Abstract A novel adaptive and patch-based approach is proposed for image regularization and representation. The method is unsupervised and based on a pointwise selection of small image patches of fixed size in the variable neighborhood of each pixel. The main idea is to associate with each pixel the weighted sum of data points within an adaptive neighborhood and to use image patches to take into account complex spatial interactions in images. In this paper, we consider the problem of the adaptive neighborhood selection in a manner that it balances the accuracy of the estimator and the stochastic error, at each spatial position. Moreover, we propose a practical algorithm with no hidden parameter for image regularization that uses no library of image patches and no training algorithm. The method is applied to both artificially corrupted and real images and the performance is very close, and in some cases even surpasses, to that of the best published denoising methods.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Unsupervised Patch-Based Image Regularization and Representation


    Beteiligte:


    Erscheinungsdatum :

    2006-01-01


    Format / Umfang :

    13 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Unsupervised Patch-Based Image Regularization and Representation

    Kervrann, C. / Boulanger, J. | British Library Conference Proceedings | 2006


    Adaptive regularization in image restoration by unsupervised learning

    Wong, H.-S. / Guan, L. | British Library Online Contents | 1998


    Convolutional Patch Representations for Image Retrieval: An Unsupervised Approach

    Paulin, M. / Mairal, J. / Douze, M. et al. | British Library Online Contents | 2017


    Truly Unsupervised Image-to-Image Translation with Contrastive Representation Learning

    Hong, Zhiwei / Feng, Jianxing / Jiang, Tao | British Library Conference Proceedings | 2023


    Local Adaptivity to Variable Smoothness for Exemplar-Based Image Regularization and Representation

    Kervrann, C. / Boulanger, J. r. | British Library Online Contents | 2008