View in EDS

Pixel-Perfect Structure-From-Motion With Featuremetric Refinement

Saved in:
Bibliographic Details
Title: Pixel-Perfect Structure-From-Motion With Featuremetric Refinement
Authors: Sarlin, Paul Edouard, Lindenberger, Philipp, Larsson, Viktor, Pollefeys, Marc
Contributors: Lund University, Faculty of Engineering, LTH, LTH Profile areas, LTH Profile Area: AI and Digitalization, Lunds universitet, Lunds Tekniska Högskola, LTH profilområden, LTH profilområde: AI och digitalisering, Originator, Lund University, Faculty of Science, Centre for Mathematical Sciences, Research groups at the Centre for Mathematical Sciences, Mathematical Imaging Group, Lunds universitet, Naturvetenskapliga fakulteten, Matematikcentrum, Forskargrupper vid Matematikcentrum, Mathematical Imaging Group, Originator, Lund University, Faculty of Science, Centre for Mathematical Sciences, Mathematics (Faculty of Engineering), Computer Vision and Machine Learning, Lunds universitet, Naturvetenskapliga fakulteten, Matematikcentrum, Matematik LTH, Datorseende och maskininlärning, Originator, Lund University, Profile areas and other strong research environments, Lund University Profile areas, LU Profile Area: Natural and Artificial Cognition, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Lunds universitets profilområden, LU profilområde: Naturlig och artificiell kognition, Originator, Lund University, Profile areas and other strong research environments, Strategic research areas (SRA), ELLIIT: the Linköping-Lund initiative on IT and mobile communication, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Strategiska forskningsområden (SFO), ELLIIT: the Linköping-Lund initiative on IT and mobile communication, Originator
Source: IEEE Transactions on Pattern Analysis and Machine Intelligence. 47(5):3298-3309
Subject Terms: Natural Sciences, Computer and Information Sciences, Computer graphics and computer vision, Naturvetenskap, Data- och informationsvetenskap (Datateknik), Datorgrafik och datorseende
Description: Finding local features that are repeatable across multiple views is a cornerstone of sparse 3D reconstruction. The classical image matching paradigm detects keypoints per-image once and for all, which can yield poorly-localized features and propagate large errors to the final geometry. In this article, we refine two key steps of structure-from-motion by a direct alignment of low-level image information from multiple views: we first adjust the initial keypoint locations prior to any geometric estimation, and subsequently refine points and camera poses as a post-processing. This refinement is robust to large detection noise and appearance changes, as it optimizes a featuremetric error based on dense features predicted by a neural network. This significantly improves the accuracy of camera poses and scene geometry for a wide range of keypoint detectors, challenging viewing conditions, and off-the-shelf deep features. Our system easily scales to large image collections, enabling pixel-perfect crowd-sourced localization at scale.
Access URL: https://doi.org/10.1109/TPAMI.2023.3237269
Database: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://doi.org/10.1109/TPAMI.2023.3237269#
    Name: EDS - SwePub (s4221598)
    Category: fullText
    Text: View record in SwePub
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsswe&genre=article&issn=01628828&ISBN=&volume=47&issue=5&date=20250101&spage=3298&pages=3298-3309&title=IEEE Transactions on Pattern Analysis and Machine Intelligence&atitle=Pixel-Perfect%20Structure-From-Motion%20With%20Featuremetric%20Refinement&aulast=Sarlin%2C%20Paul%20Edouard&id=DOI:10.1109/TPAMI.2023.3237269
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Sarlin%20PE
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.portal.research.lu.se.publications.3336ceae.3da4.4656.a4cc.221aa5f62130
RelevancyScore: 1115
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1114.736328125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Pixel-Perfect Structure-From-Motion With Featuremetric Refinement
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Sarlin%2C+Paul+Edouard%22">Sarlin, Paul Edouard</searchLink><br /><searchLink fieldCode="AR" term="%22Lindenberger%2C+Philipp%22">Lindenberger, Philipp</searchLink><br /><searchLink fieldCode="AR" term="%22Larsson%2C+Viktor%22">Larsson, Viktor</searchLink><br /><searchLink fieldCode="AR" term="%22Pollefeys%2C+Marc%22">Pollefeys, Marc</searchLink>
– Name: Author
  Label: Contributors
  Group: Au
  Data: Lund University, Faculty of Engineering, LTH, LTH Profile areas, LTH Profile Area: AI and Digitalization, Lunds universitet, Lunds Tekniska Högskola, LTH profilområden, LTH profilområde: AI och digitalisering, Originator<br />Lund University, Faculty of Science, Centre for Mathematical Sciences, Research groups at the Centre for Mathematical Sciences, Mathematical Imaging Group, Lunds universitet, Naturvetenskapliga fakulteten, Matematikcentrum, Forskargrupper vid Matematikcentrum, Mathematical Imaging Group, Originator<br />Lund University, Faculty of Science, Centre for Mathematical Sciences, Mathematics (Faculty of Engineering), Computer Vision and Machine Learning, Lunds universitet, Naturvetenskapliga fakulteten, Matematikcentrum, Matematik LTH, Datorseende och maskininlärning, Originator<br />Lund University, Profile areas and other strong research environments, Lund University Profile areas, LU Profile Area: Natural and Artificial Cognition, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Lunds universitets profilområden, LU profilområde: Naturlig och artificiell kognition, Originator<br />Lund University, Profile areas and other strong research environments, Strategic research areas (SRA), ELLIIT: the Linköping-Lund initiative on IT and mobile communication, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Strategiska forskningsområden (SFO), ELLIIT: the Linköping-Lund initiative on IT and mobile communication, Originator
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>. 47(5):3298-3309
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Natural+Sciences%22">Natural Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+and+Information+Sciences%22">Computer and Information Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+graphics+and+computer+vision%22">Computer graphics and computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Naturvetenskap%22">Naturvetenskap</searchLink><br /><searchLink fieldCode="DE" term="%22Data-+och+informationsvetenskap+%28Datateknik%29%22">Data- och informationsvetenskap (Datateknik)</searchLink><br /><searchLink fieldCode="DE" term="%22Datorgrafik+och+datorseende%22">Datorgrafik och datorseende</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Finding local features that are repeatable across multiple views is a cornerstone of sparse 3D reconstruction. The classical image matching paradigm detects keypoints per-image once and for all, which can yield poorly-localized features and propagate large errors to the final geometry. In this article, we refine two key steps of structure-from-motion by a direct alignment of low-level image information from multiple views: we first adjust the initial keypoint locations prior to any geometric estimation, and subsequently refine points and camera poses as a post-processing. This refinement is robust to large detection noise and appearance changes, as it optimizes a featuremetric error based on dense features predicted by a neural network. This significantly improves the accuracy of camera poses and scene geometry for a wide range of keypoint detectors, challenging viewing conditions, and off-the-shelf deep features. Our system easily scales to large image collections, enabling pixel-perfect crowd-sourced localization at scale.
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://doi.org/10.1109/TPAMI.2023.3237269" linkWindow="_blank">https://doi.org/10.1109/TPAMI.2023.3237269</link>
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.portal.research.lu.se.publications.3336ceae.3da4.4656.a4cc.221aa5f62130
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TPAMI.2023.3237269
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 3298
    Subjects:
      – SubjectFull: Natural Sciences
        Type: general
      – SubjectFull: Computer and Information Sciences
        Type: general
      – SubjectFull: Computer graphics and computer vision
        Type: general
      – SubjectFull: Naturvetenskap
        Type: general
      – SubjectFull: Data- och informationsvetenskap (Datateknik)
        Type: general
      – SubjectFull: Datorgrafik och datorseende
        Type: general
    Titles:
      – TitleFull: Pixel-Perfect Structure-From-Motion With Featuremetric Refinement
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Sarlin, Paul Edouard
      – PersonEntity:
          Name:
            NameFull: Lindenberger, Philipp
      – PersonEntity:
          Name:
            NameFull: Larsson, Viktor
      – PersonEntity:
          Name:
            NameFull: Pollefeys, Marc
      – PersonEntity:
          Name:
            NameFull: Lund University, Faculty of Engineering, LTH, LTH Profile areas, LTH Profile Area: AI and Digitalization, Lunds universitet, Lunds Tekniska Högskola, LTH profilområden, LTH profilområde: AI och digitalisering, Originator
      – PersonEntity:
          Name:
            NameFull: Lund University, Faculty of Science, Centre for Mathematical Sciences, Research groups at the Centre for Mathematical Sciences, Mathematical Imaging Group, Lunds universitet, Naturvetenskapliga fakulteten, Matematikcentrum, Forskargrupper vid Matematikcentrum, Mathematical Imaging Group, Originator
      – PersonEntity:
          Name:
            NameFull: Lund University, Faculty of Science, Centre for Mathematical Sciences, Mathematics (Faculty of Engineering), Computer Vision and Machine Learning, Lunds universitet, Naturvetenskapliga fakulteten, Matematikcentrum, Matematik LTH, Datorseende och maskininlärning, Originator
      – PersonEntity:
          Name:
            NameFull: Lund University, Profile areas and other strong research environments, Lund University Profile areas, LU Profile Area: Natural and Artificial Cognition, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Lunds universitets profilområden, LU profilområde: Naturlig och artificiell kognition, Originator
      – PersonEntity:
          Name:
            NameFull: Lund University, Profile areas and other strong research environments, Strategic research areas (SRA), ELLIIT: the Linköping-Lund initiative on IT and mobile communication, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Strategiska forskningsområden (SFO), ELLIIT: the Linköping-Lund initiative on IT and mobile communication, Originator
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 01628828
            – Type: issn-locals
              Value: SWEPUB_FREE
            – Type: issn-locals
              Value: LU_SWEPUB
          Numbering:
            – Type: volume
              Value: 47
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: IEEE Transactions on Pattern Analysis and Machine Intelligence
              Type: main
ResultId 1