There has been a lot of activity recently surrounding the reconstruction of photorealistic 3D scenes and high-resolution images from video sequences. We present some of our recent work in this area, which is based on the registration of multiple images (views) in a projective framework. Unlike most other techniques, we do not rely on special features to form a projective basis. Instead, we directly solve a least-squares estimation problem in the unknown structure and motion parameters, which leads to statistically optimal estimates. We discuss algorithms for both constructing planar and panoramic mosaics, and for projective depth recovery. We also speculate about the ultimate usefulness of projective approaches to visual scene reconstruction.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Direct methods for visual scene reconstruction


    Beteiligte:
    Szeliski, R. (Autor:in) / Sing Bing Kang (Autor:in)


    Erscheinungsdatum :

    01.01.1995


    Format / Umfang :

    1436281 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Direct Methods for Visual Scene Reconstruction

    Szeliski, R. / Sing Bing Kang / IEEE et al. | British Library Conference Proceedings | 1995


    Instant Scene Modeler for Crime Scene Reconstruction

    Se, S. / Jasiobedzki, P. | IEEE | 2005


    TRAFFIC ANOMALY SCENE RECONSTRUCTION

    PASCH FREDERIK / BUERKLE CORNELIUS / OBORIL FABIAN | Europäisches Patentamt | 2024

    Freier Zugriff

    Image reconstruction from an accident's scene

    Wang,Y.W. / Ting,K.L. / Huang,Y.P. et al. | Kraftfahrwesen | 1996


    Image Reconstruction from An Accident's Scene

    Wang, Y.-W. / Ting, K.-L. / Huang, Y.-P. | British Library Conference Proceedings | 1996