In this paper, we propose a method for jointly computing optical flow and segmenting video while accounting for mixed pixels (matting). Our method is based on statistical modeling of an image pair using constraints on appearance and motion. Segments are viewed as overlapping regions with fractional (/spl alpha/) contributions. Bidirectional motion is estimated based on spatial coherence and similarity of segment colors. Our model is extended to video by chaining the pairwise models to produce a joint probability distribution to be maximized. To make the problem more tractable, we factorize the posterior distribution and iteratively minimize its parts. We demonstrate our method on frame interpolation.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Consistent segmentation for optical flow estimation


    Contributors:
    Zitnick, C.W. (author) / Jojic, N. (author) / Sing Bing Kang, (author)


    Publication date :

    2005-01-01


    Size :

    847379 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Consistent Segmentation for Optical Flow Estimation

    Zitnick, C. / Jojic, N. / Kang, S. et al. | British Library Conference Proceedings | 2005


    Consistent link flow estimation from counts

    van Zuylen, Henk J. / Branston, David M. | Elsevier | 1981




    Spatially Consistent 3D Motion Segmentation

    Schindler, K. | British Library Conference Proceedings | 2005