Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Dense Match Summarization for Faster Two-view Estimation

Astermark, Jonathan LU orcid ; Heyden, Anders LU orcid and Larsson, Viktor LU (2025) 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025 In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition p.1093-1102
Abstract

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.

Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
dense matching, ransac, robust estimation, two-view estimation
host publication
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
series title
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
pages
10 pages
conference name
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025
conference location
Nashville, United States
conference dates
2025-06-11 - 2025-06-15
external identifiers
  • scopus:105017027611
ISSN
1063-6919
ISBN
979-8-3315-4364-8
DOI
10.1109/CVPR52734.2025.00110
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2025 IEEE.
id
19568644-5369-455e-953f-58af98e219e5
date added to LUP
2025-12-09 08:22:47
date last changed
2025-12-09 08:23:27
@inproceedings{19568644-5369-455e-953f-58af98e219e5,
  abstract     = {{<p>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.</p>}},
  author       = {{Astermark, Jonathan and Heyden, Anders and Larsson, Viktor}},
  booktitle    = {{2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}},
  isbn         = {{979-8-3315-4364-8}},
  issn         = {{1063-6919}},
  keywords     = {{dense matching; ransac; robust estimation; two-view estimation}},
  language     = {{eng}},
  pages        = {{1093--1102}},
  series       = {{Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition}},
  title        = {{Dense Match Summarization for Faster Two-view Estimation}},
  url          = {{http://dx.doi.org/10.1109/CVPR52734.2025.00110}},
  doi          = {{10.1109/CVPR52734.2025.00110}},
  year         = {{2025}},
}