Saved in:
Bibliographic Details
Main Authors: Astermark, Jonathan, Heyden, Anders, Larsson, Viktor
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.02893
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915321491750912
author Astermark, Jonathan
Heyden, Anders
Larsson, Viktor
author_facet Astermark, Jonathan
Heyden, Anders
Larsson, Viktor
contents In this paper, we speed up robust two-view relative pose from dense correspondences. Previous work has shown that dense matchers can significantly improve both accuracy and robustness in the resulting pose. However, the large number of matches comes with a significantly increased runtime during robust estimation in RANSAC. To avoid this, we propose an efficient match summarization scheme which provides comparable accuracy to using the full set of dense matches, while having 10-100x faster runtime. We validate our approach on standard benchmark datasets together with multiple state-of-the-art dense matchers.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02893
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dense Match Summarization for Faster Two-view Estimation
Astermark, Jonathan
Heyden, Anders
Larsson, Viktor
Computer Vision and Pattern Recognition
In this paper, we speed up robust two-view relative pose from dense correspondences. Previous work has shown that dense matchers can significantly improve both accuracy and robustness in the resulting pose. However, the large number of matches comes with a significantly increased runtime during robust estimation in RANSAC. To avoid this, we propose an efficient match summarization scheme which provides comparable accuracy to using the full set of dense matches, while having 10-100x faster runtime. We validate our approach on standard benchmark datasets together with multiple state-of-the-art dense matchers.
title Dense Match Summarization for Faster Two-view Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.02893