papers AI Learner
The Github is limit! Click to go to the new site.

Robust Motion Segmentation from Pairwise Matches

2019-05-22
Federica Arrigoni, Tomas Pajdla

Abstract

In this paper we address a classification problem that has not been considered before, namely motion segmentation given pairwise matches only. Our contribution to this unexplored task is a novel formulation of motion segmentation as a two-step process. First, motion segmentation is performed on image pairs independently. Secondly, we combine independent pairwise segmentation results in a robust way into the final globally consistent segmentation. Our approach is inspired by the success of averaging methods. We demonstrate in simulated as well as in real experiments that our method is very effective in reducing the errors in the pairwise motion segmentation and can cope with large number of mismatches.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.09043

PDF

http://arxiv.org/pdf/1905.09043


Similar Posts

Comments