Show simple item record

dc.contributor.author
Cavalli, Luca
dc.contributor.author
Larsson, Viktor
dc.contributor.author
Oswald, Martin R.
dc.contributor.author
Sattler, Torsten
dc.contributor.author
Pollefeys, Marc
dc.contributor.editor
Vedaldi, Andrea
dc.contributor.editor
Bischof, Horst
dc.contributor.editor
Brox, Thomas
dc.contributor.editor
Frahm, Jan-Michael
dc.date.accessioned
2021-01-06T15:07:26Z
dc.date.available
2020-12-23T07:52:55Z
dc.date.available
2021-01-06T15:07:26Z
dc.date.issued
2020
dc.identifier.isbn
978-3-030-58528-0
en_US
dc.identifier.isbn
978-3-030-58529-7
en_US
dc.identifier.issn
0302-9743
dc.identifier.issn
1611-3349
dc.identifier.other
10.1007/978-3-030-58529-7_45
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/458249
dc.description.abstract
Local feature matching is a critical part of many computer vision pipelines, including among others Structure-from-Motion, SLAM, and Visual Localization. However, due to limitations in the descriptors, raw matches are often contaminated by a majority of outliers. As a result, outlier detection is a fundamental problem in computer vision and a wide range of approaches, from simple checks based on descriptor similarity to geometric verification, have been proposed over the last decades. In recent years, deep learning-based approaches to outlier detection have become popular. Unfortunately, the corresponding works rarely compare with strong classical baselines. In this paper we revisit handcrafted approaches to outlier filtering. Based on best practices, we propose a hierarchical pipeline for effective outlier detection as well as integrate novel ideas which in sum lead to an efficient and competitive approach to outlier rejection. We show that our approach, although not relying on learning, is more than competitive to both recent learned works as well as handcrafted approaches, both in terms of efficiency and effectiveness. The code is available at https://github.com/cavalli1234/AdaLAM.
en_US
dc.language.iso
en
en_US
dc.publisher
Springer
en_US
dc.subject
Low-level vision
en_US
dc.subject
Matching
en_US
dc.subject
Spatial matching
en_US
dc.subject
Spatial consistency
en_US
dc.subject
Spatial verification
en_US
dc.title
Handcrafted Outlier Detection Revisited
en_US
dc.type
Conference Paper
dc.date.published
2020-11-13
ethz.book.title
Computer Vision – ECCV 2020
en_US
ethz.journal.title
Lecture Notes in Computer Science
ethz.journal.volume
12364
en_US
ethz.journal.abbreviated
LNCS
ethz.pages.start
770
en_US
ethz.pages.end
787
en_US
ethz.event
16th European Conference on Computer Vision (ECCV 2020) (virtual)
en_US
ethz.event.location
Glasgow, United Kingdom
en_US
ethz.event.date
August 23-28, 2020
en_US
ethz.notes
Due to the Coronavirus (COVID-19) the conference was conducted virtually.
en_US
ethz.publication.place
Cham
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.date.deposited
2020-12-23T07:53:05Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2021-01-06T15:07:34Z
ethz.rosetta.lastUpdated
2021-02-15T22:56:24Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Handcrafted%20Outlier%20Detection%20Revisited&rft.jtitle=Lecture%20Notes%20in%20Computer%20Science&rft.date=2020&rft.volume=12364&rft.spage=770&rft.epage=787&rft.issn=0302-9743&1611-3349&rft.au=Cavalli,%20Luca&Larsson,%20Viktor&Oswald,%20Martin%20R.&Sattler,%20Torsten&Pollefeys,%20Marc&rft.isbn=978-3-030-58528-0&978-3-030-58529-7&rft.genre=proceeding&rft_id=info:doi/10.1007/978-3-030-58529-7_45&rft.btitle=Computer%20Vision%20%E2%80%93%20ECCV%202020
 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