# A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors

@article{Szeliski2008ACS, title={A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors}, author={R. Szeliski and R. Zabih and D. Scharstein and Olga Veksler and V. Kolmogorov and A. Agarwala and M. Tappen and C. Rother}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, year={2008}, volume={30}, pages={1068-1080} }

Among the most exciting advances in early vision has been the development of efficient energy minimization algorithms for pixel-labeling tasks such as depth or texture computation. It has been known for decades that such problems can be elegantly expressed as Markov random fields, yet the resulting energy minimization problems have been widely viewed as intractable. Algorithms such as graph cuts and loopy belief propagation (LBP) have proven to be very powerful: For example, such methods form… Expand

#### Figures, Tables, and Topics from this paper

#### 1,031 Citations

Fast Approximate Energy Minimization with Label Costs

- Computer Science
- 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
- 2010

The main algorithmic contribution is an extension of α-expansion that also optimizes “label costs” with well-characterized optimality bounds, which has a natural interpretation as minimizing description length (MDL) and sheds light on classical algorithms like K-means and expectation-maximization (EM). Expand

A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems

- Computer Science
- 2013 IEEE Conference on Computer Vision and Pattern Recognition
- 2013

This study presents an empirical comparison of 24 state-of-art techniques on a corpus of 2,300 energy minimization instances from 20 diverse computer vision applications and suggests that polyhedral methods and integer programming solvers are competitive in terms of runtime and solution quality over a large range of model types. Expand

Graph-based variational optimization and applications in computer vision. (Optimisation variationnelle discrète et applications en vision par ordinateur)

- Mathematics, Computer Science
- 2011

This work develops a discrete yet isotropic energy minimization formulation for the continuous maximum flow problem that prevents metrication errors, and develops a globally optimal optimization method, named "Power watershed''. Expand

Applying convex optimization techniques to energy minimization problems in computer vision

- Mathematics
- 2008

Energy minimization is an important technique in computer vision that has been applied to practically all early vision problems. Several methods have been proposed to solve the problem and to date,… Expand

Alphabet SOUP: A framework for approximate energy minimization

- 2009 IEEE Conference on Computer Vision and Pattern Recognition
- 2009

A general framework for finding approximate MAP solutions of arbitrary energy functions by iteratively solving subproblems over a reduced state-space and provides a theoretical guarantee on the quality of the solution when the inner loop of the algorithm is solved exactly. Expand

Alphabet SOUP: A framework for approximate energy minimization

- Computer Science
- CVPR
- 2009

A general framework for finding approximate MAP solutions of arbitrary energy functions by iteratively solving subproblems over a reduced state-space and provides a theoretical guarantee on the quality of the solution when the inner loop of the algorithm is solved exactly. Expand

Gentle ICM energy minimization for Markov random fields with smoothness-based priors

- Computer Science
- Journal of Real-Time Image Processing
- 2012

It is demonstrated that the modified ICM can be competitive to other optimization algorithms on a set of vision problems such as stereo depth estimation, image segmentation, image denoising and inpainting. Expand

A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems

- Computer Science
- International Journal of Computer Vision
- 2015

An empirical comparison of more than 27 state-of-the-art optimization techniques on a corpus of 2453 energy minimization instances from diverse applications in computer vision suggests that polyhedral methods and integer programming solvers are competitive in terms of runtime and solution quality over a large range of model types. Expand

Efficient Loopy Belief Propagation Using the Four Color Theorem

- Computer Science, Mathematics
- Advanced Topics in Computer Vision
- 2013

It is shown how to reduce the computational complexity of belief propagation by applying the Four Color Theorem to limit the maximum number of labels in the underlying image segmentation to at most four. Expand

Efficient Inference and Learning for Computer Vision Labelling Problems

- Computer Science
- 2010

A substantial improvement in the running time of various labelling problems such as, interactive image and video segmentation, object recognition, stereo matching is demonstrated and an accurate and efficient learning method is presented that is widely applicable. Expand

#### References

SHOWING 1-10 OF 66 REFERENCES

Comparison of Energy Minimization Algorithms for Highly Connected Graphs

- Computer Science
- ECCV
- 2006

This paper proposes the problem of stereo with occlusions as a new test bed for minimization algorithms and shows that sophisticated implementations of BP and TRW have the same time and memory complexity as that of 4-connected grid-graph stereo. Expand

Efficient Belief Propagation for Early Vision

- Mathematics, Computer Science
- Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
- 2004

Algorithmic techniques are presented that substantially improve the running time of the loopy belief propagation approach and reduce the complexity of the inference algorithm to be linear rather than quadratic in the number of possible labels for each pixel, which is important for problems such as image restoration that have a large label set. Expand

Globally optimal solutions for energy minimization in stereo vision using reweighted belief propagation

- Mathematics, Computer Science
- Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
- 2005

It is shown that for standard benchmark stereo pairs, the global optimum can be found in about 30 minutes using a variant of the belief propagation (BP) algorithm. Expand

An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision

- Computer Science
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2004

The goal of this paper is to provide an experimental comparison of the efficiency of min-cut/max flow algorithms for applications in vision, comparing the running times of several standard algorithms, as well as a new algorithm that is recently developed. Expand

Graph Cut Based Optimization for MRFs with Truncated Convex Priors

- Mathematics, Computer Science
- 2007 IEEE Conference on Computer Vision and Pattern Recognition
- 2007

This work develops several optimization algorithms for truncated convex priors, which imply piecewise smoothness assumption, and develops new "range" moves which act on a larger set of labels than the expansion and swap algorithms. Expand

Optimizing Binary MRFs via Extended Roof Duality

- Mathematics, Computer Science
- 2007 IEEE Conference on Computer Vision and Pattern Recognition
- 2007

An efficient implementation of the "probing" technique is discussed, which simplifies the MRF while preserving the global optimum, and a new technique which takes an arbitrary input labeling and tries to improve its energy is presented. Expand

Convergent Tree-Reweighted Message Passing for Energy Minimization

- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2006

This paper develops a modification of the recent technique proposed by Wainwright et al. (Nov. 2005), called sequential tree-reweighted message passing, which outperforms both the ordinary belief propagation and tree- reweighted algorithm in both synthetic and real problems. Expand

Comparison of graph cuts with belief propagation for stereo, using identical MRF parameters

- Mathematics, Computer Science
- Proceedings Ninth IEEE International Conference on Computer Vision
- 2003

This work compares the belief propagation algorithm and the graph cuts algorithm on the same MRF's, which have been created for calculating stereo disparities, and finds that the labellings produced by the two algorithms are comparable. Expand

What energy functions can be minimized via graph cuts?

- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2004

This work gives a precise characterization of what energy functions can be minimized using graph cuts, among the energy functions that can be written as a sum of terms containing three or fewer binary variables. Expand

An efficient algorithm for image segmentation, Markov random fields and related problems

- Mathematics, Computer Science
- JACM
- 2001

This paper discusses Markov random fields problems in the context of a representative application---the image segmentation problem and presents an algorithm that solves the problem in polynomial time when the deviation function is convex and separation function is linear. Expand