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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F21%3A00337192" target="_blank" >RIV/68407700:21730/21:00337192 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/TPAMI.2019.2941876" target="_blank" >https://doi.org/10.1109/TPAMI.2019.2941876</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TPAMI.2019.2941876" target="_blank" >10.1109/TPAMI.2019.2941876</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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 pose accuracy similar to the state-of-the-art structure-based methods. Our results suggest that we might want to reconsider the current approach for accurate large-scale localization.

Název v anglickém jazyce

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

Popis výsledku anglicky

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 pose accuracy similar to the state-of-the-art structure-based methods. Our results suggest that we might want to reconsider the current approach for accurate large-scale localization.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF15_003%2F0000468" target="_blank" >EF15_003/0000468: Inteligentní strojové vnímání</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Transactions on Pattern Analysis and Machine Intelligence

ISSN

0162-8828

e-ISSN

1939-3539

Svazek periodika

43

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

16

Strana od-do

814-829

Kód UT WoS článku

000616309900005

EID výsledku v databázi Scopus

2-s2.0-85100756457