We present a novel approach for establishing multiple-view feature correspondences along an unordered set of images taken from substantially different viewpoints. Several wide-baseline stereo (WBS) algorithms have appeared, the N-view case is largely unexplored. In this paper, an established WBS algorithm is used to extract and match features in pairs of views. The pairwise matches are first integrated into disjoint feature tracks, each representing a single physical surface patch in several views. By exploiting the interplay between the tracks, they are extended over more views, while unrelated image features are removed. Similarity and spatial relationships between the features are simultaneously used. The output consists of many reliable and accurate feature tracks, strongly connecting the input views. Applications include 3D reconstruction and object recognition. The proposed approach is not restricted to the particular choice of features and matching criteria. It can extend any method that provides feature correspondences between pairs of images.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Wide-baseline multiple-view correspondences


    Contributors:


    Publication date :

    2003-01-01


    Size :

    1121224 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Wide-Baseline Multiple-View Correspondences

    Ferrari, V. / Tuytelaars, T. / Van Gool, L. et al. | British Library Conference Proceedings | 2003


    Multiple-View Structure and Motion from Line Correspondences

    Bartoli, A. / Sturm, P. / IEEE | British Library Conference Proceedings | 2003



    Dense matching of multiple wide-baseline views

    Strecha, / Tuytelaars, / Van Gool, | IEEE | 2003


    Dense Matching of Multiple Wide-baseline Views

    Strecha, C. / Tuytelaars, T. / Van Gool, L. et al. | British Library Conference Proceedings | 2003