title | authors | fieldsOfStudy | meta_key | numCitedBy | reading_status | ref_count | tags | urls | venue | year | ||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision |
|
|
2004-an-experimental-comparison-of-min-cut-max-flow-algorithms-for-energy-minimization-in-vision |
3581 |
TBD |
58 |
|
IEEE Transactions on Pattern Analysis and Machine Intelligence |
2004 |
Minimum cut/maximum flow algorithms on graphs have emerged as an increasingly useful tool for exactor approximate energy minimization in low-level vision. The combinatorial optimization literature provides many min-cut/max-flow algorithms with different polynomial time complexity. Their practical efficiency, however, has to date been studied mainly outside the scope of computer vision. The goal of this paper is to provide an experimental comparison of the efficiency of min-cut/max flow algorithms for applications in vision. We compare the running times of several standard algorithms, as well as a new algorithm that we have recently developed. The algorithms we study include both Goldberg-Tarjan style "push -relabel" methods and algorithms based on Ford-Fulkerson style "augmenting paths." We benchmark these algorithms on a number of typical graphs in the contexts of image restoration, stereo, and segmentation. In many cases, our new algorithm works several times faster than any of the other methods, making near real-time performance possible. An implementation of our max-flow/min-cut algorithm is available upon request for research purposes.
- An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision.
- What energy functions can be minimized via graph cuts?
- A maximum-flow formulation of the N-camera stereo correspondence problem
- Computing geodesics and minimal surfaces via graph cuts
- An Optimal Graph Theoretic Approach to Data Clustering - Theory and Its Application to Image Segmentation
- Multi-camera Scene Reconstruction via Graph Cuts
- Random sampling in cut, flow, and network design problems
- Image segmentation by nested cuts
- Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images
- Stereo Without Epipolar Lines - A Maximum-Flow Formulation
- Segmentation by grouping junctions
- Graphcut textures - image and video synthesis using graph cuts
- A taxonomy and evaluation of dense two-frame stereo correspondence algorithms
- MRF solutions for probabilistic optical flow formulations
- Computing visual correspondence with occlusions using graph cuts
- Faster shortest-path algorithms for planar graphs
- Exact voxel occupancy with graph cuts
- Markov random fields with efficient approximations
- A new approach to the maximum flow problem
- Minimal Surfaces for Stereo
- Level set methods and dynamic implicit surfaces
- Large Occlusion Stereo
- Fusion of color, shading and boundary information for factory pipe segmentation
- A new Bayesian framework for object recognition
- Exact Optimization for Markov Random Fields with Convex Priors
- On Implementing the Push-Relabel Method for the Maximum Flow Problem
- Flow in Planar Graphs with Multiple Sources and Sinks
- On Implementing Push-Relabel Method for the Maximum Flow Problem
- Incorporating Spatial Priors into an Information Theoretic Approach for fMRI Data Analysis
- Geometric partial differential equations and image analysis
- Occlusions, Discontinuities, and Epipolar Lines in Stereo
- Exact Maximum A Posteriori Estimation for Binary Images
- Algorithm for solution of a problem of maximal flow in a network with power estimation
- Combinatorial optimization
- Level Set Methods and Fast Marching Methods
- Medical Image Computing and Computer-Assisted Intervention - MICCAI 2006, 9th International Conference, Copenhagen, Denmark, October 1-6, 2006, Proceedings, Part II
- Geometric Level Set Methods in Imaging, Vision, and Graphics
- An Experimental Comparison of Stereo Algorithms
- Fast approximate energy minimization via graph cuts