ML Anthology

Graph-Cut RANSAC

Daniel Barath, Jiří Matas
CVPR 2018
doi:10.1109/CVPR.2018.00704 /cvpr/2018/barath2018cvpr-graphcut/

Abstract

A novel method for robust estimation, called Graph-Cut RANSAC, GC-RANSAC in short, is introduced. To separate inliers and outliers, it runs the graph-cut algorithm in the local optimization (LO) step which is applied when a so-far-the-best model is found. The proposed LO step is conceptually simple, easy to implement, globally optimal and efficient. GC-RANSAC is shown experimentally, both on synthesized tests and real image pairs, to be more geometrically accurate than state-of-the-art methods on a range of problems, e.g. line fitting, homography, affine transformation, fundamental and essential matrix estimation. It runs in real-time for many problems at a speed approximately equal to that of the less accurate alternatives (in milliseconds on standard CPU).

PDF CVPR Semantic Scholar

Cite

Text

Barath and Matas. "Graph-Cut RANSAC." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00704

Markdown

[Barath and Matas. "Graph-Cut RANSAC." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/barath2018cvpr-graphcut/) doi:10.1109/CVPR.2018.00704

BibTeX

@inproceedings{barath2018cvpr-graphcut,
  title     = {{Graph-Cut RANSAC}},
  author    = {Barath, Daniel and Matas, Jiří},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00704},
  url       = {https://mlanthology.org/cvpr/2018/barath2018cvpr-graphcut/}
}