Robust Motion Segmentation from Pairwise Matches
This work addresses motion segmentation for computer vision applications, but it is incremental as it builds on existing averaging methods.
The paper tackles motion segmentation using only pairwise matches, a previously unaddressed classification problem, by proposing a two-step process that independently segments image pairs and then robustly combines them into a globally consistent result, showing effectiveness in reducing errors and handling mismatches in simulated and real experiments.
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.