Epiflow Based Stereo Fusion

  • Hongsheng Zhang
  • Shahriar Negahdaripour
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4477)


3-D reconstruction from images sequences has been the center topic of computer vision. Real-time applications call for causal processing of stereo sequences, as they are acquired, covering different regions of the scene. The first step is to compute the current stereo disparity, and recursive map building often requires fusing with the previous estimate. In this paper, the epiflow framework [1], originally proposed for establishing matches among stereo feature pairs is generalized to devise an iterative causal algorithm for stereo disparity map fusion. In the context of disparity fusion, quadruplet correspondence of the epiflow tracking algorithm becomes reminiscent of the “closest point” of the 3-D ICP algorithm. Unlike ICP, the 2-D epiflow framework permits incorporating both photometric and geometrical constraints, estimation of the stereo rig motion as supplementary information, as well as identifying local inconsistencies between the two disparity maps. Experiments with real data validate the proposed approach, and improved converge compared to the ICP algorithm.


Iterative Close Point Stereo Match Stereo Pair Epipolar Geometry Iterative Close Point Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Zhang, H., Negahdaripour, S.: Epiflow quadruplet matching:enforcing epipolar geometry for spatio-temporal stereo correspondences. In: WACV, Breckenridge, CO (January 2005)Google Scholar
  2. 2.
    Zhang, H., Negahdaripour, S.: Fast and robust progressive stereo reconstruction via symmetry guided fusion. In: Proc. Oceans ’05 Europe, Brest, France (June 2005)Google Scholar
  3. 3.
    Besl, P.J., McKay, N.: A method for registration of 3D shapes. IEEE Trans. Pattern Anal. Mach. Intell 14(2), 239–256 (1992)CrossRefGoogle Scholar
  4. 4.
    Zhang, Z.: On local matching of free-form curves. In: Proc. British Machine Vision Conference, pp. 347–356, Leeds (1992)Google Scholar
  5. 5.
    Duda, R., Hart, P.: Pattern Classification and Scene Analysis. Wiley, Chichester (1973)zbMATHGoogle Scholar
  6. 6.
    Press, W., Flannery, B., Teukolsky, S., Vetterling, W.: Numerical Recipes in C. Cambridge University Press, Cambridge (1988)zbMATHGoogle Scholar
  7. 7.
    Cheng, Y.: Mean shift, mode seeking, and clustering. IEEE Trans. Pattern Anal. Machine Intell. 17(8), 790–799 (1995)CrossRefGoogle Scholar
  8. 8.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Machine Intell. 24(5), 603–619 (2002)CrossRefGoogle Scholar
  9. 9.
    Fitzgibbon, A.: Robust registration of 2D and 3D point sets. In: BMVC (2001)Google Scholar
  10. 10.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision 47(1), 7–42 (2002)zbMATHCrossRefGoogle Scholar
  11. 11.
    Chen, Q., Medioni, G.: A volumetric stereo matching method: Application to image-based modeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 29–34, Colorado (June 1999)Google Scholar
  12. 12.
    Lhuillier, M., Quan, L.: Match propogation for image-based modeling and rendering. IEEE Trans. Pattern Anal. Mach. Intell. 24(8), 1140–1146 (2002)CrossRefGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Hongsheng Zhang
    • 1
  • Shahriar Negahdaripour
    • 2
  1. 1.Mako Surgical Corp., Ft. Lauderdale FL 33317USA
  2. 2.University of Miami, Coral Gables, FL 33124USA

Personalised recommendations