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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Fields of Experts: a framework for learning image priors


    Contributors:
    Roth, S. (author) / Black, M.J. (author)


    Publication date :

    2005-01-01


    Size :

    474476 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Optimal Learning High-Order Markov Random Fields Priors of Colour Image

    Zhang, Ke / Jin, Huidong / Fu, Zhouyu et al. | Springer Verlag | 2007


    Visualizing Image Priors

    Shaham, Tamar Rott / Michaeli, Tomer | British Library Conference Proceedings | 2016


    Image-Modeling Gibbs Priors

    Levitan, E. / Chan, M. / Herman, G. T. | British Library Online Contents | 1995


    Fields of Experts

    Roth, S. / Black, M. J. | British Library Online Contents | 2009


    Image-Based Rendering Using Image-Based Priors

    Fitzgibbon, A. / Wexler, Y. / Zisserman, A. | British Library Online Contents | 2005