International Journal of Computer Vision

, Volume 28, Issue 2, pp 155–174

Stereo Matching with Nonlinear Diffusion

  • Daniel Scharstein
  • Richard Szeliski

DOI: 10.1023/A:1008015117424

Cite this article as:
Scharstein, D. & Szeliski, R. International Journal of Computer Vision (1998) 28: 155. doi:10.1023/A:1008015117424


One of the central problems in stereo matching (and other image registration tasks) is the selection of optimal window sizes for comparing image regions. This paper addresses this problem with some novel algorithms based on iteratively diffusing support at different disparity hypotheses, and locally controlling the amount of diffusion based on the current quality of the disparity estimate. It also develops a novel Bayesian estimation technique, which significantly outperforms techniques based on area-based matching (SSD) and regular diffusion. We provide experimental results on both synthetic and real stereo image pairs.

stereo matching variable-sized support region nonlinear diffusion Bayesian estimation 

Copyright information

© Kluwer Academic Publishers 1998

Authors and Affiliations

  • Daniel Scharstein
    • 1
  • Richard Szeliski
    • 2
  1. 1.Department of Mathematics and Computer ScienceMiddlebury CollegeMiddlebury
  2. 2.Microsoft ResearchOne Microsoft WayRedmond

Personalised recommendations