When we take a picture through a window, the image we obtain is often a linear superposition of two images: the image of the scene beyond the window plus the image of the scene reflected by the window. Decomposing the single input image into two images is a massively ill-posed problem: in the absence of additional knowledge about the scene being viewed there is an infinite number of valid decompositions. We describe an algorithm that uses an extremely simple form of prior knowledge to perform the decomposition. Given a single image as input, the algorithm searches for a decomposition into two images that minimize the total amount of edges and comers. The search is performed using belief propagation on a patch representation of the image. We show that this simple prior is surprisingly powerful: our algorithm obtains "correct" separations on challenging reflection scenes using only a single image.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Separating reflections from a single image using local features


    Beteiligte:
    Levin, A. (Autor:in) / Zomet, A. (Autor:in) / Weiss, Y. (Autor:in)


    Erscheinungsdatum :

    01.01.2004


    Format / Umfang :

    717941 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Separating Reflections from a Single Image Using Local Features

    Levin, A. / Zomet, A. / Weiss, Y. et al. | British Library Conference Proceedings | 2004


    Separating linear features from textured backgrounds

    Pidaparthi, B. / Rao, R. M. / Peng, H. | British Library Online Contents | 2006



    Separating Reflection Components of Textured Surface Using a Single Image

    Tan, R. / Ikeuchi, K. / IEEE | British Library Conference Proceedings | 2003


    Separating reflections in human iris images for illumination estimation

    Huiqiong Wang, / Lin, S. / Xiaopei Liu, et al. | IEEE | 2005