In this paper, we present a novel learning based framework for performing super-resolution using multiple images. We model the image as an undirected graphical model over image patches in which the compatibility functions are represented as non-parametric kernel densities which are learnt from training data. The observed images are translation rectified and stitched together onto a high resolution grid and the inference problem reduces to estimating unknown pixels in the grid. We solve the inference problem by using an extended version of the non-parametric belief propagation algorithm. We show experimental results on synthetic digit images and real face images from the ORL face dataset.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Non-parametric image super-resolution using multiple images


    Contributors:
    Gupta, M.D. (author) / Rajaram, S. (author) / Petrovic, N. (author) / Huang, T.S. (author)


    Publication date :

    2005-01-01


    Size :

    137365 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Non-Parametric Image Super-Resolution using Multiple Images

    Gupta, M. D. / Rajaram, S. / Petrovic, N. et al. | British Library Conference Proceedings | 2005


    Super-Resolution Image Restoration from Blurred Low-Resolution Images

    Ng, M. K. / Yau, A. C. | British Library Online Contents | 2005


    Multiple Sentinel-2 Images Super-Resolution with Google Earth Pro Images

    Liu, Shuai / Fonseca, Jose M. / Mora, Andre | IEEE | 2023



    Super-Resolution from Multiple Views Using Learnt Image Models

    Capel, D. / Zisserman, A. / IEEE | British Library Conference Proceedings | 2001