Non-parametric Patch based Video Matting

  title={Non-parametric Patch based Video Matting},
  author={Muhammad Sarim and Adrian Hilton and Jean-Yves Guillemaut},
In computer vision, matting is the process of accurate foreground estimation in images and videos. In this paper we presents a novel patch based approach to video matting relying on non-parametric statistics to represent image variations in appearance. This overcomes the limitation of parametric algorithms which only rely on strong colour correlation between the nearby pixels. Initially we construct a clean background by utilising the foreground object’s movement across the background. For a… CONTINUE READING


Publications citing this paper.


Publications referenced by this paper.

Alpha channel estimation in high resolution images and image sequences

  • Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • 2001

A bayesian approach to digital matting

B. Curless, D. H. Salesin, R. Szeliski

    A closed form solution to natural image matting

    D. Lischinski Levin, Y. Weiss
    • Computer Vision and Pattern Recognition , IEEE Computer Society Conference on ACM SIGGRAPH ’ 84 : Proceedings of the 11 th annual conference on Computer graphics and interactive techniques

    Poisson matting

    J. Jia J. Sun, C. K. Tang, H. Y. Shum
    • ACM Transactions on Graphics