Notice

This record has been edited as far as possible, missing data will be added when the version of record is issued.

Show simple item record

dc.contributor.author
Hajder, Levente
dc.contributor.author
Lóczi, Lajos
dc.contributor.author
Barath, Daniel
dc.date.accessioned
2023-11-29T15:04:44Z
dc.date.available
2023-11-23T17:37:00Z
dc.date.available
2023-11-29T15:04:44Z
dc.date.issued
2023
dc.identifier.uri
http://hdl.handle.net/20.500.11850/643520
dc.description.abstract
We present a new solver for estimating a surface normal from a single affine correspondence in two calibrated views. The proposed approach provides a new globally optimal solution for this over-determined problem and proves that it reduces to a linear system that can be solved extremely efficiently. This allows for performing significantly faster than other recent methods, solving the same problem and obtaining the same globally optimal solution. We demonstrate on 15k image pairs from standard benchmarks that the proposed approach leads to the same results as other optimal algorithms while being, on average, five times faster than the fastest alternative. Besides its theoretical value, we demonstrate that such an approach has clear benefits, e.g., in image-based visual localization, due to not requiring a dense point cloud to recover the surface normal. We show on the Cambridge Landmarks dataset that leveraging the proposed surface normal estimation further improves localization accuracy. Matlab and C++ implementations are also published in the supplementary material.
en_US
dc.language.iso
en
en_US
dc.title
Fast Globally Optimal Surface Normal Estimation from an Affine Correspondence
en_US
dc.type
Conference Paper
ethz.book.title
2023 IEEE/CVF International Conference on Computer Vision (ICCV)
en_US
ethz.pages.start
3390
en_US
ethz.pages.end
3401
en_US
ethz.event
19th International Conference on Computer Vision (ICCV 2023)
en_US
ethz.event.location
Paris, France
en_US
ethz.event.date
October 2-6, 2023
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02659 - Institut für Visual Computing / Institute for Visual Computing::03766 - Pollefeys, Marc / Pollefeys, Marc
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02659 - Institut für Visual Computing / Institute for Visual Computing::03766 - Pollefeys, Marc / Pollefeys, Marc
en_US
ethz.identifier.url
https://openaccess.thecvf.com/content/ICCV2023/html/Hajder_Fast_Globally_Optimal_Surface_Normal_Estimation_from_an_Affine_Correspondence_ICCV_2023_paper.html
ethz.date.deposited
2023-11-23T17:37:01Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.exportRequired
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Fast%20Globally%20Optimal%20Surface%20Normal%20Estimation%20from%20an%20Affine%20Correspondence&rft.date=2023&rft.spage=3390&rft.epage=3401&rft.au=Hajder,%20Levente&L%C3%B3czi,%20Lajos&Barath,%20Daniel&rft.genre=proceeding&rft.btitle=2023%20IEEE/CVF%20International%20Conference%20on%20Computer%20Vision%20(ICCV)
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record