Graph-Cut RANSAC

06/03/2017
by   Daniel Barath, et al.
0

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).

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 6

page 7

10/07/2019

Faster Minimum k-cut of a Simple Graph

We consider the (exact, minimum) k-cut problem: given a graph and an int...
03/01/2018

Five-point Fundamental Matrix Estimation for Uncalibrated Cameras

We aim at estimating the fundamental matrix in two views from five corre...
09/07/2014

A Computational Model of the Short-Cut Rule for 2D Shape Decomposition

We propose a new 2D shape decomposition method based on the short-cut ru...
12/07/2018

Cut polytope has vertices on a line

The cut polytope CUT(n) is the convex hull of the cut vectors in a comp...
06/05/2019

Progressive NAPSAC: sampling from gradually growing neighborhoods

We propose Progressive NAPSAC, P-NAPSAC in short, which merges the advan...
04/11/2021

USACv20: robust essential, fundamental and homography matrix estimation

We review the most recent RANSAC-like hypothesize-and-verify robust esti...
05/07/2019

Parallel Cut Pursuit For Minimization of the Graph Total Variation

We present a parallel version of the cut-pursuit algorithm for minimizin...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.