Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Robust Motion Segmentation from Pairwise Matches

About

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.

Federica Arrigoni, Tomas Pajdla• 2019

Related benchmarks

TaskDatasetResultRank
Motion SegmentationHopkins 155 3-motion sequences
Mean Clustering Error (%)2.67
45
Motion SegmentationHopkins 155 (all sequences)
Mean Clustering Error1.37
45
Motion SegmentationHopkins 155 2-motion sequences
Classification Error0.01
31
Motion SegmentationHopkins 12
Avg Classification Error4.33
20
Motion SegmentationIndoor Dataset Penguin sequence 1.0 (test)
Misclassification Error0.0076
6
Motion SegmentationIndoor Dataset Flowers sequence 1.0 (test)
Error (%)1.23
6
Motion SegmentationIndoor Dataset Bag sequence 1.0 (test)
Misclassification Error (%)1.52
6
Motion SegmentationIndoor Dataset Pencils sequence 1.0 (test)
Misclassification Error0.038
6
Motion SegmentationIndoor Dataset Bears sequence 1.0 (test)
Error Rate4.82
6
Motion Segmentationhelicopter
Misclassification Error (%)2.01
3
Showing 10 of 13 rows

Other info

Follow for update