In this paper, we propose a novel patch-based face hallucination framework, which employs a dual model to hallucinate different components associated with one facial image. Our model is based on a statistical learning approach: associative learning. It suffices to learn the dependencies between low-resolution image patches and their high-resolution ones with a new concept hidden parameter space as a bridge to connect those patches with different resolutions. To compensate higher frequency information of images, we present a dual associative learning algorithm for orderly inferring main components and high frequency components of faces. The patches can be finally integrated to form a whole high-resolution image. Experiments demonstrate that our approach does render high quality superresolution faces.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Face hallucination through dual associative learning


    Beteiligte:
    Wei Liu, (Autor:in) / Dahua Lin, (Autor:in) / Xiaoou Tang, (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    367090 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Face Hallucination through Dual Associative Learning

    Liu, W. / Lin, D. / Tang, X. | British Library Conference Proceedings | 2005


    Face Hallucination: Theory and Practice

    Liu, C. / Shum, H. Y. / Freeman, W. T. | British Library Online Contents | 2007


    A Comprehensive Survey to Face Hallucination

    Wang, N. / Tao, D. / Gao, X. et al. | British Library Online Contents | 2014



    Hallucination of facial details from degraded images using 3D face models

    Schumacher, M. / Piotraschke, M. / Blanz, V. | British Library Online Contents | 2015