In this paper, we propose a novel method for solving single-image super-resolution problems. Given a low-resolution image as input, we recover its high-resolution counterpart using a set of training examples. While this formulation resembles other learning-based methods for super-resolution, our method has been inspired by recent manifold teaming methods, particularly locally linear embedding (LLE). Specifically, small image patches in the lowand high-resolution images form manifolds with similar local geometry in two distinct feature spaces. As in LLE, local geometry is characterized by how a feature vector corresponding to a patch can be reconstructed by its neighbors in the feature space. Besides using the training image pairs to estimate the high-resolution embedding, we also enforce local compatibility and smoothness constraints between patches in the target high-resolution image through overlapping. Experiments show that our method is very flexible and gives good empirical results.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Super-resolution through neighbor embedding


    Beteiligte:
    Hong Chang, (Autor:in) / Dit-Yan Yeung, (Autor:in) / Yimin Xiong, (Autor:in)


    Erscheinungsdatum :

    01.01.2004


    Format / Umfang :

    733489 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Super-Resolution through Neighbor Embedding

    Chang, H. / Yeung, D.-Y. / Xiong, Y. et al. | British Library Conference Proceedings | 2004


    Adaptive Neighbor Embedding for Efficient Stereo Matching

    Chong, Ai-Xin / Yin, Hui / Wan, Jin et al. | IEEE | 2024


    Super-Resolution Imaging

    Pillman, B.H. | British Library Online Contents | 2013


    Robust Super-Resolution

    Zomet, A. / Rav-Acha, A. / Peleg, S. et al. | British Library Conference Proceedings | 2001


    Robust super-resolution

    Zomet, A. / Rav-Acha, A. / Peleg, S. | IEEE | 2001