Computing visual correspondence with occlusions using graph cuts
Top Cited Papers
- 13 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 508-515
- https://doi.org/10.1109/iccv.2001.937668
Abstract
Several new algorithms for visual correspondence based on graph cuts have recently been developed. While these methods give very strong results in practice, they do not handle occlusions properly. Specifically, they treat the two input images asymmetrically, and they do not ensure that a pixel corresponds to at most one pixel in the other image. In this paper, we present a new method which properly addresses occlusions, while preserving the advantages of graph cut algorithms. We give experimental results for stereo as well as motion, which demonstrate that our method performs well both at detecting occlusions and computing disparities.Keywords
This publication has 13 references indexed in Scilit:
- An Experimental Comparison of Min-cut/Max-flow Algorithms for Energy Minimization in VisionPublished by Springer Nature ,2001
- An Experimental Comparison of Stereo AlgorithmsPublished by Springer Nature ,2000
- Large Occlusion StereoInternational Journal of Computer Vision, 1999
- Fast approximate energy minimization via graph cutsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- A pixel dissimilarity measure that is insensitive to image samplingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1998
- Occlusions, discontinuities, and epipolar lines in stereoPublished by Springer Nature ,1998
- Occlusions and binocular stereoInternational Journal of Computer Vision, 1995
- 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
- Some generalized order-disorder transformationsMathematical Proceedings of the Cambridge Philosophical Society, 1952