Fields of Experts: a framework for learning image priors

• Published in: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 2; pp. 860 - 867 vol. 2
• Main Authors: Roth, S., Black, M.J.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2005
• Subjects: Computer science; Image coding; Image databases; Image denoising; Machine vision; Markov random fields; Nonlinear filters; PSNR; Statistics; Training data
• DOI: 10.1109/CVPR.2005.160
• ISBN: 0769523722; 9780769523729
• ISSN: 1063-6919

We develop a framework for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks. The approach extends traditional Markov random field (MRF) models by learning potential functions over extended pixel neighborhoods. Field potentials are modeled using a Products-of-Experts framework that exploits nonlinear functions of many linear filter responses. In contrast to previous MRF approaches all parameters, including the linear filters themselves, are learned from training data. We demonstrate the capabilities of this Field of Experts model with two example applications, image denoising and image inpainting, which are implemented using a simple, approximate inference scheme. While the model is trained on a generic image database and is not tuned toward a specific application, we obtain results that compete with and even outperform specialized techniques.