An Experimental Comparison of Min-cut/Max-flow Algorithms for Energy Minimization in Vision
Yuri Boykov,Vladimir Kolmogorov +1 more
- 03 Sep 2001
- pp 359-374
TL;DR: 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.
read more
Abstract: After [10, 15, 12, 2, 4] minimum cut/maximum flow algorithms on graphs emerged as an increasingly useful tool for exact or 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 energy minimization 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-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 interactive segmentation. In many cases our new algorithm works several times faster than any of the other methods making near real-time performance possible.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Computational TMA analysis and cell nucleus classification of renal cell carcinoma
Peter J. Schüffler,Thomas J. Fuchs,Cheng Soon Ong,Volker Roth,Joachim M. Buhmann +4 more
- 22 Sep 2010
TL;DR: Results show that classification accuracy, which is comparable to trained human experts, can be achieved by using support vector machines (SVM) with appropriate kernels, and provide evidence that the shape of cell nuclei increases the classification performance.
26
Novel view synthesis with residual error feedback for FTV
Hisayoshi Furihata,Tomohiro Yendo,Mehrdad Panahpour Tehrani,Toshiaki Fujii,Masayuki Tanimoto +4 more
TL;DR: A new method of DIBR using multi-view images acquired in a linear camera arrangement that improves virtual viewpoint images by predicting the residual errors and in the experiments, PSNR could be improved for few decibels compared with the conventional method.
26
Advances in visual computing: 12th international symposium, ISVC 2016 Las Vegas, NV, USA, december 12–14, 2016 proceedings, part II
George Bebis,Richard Boyle,Bahram Parvin,Darko Koracin,Ryan McMahan,Jason Jerald,Hui Zhang,Steven M. Drucker,Chandra Kambhamettu,Maha El Choubassi,Zhigang Deng,Mark Carlson +11 more
- 01 Jan 2014
TL;DR: This work gives an analysis of noise, as one of the most important degradations in 3D EM imaging, and proposes a Non-Local Means image restoration algorithm that exploits the derived noise characteristics.
$\ell _p$ ℓ p -Box ADMM: A Versatile Framework for Integer Programming
Baoyuan Wu,Bernard Ghanem +1 more
- 01 Jul 2019
TL;DR: This paper revisits the integer programming (IP) problem, and proposes a novel and versatile framework called Alternating Direction Method of Multipliers (ADMM), which significantly outperforms existing generic IP solvers both in runtime and objective.
26
•Posted Content
Incorporating Near-Infrared Information into Semantic Image Segmentation.
TL;DR: It is shown that adding NIR leads to improved performance for classes that correspond to a specific type of material in both outdoor and indoor scenes, and the results with respect to the physical properties of the NIR response are discussed.
References
A taxonomy and evaluation of dense two-frame stereo correspondence algorithms
TL;DR: This paper has designed a stand-alone, flexible C++ implementation that enables the evaluation of individual components and that can easily be extended to include new algorithms.
Fast approximate energy minimization via graph cuts
TL;DR: This work presents two algorithms based on graph cuts that efficiently find a local minimum with respect to two types of large moves, namely expansion moves and swap moves that allow important cases of discontinuity preserving energies.
•Book
Level Set Methods and Dynamic Implicit Surfaces
Stanley Osher,Ronald Fedkiw +1 more
- 31 Oct 2002
TL;DR: A student or researcher working in mathematics, computer graphics, science, or engineering interested in any dynamic moving front, which might change its topology or develop singularities, will find this book interesting and useful.
6.1K
An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision
Yuri Boykov,Vladimir Kolmogorov +1 more
TL;DR: This paper compares the running times of several standard algorithms, as well as a new algorithm that is recently developed that works several times faster than any of the other methods, making near real-time performance possible.
Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images
Yuri Boykov,Marie-Pierre Jolly +1 more
- 07 Jul 2001
TL;DR: In this paper, the user marks certain pixels as "object" or "background" to provide hard constraints for segmentation, and additional soft constraints incorporate both boundary and region information.