Computing Visual Correspondence with Occlusions via Graph Cuts

Authors:
Vladimir Kolmogorov;Ramin Zabih
Affiliations:
-;-
Venue:
Computing Visual Correspondence with Occlusions via Graph Cuts
Year:
2001

Citing 0
Cited 4

Stereo Matching Using Belief Propagation

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Surface Reconstruction Method Using Global Graph Cut Optimization

International Journal of Computer Vision
A progressive edge-based stereo correspondence method

ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part I
Reliable depth map regeneration via a novel omnidirectional stereo sensor

ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

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 two new methods which properly address occlusions, while preserving the advantages of graph cut algorithms. We give experimental results for stereo as well as motion, which demonstrate that our methods perform well both at detecting occlusions and computing disparities.