International Journal of Computer Vision

, 82:205

Fields of Experts

Authors

    • Department of Computer ScienceTU Darmstadt
  • Michael J. Black
    • Department of Computer ScienceBrown University
Article

DOI: 10.1007/s11263-008-0197-6

Cite this article as:
Roth, S. & Black, M.J. Int J Comput Vis (2009) 82: 205. doi:10.1007/s11263-008-0197-6

Abstract

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 provides a practical method for learning high-order Markov random field (MRF) models with potential functions that extend over large pixel neighborhoods. These clique potentials are modeled using the Product-of-Experts framework that uses non-linear 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 specialized techniques.

Keywords

Markov random fields Low-level vision Image modeling Learning Image restoration

Copyright information

© Springer Science+Business Media, LLC 2009