Image Matching Across Wide Baselines: From Paper to Practice
We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task—the accuracy of the reconstructed camera pose—as our primary metric. Our pipeline’s modular structure allows easy integration, configuration, and combination of different metho...
Gespeichert in:
Veröffentlicht in: | International journal of computer vision 2021-02, Vol.129 (2), p.517-547 |
---|---|
Hauptverfasser: | , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 547 |
---|---|
container_issue | 2 |
container_start_page | 517 |
container_title | International journal of computer vision |
container_volume | 129 |
creator | Jin, Yuhe Mishkin, Dmytro Mishchuk, Anastasiia Matas, Jiri Fua, Pascal Yi, Kwang Moo Trulls, Eduard |
description | We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task—the accuracy of the reconstructed camera pose—as our primary metric. Our pipeline’s modular structure allows easy integration, configuration, and combination of different methods and heuristics. This is demonstrated by embedding dozens of popular algorithms and evaluating them, from seminal works to the cutting edge of machine learning research. We show that with proper settings, classical solutions may still outperform the
perceived state of the art
. Besides establishing the
actual state of the art
, the conducted experiments reveal unexpected properties of structure from motion pipelines that can help improve their performance, for both algorithmic and learned methods. Data and code are online (
https://github.com/ubc-vision/image-matching-benchmark
), providing an easy-to-use and flexible framework for the benchmarking of local features and robust estimation methods, both
alongside
and
against
top-performing methods. This work provides a basis for the Image Matching Challenge (
https://image-matching-challenge.github.io
). |
doi_str_mv | 10.1007/s11263-020-01385-0 |
format | Article |
fullrecord | <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_journals_2489055227</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A651789904</galeid><sourcerecordid>A651789904</sourcerecordid><originalsourceid>FETCH-LOGICAL-c392t-66ab297e28ab2770067f2b4497a6c82d03120b3f0a0d49a2e8094ab2dc3e895d3</originalsourceid><addsrcrecordid>eNp9kc9LwzAUx4MoOKf_gKeCJw-dL0nTNOJlDqcDxeEPPIYsfa0dazuTDvS_N66C7CI5PMj7fPIe-RJySmFEAeSFp5SlPAYGMVCeiRj2yIAKyWOagNgnA1ChJVJFD8mR90sAYBnjA3I1q02J0YPp7HvVlNHYutb76K3KMbo2HldVg_4ymrq2juZmjS7q2mjujO0qi8fkoDArjye_dUhepzcvk7v4_vF2Nhnfx5Yr1sVpahZMSWRZqFICpLJgiyRR0qQ2YzlwymDBCzCQJ8owzEAlAc0tx0yJnA_JWf_u2rUfG_SdXrYb14SRmiWZAiEYk4Ea9VRpVqirpmi7sGc4OdaVbRssqnA_TgWVmVKQBOF8RwhMh59daTbe69nz0y7Lenb7Pw4LvXZVbdyXpqB_ItB9BDpEoLcRaAgS7yUf4KZE97f3P9Y3OpuFSw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2489055227</pqid></control><display><type>article</type><title>Image Matching Across Wide Baselines: From Paper to Practice</title><source>SpringerNature Journals</source><creator>Jin, Yuhe ; Mishkin, Dmytro ; Mishchuk, Anastasiia ; Matas, Jiri ; Fua, Pascal ; Yi, Kwang Moo ; Trulls, Eduard</creator><creatorcontrib>Jin, Yuhe ; Mishkin, Dmytro ; Mishchuk, Anastasiia ; Matas, Jiri ; Fua, Pascal ; Yi, Kwang Moo ; Trulls, Eduard</creatorcontrib><description>We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task—the accuracy of the reconstructed camera pose—as our primary metric. Our pipeline’s modular structure allows easy integration, configuration, and combination of different methods and heuristics. This is demonstrated by embedding dozens of popular algorithms and evaluating them, from seminal works to the cutting edge of machine learning research. We show that with proper settings, classical solutions may still outperform the
perceived state of the art
. Besides establishing the
actual state of the art
, the conducted experiments reveal unexpected properties of structure from motion pipelines that can help improve their performance, for both algorithmic and learned methods. Data and code are online (
https://github.com/ubc-vision/image-matching-benchmark
), providing an easy-to-use and flexible framework for the benchmarking of local features and robust estimation methods, both
alongside
and
against
top-performing methods. This work provides a basis for the Image Matching Challenge (
https://image-matching-challenge.github.io
).</description><identifier>ISSN: 0920-5691</identifier><identifier>EISSN: 1573-1405</identifier><identifier>DOI: 10.1007/s11263-020-01385-0</identifier><language>eng</language><publisher>New York: Springer US</publisher><subject>Algorithms ; Artificial Intelligence ; Benchmarks ; Computer Imaging ; Computer Science ; Heuristic methods ; Image Processing and Computer Vision ; Machine learning ; Matching ; Modular structures ; Pattern Recognition ; Pattern Recognition and Graphics ; Robustness ; Special Issue on Performance Evaluation in Computer Vision ; Vision</subject><ispartof>International journal of computer vision, 2021-02, Vol.129 (2), p.517-547</ispartof><rights>Springer Science+Business Media, LLC, part of Springer Nature 2020</rights><rights>COPYRIGHT 2021 Springer</rights><rights>Springer Science+Business Media, LLC, part of Springer Nature 2020.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c392t-66ab297e28ab2770067f2b4497a6c82d03120b3f0a0d49a2e8094ab2dc3e895d3</citedby><cites>FETCH-LOGICAL-c392t-66ab297e28ab2770067f2b4497a6c82d03120b3f0a0d49a2e8094ab2dc3e895d3</cites><orcidid>0000-0002-1425-7881 ; 0000-0001-8205-6718 ; 0000-0003-0863-4844</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11263-020-01385-0$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11263-020-01385-0$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Jin, Yuhe</creatorcontrib><creatorcontrib>Mishkin, Dmytro</creatorcontrib><creatorcontrib>Mishchuk, Anastasiia</creatorcontrib><creatorcontrib>Matas, Jiri</creatorcontrib><creatorcontrib>Fua, Pascal</creatorcontrib><creatorcontrib>Yi, Kwang Moo</creatorcontrib><creatorcontrib>Trulls, Eduard</creatorcontrib><title>Image Matching Across Wide Baselines: From Paper to Practice</title><title>International journal of computer vision</title><addtitle>Int J Comput Vis</addtitle><description>We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task—the accuracy of the reconstructed camera pose—as our primary metric. Our pipeline’s modular structure allows easy integration, configuration, and combination of different methods and heuristics. This is demonstrated by embedding dozens of popular algorithms and evaluating them, from seminal works to the cutting edge of machine learning research. We show that with proper settings, classical solutions may still outperform the
perceived state of the art
. Besides establishing the
actual state of the art
, the conducted experiments reveal unexpected properties of structure from motion pipelines that can help improve their performance, for both algorithmic and learned methods. Data and code are online (
https://github.com/ubc-vision/image-matching-benchmark
), providing an easy-to-use and flexible framework for the benchmarking of local features and robust estimation methods, both
alongside
and
against
top-performing methods. This work provides a basis for the Image Matching Challenge (
https://image-matching-challenge.github.io
).</description><subject>Algorithms</subject><subject>Artificial Intelligence</subject><subject>Benchmarks</subject><subject>Computer Imaging</subject><subject>Computer Science</subject><subject>Heuristic methods</subject><subject>Image Processing and Computer Vision</subject><subject>Machine learning</subject><subject>Matching</subject><subject>Modular structures</subject><subject>Pattern Recognition</subject><subject>Pattern Recognition and Graphics</subject><subject>Robustness</subject><subject>Special Issue on Performance Evaluation in Computer Vision</subject><subject>Vision</subject><issn>0920-5691</issn><issn>1573-1405</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNp9kc9LwzAUx4MoOKf_gKeCJw-dL0nTNOJlDqcDxeEPPIYsfa0dazuTDvS_N66C7CI5PMj7fPIe-RJySmFEAeSFp5SlPAYGMVCeiRj2yIAKyWOagNgnA1ChJVJFD8mR90sAYBnjA3I1q02J0YPp7HvVlNHYutb76K3KMbo2HldVg_4ymrq2juZmjS7q2mjujO0qi8fkoDArjye_dUhepzcvk7v4_vF2Nhnfx5Yr1sVpahZMSWRZqFICpLJgiyRR0qQ2YzlwymDBCzCQJ8owzEAlAc0tx0yJnA_JWf_u2rUfG_SdXrYb14SRmiWZAiEYk4Ea9VRpVqirpmi7sGc4OdaVbRssqnA_TgWVmVKQBOF8RwhMh59daTbe69nz0y7Lenb7Pw4LvXZVbdyXpqB_ItB9BDpEoLcRaAgS7yUf4KZE97f3P9Y3OpuFSw</recordid><startdate>20210201</startdate><enddate>20210201</enddate><creator>Jin, Yuhe</creator><creator>Mishkin, Dmytro</creator><creator>Mishchuk, Anastasiia</creator><creator>Matas, Jiri</creator><creator>Fua, Pascal</creator><creator>Yi, Kwang Moo</creator><creator>Trulls, Eduard</creator><general>Springer US</general><general>Springer</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>ISR</scope><scope>3V.</scope><scope>7SC</scope><scope>7WY</scope><scope>7WZ</scope><scope>7XB</scope><scope>87Z</scope><scope>8AL</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>8FL</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BEZIV</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FRNLG</scope><scope>F~G</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K60</scope><scope>K6~</scope><scope>K7-</scope><scope>L.-</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>M0C</scope><scope>M0N</scope><scope>P5Z</scope><scope>P62</scope><scope>PQBIZ</scope><scope>PQBZA</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PYYUZ</scope><scope>Q9U</scope><orcidid>https://orcid.org/0000-0002-1425-7881</orcidid><orcidid>https://orcid.org/0000-0001-8205-6718</orcidid><orcidid>https://orcid.org/0000-0003-0863-4844</orcidid></search><sort><creationdate>20210201</creationdate><title>Image Matching Across Wide Baselines: From Paper to Practice</title><author>Jin, Yuhe ; Mishkin, Dmytro ; Mishchuk, Anastasiia ; Matas, Jiri ; Fua, Pascal ; Yi, Kwang Moo ; Trulls, Eduard</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c392t-66ab297e28ab2770067f2b4497a6c82d03120b3f0a0d49a2e8094ab2dc3e895d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Artificial Intelligence</topic><topic>Benchmarks</topic><topic>Computer Imaging</topic><topic>Computer Science</topic><topic>Heuristic methods</topic><topic>Image Processing and Computer Vision</topic><topic>Machine learning</topic><topic>Matching</topic><topic>Modular structures</topic><topic>Pattern Recognition</topic><topic>Pattern Recognition and Graphics</topic><topic>Robustness</topic><topic>Special Issue on Performance Evaluation in Computer Vision</topic><topic>Vision</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Jin, Yuhe</creatorcontrib><creatorcontrib>Mishkin, Dmytro</creatorcontrib><creatorcontrib>Mishchuk, Anastasiia</creatorcontrib><creatorcontrib>Matas, Jiri</creatorcontrib><creatorcontrib>Fua, Pascal</creatorcontrib><creatorcontrib>Yi, Kwang Moo</creatorcontrib><creatorcontrib>Trulls, Eduard</creatorcontrib><collection>CrossRef</collection><collection>Gale In Context: Science</collection><collection>ProQuest Central (Corporate)</collection><collection>Computer and Information Systems Abstracts</collection><collection>Access via ABI/INFORM (ProQuest)</collection><collection>ABI/INFORM Global (PDF only)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ABI/INFORM Global (Alumni Edition)</collection><collection>Computing Database (Alumni Edition)</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ABI/INFORM Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Business Premium Collection</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Business Premium Collection (Alumni)</collection><collection>ABI/INFORM Global (Corporate)</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Business Collection (Alumni Edition)</collection><collection>ProQuest Business Collection</collection><collection>Computer Science Database</collection><collection>ABI/INFORM Professional Advanced</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>ABI/INFORM Global</collection><collection>Computing Database</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>One Business (ProQuest)</collection><collection>ProQuest One Business (Alumni)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ABI/INFORM Collection China</collection><collection>ProQuest Central Basic</collection><jtitle>International journal of computer vision</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jin, Yuhe</au><au>Mishkin, Dmytro</au><au>Mishchuk, Anastasiia</au><au>Matas, Jiri</au><au>Fua, Pascal</au><au>Yi, Kwang Moo</au><au>Trulls, Eduard</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Image Matching Across Wide Baselines: From Paper to Practice</atitle><jtitle>International journal of computer vision</jtitle><stitle>Int J Comput Vis</stitle><date>2021-02-01</date><risdate>2021</risdate><volume>129</volume><issue>2</issue><spage>517</spage><epage>547</epage><pages>517-547</pages><issn>0920-5691</issn><eissn>1573-1405</eissn><abstract>We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task—the accuracy of the reconstructed camera pose—as our primary metric. Our pipeline’s modular structure allows easy integration, configuration, and combination of different methods and heuristics. This is demonstrated by embedding dozens of popular algorithms and evaluating them, from seminal works to the cutting edge of machine learning research. We show that with proper settings, classical solutions may still outperform the
perceived state of the art
. Besides establishing the
actual state of the art
, the conducted experiments reveal unexpected properties of structure from motion pipelines that can help improve their performance, for both algorithmic and learned methods. Data and code are online (
https://github.com/ubc-vision/image-matching-benchmark
), providing an easy-to-use and flexible framework for the benchmarking of local features and robust estimation methods, both
alongside
and
against
top-performing methods. This work provides a basis for the Image Matching Challenge (
https://image-matching-challenge.github.io
).</abstract><cop>New York</cop><pub>Springer US</pub><doi>10.1007/s11263-020-01385-0</doi><tpages>31</tpages><orcidid>https://orcid.org/0000-0002-1425-7881</orcidid><orcidid>https://orcid.org/0000-0001-8205-6718</orcidid><orcidid>https://orcid.org/0000-0003-0863-4844</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0920-5691 |
ispartof | International journal of computer vision, 2021-02, Vol.129 (2), p.517-547 |
issn | 0920-5691 1573-1405 |
language | eng |
recordid | cdi_proquest_journals_2489055227 |
source | SpringerNature Journals |
subjects | Algorithms Artificial Intelligence Benchmarks Computer Imaging Computer Science Heuristic methods Image Processing and Computer Vision Machine learning Matching Modular structures Pattern Recognition Pattern Recognition and Graphics Robustness Special Issue on Performance Evaluation in Computer Vision Vision |
title | Image Matching Across Wide Baselines: From Paper to Practice |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T15%3A17%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Image%20Matching%20Across%20Wide%20Baselines:%20From%20Paper%20to%20Practice&rft.jtitle=International%20journal%20of%20computer%20vision&rft.au=Jin,%20Yuhe&rft.date=2021-02-01&rft.volume=129&rft.issue=2&rft.spage=517&rft.epage=547&rft.pages=517-547&rft.issn=0920-5691&rft.eissn=1573-1405&rft_id=info:doi/10.1007/s11263-020-01385-0&rft_dat=%3Cgale_proqu%3EA651789904%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2489055227&rft_id=info:pmid/&rft_galeid=A651789904&rfr_iscdi=true |