A comparative study of energy minimization methods for Markov random fields

R. Szeliski, R. Zabih, D. Scharstein, O. Veksler, V. Kolmogorov, A. Agarwala, M. Tappen, C. Rother, in:, Springer, 2006, pp. 16–29.

Download
No fulltext has been uploaded. References only!

Conference Paper | Published
Author
Szeliski, Richard S; Zabih, Ramin; Scharstein, Daniel; Veksler, Olga; Kolmogorov, VladimirIST Austria; Agarwala, Aseem; Tappen, Marshall F; Rother, Carsten
Abstract
One of the most exciting advances in early vision has been the development of efficient energy minimization algorithms. Many early vision tasks require labeling each pixel with some quantity such as depth or texture. While many such problems can be elegantly expressed in the language of Markov Random Fields (MRF's), the resulting energy minimization problems were widely viewed as intractable. Recently, algorithms such as graph cuts and loopy belief propagation (LBP) have proven to be very powerful: for example, such methods form the basis for almost all the top-performing stereo methods. Unfortunately, most papers define their own energy function, which is minimized with a specific algorithm of their choice. As a result, the tradeoffs among different energy minimization algorithms are not well understood. In this paper we describe a set of energy minimization benchmarks, which we use to compare the solution quality and running time of several common energy minimization algorithms. We investigate three promising recent methods - graph cuts, LBP, and tree-reweighted message passing - as well as the well-known older iterated conditional modes (ICM) algorithm. Our benchmark problems are drawn from published energy functions used for stereo, image stitching and interactive segmentation. We also provide a general-purpose software interface that allows vision researchers to easily switch between optimization methods with minimal overhead. We expect that the availability of our benchmarks and interface will make it significantly easier for vision researchers to adopt the best method for their specific problems. Benchmarks, code, results and images are available at http://vision.middlebury.edu/MRF.
Publishing Year
Date Published
2006-05-03
Volume
3952
Page
16 - 29
Conference
ECCV: European Conference on Computer Vision
IST-REx-ID

Cite this

Szeliski R, Zabih R, Scharstein D, et al. A comparative study of energy minimization methods for Markov random fields. In: Vol 3952. Springer; 2006:16-29. doi:10.1007/11744047_2
Szeliski, R., Zabih, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwala, A., … Rother, C. (2006). A comparative study of energy minimization methods for Markov random fields (Vol. 3952, pp. 16–29). Presented at the ECCV: European Conference on Computer Vision, Springer. https://doi.org/10.1007/11744047_2
Szeliski, Richard, Ramin Zabih, Daniel Scharstein, Olga Veksler, Vladimir Kolmogorov, Aseem Agarwala, Marshall Tappen, and Carsten Rother. “A Comparative Study of Energy Minimization Methods for Markov Random Fields,” 3952:16–29. Springer, 2006. https://doi.org/10.1007/11744047_2.
R. Szeliski et al., “A comparative study of energy minimization methods for Markov random fields,” presented at the ECCV: European Conference on Computer Vision, 2006, vol. 3952, pp. 16–29.
Szeliski R, Zabih R, Scharstein D, Veksler O, Kolmogorov V, Agarwala A, Tappen M, Rother C. 2006. A comparative study of energy minimization methods for Markov random fields. ECCV: European Conference on Computer Vision vol. 3952. 16–29.
Szeliski, Richard, et al. A Comparative Study of Energy Minimization Methods for Markov Random Fields. Vol. 3952, Springer, 2006, pp. 16–29, doi:10.1007/11744047_2.

Link(s) to Main File(s)
Access Level
Restricted Closed Access

Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar