LogCut - Efficient Graph Cut Optimization for Markov Random Fields

Markov Random Fields (MRFs) are ubiquitous in low- level computer vision. In this paper, we propose a new approach to the optimization of multi-labeled MRFs. Similarly to a-expansion it is based on iterative application of binary graph cut. However, the number of binary graph cuts required to comput...

Full description

Saved in:
Bibliographic Details
Published in2007 IEEE 11th International Conference on Computer Vision pp. 1 - 8
Main Authors Lempitsky, V., Rother, C., Blake, A.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2007
Subjects
Application software
Computer vision
Image motion analysis
Image restoration
Labeling
Markov random fields
Message passing
Optical computing
Partitioning algorithms
Stereo vision
Online AccessGet full text

Cover

More Information
Summary:Markov Random Fields (MRFs) are ubiquitous in low- level computer vision. In this paper, we propose a new approach to the optimization of multi-labeled MRFs. Similarly to a-expansion it is based on iterative application of binary graph cut. However, the number of binary graph cuts required to compute a labelling grows only logarithmically with the size of label space, instead of linearly. We demonstrate that for applications such as optical flow, image restoration, and high resolution stereo, this gives an order of magnitude speed-up, for comparable energies. Iterations are performed by "fusion" of solutions, done with QPBO which is related to graph cut but can deal with non-submodularity. At convergence, the method achieves optima on a par with the best competitors, and sometimes even exceeds them.
ISBN:1424416302
9781424416301
ISSN:1550-5499
2380-7504
DOI:10.1109/ICCV.2007.4408907