Computing visual correspondence with occlusions using graph cuts Conference Paper

Author(s): Kolmogorov, Vladimir; Zabih, Ramin
Title: Computing visual correspondence with occlusions using graph cuts
Abstract: Several new algorithms for visual correspondence based on graph cuts [7, 14, 17] 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: Algorithms; computational complexity; Image processing; Optimization; Computer vision; Computational methods
Conference Title: ICCV: International Conference on Computer Vision
Volume: 2
Conference Dates: July 7-14, 2001
Conference Location: Vancouver, BC, USA
Publisher: IEEE  
Date Published: 2001-08-01
Start Page: 508
End Page: 515
DOI: 10.1109/ICCV.2001.937668
Open access: no
IST Austria Authors
Related IST Austria Work