Each MATLAB function comes with a brief documentation (type "help foe_demo" for an overview). Please also see the included README file.

• Source and data package (version 1.0, 06/09/2005) [tar.gz, 368kB], [zip, 380kB]

Please send comments and questions to .

Detailed package contents:

• Trained FoE models (3x3 with 8 filters, 5x5 with 24 filters).
• Code to compute the log density of an image under the FoE model.
• Code to compute the gradient of the log density with respect to an image.
• Code for image denoising with denoising demo and example images.
• Code for image inpainting with image inpainting demo and example images.

© 2010 Stefan Roth