liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
DKM: Dense Kernelized Feature Matching for Geometry Estimation
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. (Computer Vision Laboratory)ORCID iD: 0000-0002-1019-8634
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. (Computer Vision Laboratory)ORCID iD: 0000-0002-5213-6757
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. (Computer Vision Laboratory)ORCID iD: 0000-0002-0675-2794
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. (Computer Vision Laboratory)ORCID iD: 0000-0002-6096-3648
2023 (English)In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Communications Society, 2023, p. 17765-17775Conference paper, Published paper (Refereed)
Abstract [en]

Feature matching is a challenging computer vision task that involves finding correspondences between two images of a 3D scene. In this paper we consider the dense approach instead of the more common sparse paradigm, thus striving to find all correspondences. Perhaps counter-intuitively, dense methods have previously shown inferior performance to their sparse and semi-sparse counterparts for estimation of two-view geometry. This changes with our novel dense method, which outperforms both dense and sparse methods on geometry estimation. The novelty is threefold: First, we propose a kernel regression global matcher. Secondly, we propose warp refinement through stacked feature maps and depthwise convolution kernels. Thirdly, we propose learning dense confidence through consistent depth and a balanced sampling approach for dense confidence maps. Through extensive experiments we confirm that our proposed dense method, Dense Kernelized Feature Matching, sets a new state-of-the-art on multiple geometry estimation benchmarks. In particular, we achieve an improvement on MegaDepth-1500 of +4.9 and +8.9 AUC@5° compared to the best previous sparse method and dense method respectively. Our code is provided at the following repository: https://github.com/Parskatt/DKM.

Place, publisher, year, edition, pages
IEEE Communications Society, 2023. p. 17765-17775
Series
Proceedings:IEEE Conference on Computer Vision and Pattern Recognition, ISSN 1063-6919, E-ISSN 2575-7075
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-197717DOI: 10.1109/cvpr52729.2023.01704ISI: 001062531302008ISBN: 9798350301298 (electronic)ISBN: 9798350301304 (print)OAI: oai:DiVA.org:liu-197717DiVA, id: diva2:1795945
Conference
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 17-24 June 2023
Note

This work was supported by the Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP), funded by Knut and Alice Wallenberg Foundation; andby the strategic research environment ELLIIT funded by the Swedish government. The computational resources were provided by the National Academic Infrastructure forSupercomputing in Sweden (NAISS), partially funded by the Swedish Research Council through grant agreement no. 2022-06725, and by the Berzelius resource, provided bythe Knut and Alice Wallenberg Foundation at the National Supercomputer Centre.

Available from: 2023-09-11 Created: 2023-09-11 Last updated: 2023-11-30Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textCodePreprint

Authority records

Edstedt, JohanAthanasiadis, IoannisWadenbäck, MårtenFelsberg, Michael

Search in DiVA

By author/editor
Edstedt, JohanAthanasiadis, IoannisWadenbäck, MårtenFelsberg, Michael
By organisation
Computer VisionFaculty of Science & Engineering
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 113 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf