SwePub
Sök i LIBRIS databas

  Utökad sökning

id:"swepub:oai:research.chalmers.se:239b661e-563b-4535-b9be-daac10c121b7"
 

Sökning: id:"swepub:oai:research.chalmers.se:239b661e-563b-4535-b9be-daac10c121b7" > Are Large-Scale 3D ...

Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization

Torii, Akihiko (författare)
Tokyo Institute of Technology
Taira, Hajime (författare)
Tokyo Institute of Technology
Sivic, Josef (författare)
Ecole Normale Superieure (ENS)
visa fler...
Pollefeys, Marc (författare)
Eidgenössische Technische Hochschule Zürich (ETH),Swiss Federal Institute of Technology in Zürich (ETH)
Okutomi, Masatoshi (författare)
Tokyo Institute of Technology
Pajdla, Tomas (författare)
Ceske Vysoke Uceni Technicke v Praze,Czech Technical University in Prague
Sattler, Torsten, 1983 (författare)
Chalmers tekniska högskola,Chalmers University of Technology
visa färre...
 (creator_code:org_t)
2021
2021
Engelska.
Ingår i: IEEE Transactions on Pattern Analysis and Machine Intelligence. - 1939-3539 .- 0162-8828. ; 43:3, s. 814-829
  • Tidskriftsartikel (refereegranskat)
Abstract Ämnesord
Stäng  
  • Accurate visual localization is a key technology for autonomous navigation. 3D structure-based methods employ 3D models of the scene to estimate the full 6 degree-of-freedom (DOF) pose of a camera very accurately. However, constructing (and extending) large-scale 3D models is still a significant challenge. In contrast, 2D image retrieval-based methods only require a database of geo-tagged images, which is trivial to construct and to maintain. They are often considered inaccurate since they only approximate the positions of the cameras. Yet, the exact camera pose can theoretically be recovered when enough relevant database images are retrieved. In this paper, we demonstrate experimentally that large-scale 3D models are not strictly necessary for accurate visual localization. We create reference poses for a large and challenging urban dataset. Using these poses, we show that combining image-based methods with local reconstructions results in a higher pose accuracy compared to state-of-the-art structure-based methods, albeight at higher run-time costs. We show that some of these run-time costs can be alleviated by exploiting known database image poses. Our results suggest that we might want to reconsider the need for large-scale 3D models in favor of more local models, but also that further research is necessary to accelerate the local reconstruction process.

Ämnesord

TEKNIK OCH TEKNOLOGIER  -- Annan teknik -- Mediateknik (hsv//swe)
ENGINEERING AND TECHNOLOGY  -- Other Engineering and Technologies -- Media Engineering (hsv//eng)
NATURVETENSKAP  -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
TEKNIK OCH TEKNOLOGIER  -- Medicinteknik -- Medicinsk bildbehandling (hsv//swe)
ENGINEERING AND TECHNOLOGY  -- Medical Engineering -- Medical Image Processing (hsv//eng)

Nyckelord

image retrieval
place recognition
Visual localization
pose estimation
image-based localization

Publikations- och innehållstyp

art (ämneskategori)
ref (ämneskategori)

Hitta via bibliotek

Till lärosätets databas

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy