Disparity component matching for visual correspondence
- 22 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 470-475
- https://doi.org/10.1109/cvpr.1997.609367
Abstract
We present a method for computing dense visual correspondence based on general assumptions about scene geometry. Our algorithm does not rely on correlation, and uses a variable region of support. We assume that images consist of a number of connected sets of pixels with the same disparity, which we call disparity components. Using maximum likelihood arguments, at each pixel we compute a small set of plausible disparities. A pixel is assigned a disparity d based on connected components of pixels, where each pixel in a component considers d to be plausible. Our implementation chooses the largest plausible disparity component; however, global contextual constraints can also be applied. While the algorithm was originally designed for visual correspondence, it can also be used for other early vision problems such as image restoration. It runs in a few seconds on traditional benchmark images with standard parameter settings, and gives quite promising results.Keywords
This publication has 7 references indexed in Scilit:
- Geometric constraints and stereo disparity computationInternational Journal of Computer Vision, 1996
- A Maximum Likelihood Stereo AlgorithmComputer Vision and Image Understanding, 1996
- A stereo matching algorithm with an adaptive window: theory and experimentPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Computational framework for determining stereo correspondence from a set of linear spatial filtersImage and Vision Computing, 1992
- Computational vision and regularization theoryNature, 1985
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1984
- Determining optical flowArtificial Intelligence, 1981