Benchmarking Image Retrieval for Visual Localization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F20%3A00347058" target="_blank" >RIV/68407700:21730/20:00347058 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/3DV50981.2020.00058" target="_blank" >https://doi.org/10.1109/3DV50981.2020.00058</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/3DV50981.2020.00058" target="_blank" >10.1109/3DV50981.2020.00058</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Benchmarking Image Retrieval for Visual Localization

Popis výsledku v původním jazyce

Visual localization, i.e., camera pose estimation in a known scene, is a core component of technologies such as autonomous driving and augmented reality. State-of-the-art localization approaches often rely on image retrieval techniques for one of two tasks: (1) provide an approximate pose estimate or (2) determine which parts of the scene are potentially visible in a given query image. It is common practice to use state-of-the-art image retrieval algorithms for these tasks. These algorithms are often trained for the goal of retrieving the same landmark under a large range of viewpoint changes. However, robustness to viewpoint changes is not necessarily desirable in the context of visual localization. This paper focuses on understanding the role of image retrieval for multiple visual localization tasks. We introduce a benchmark setup and compare state-of-the-art retrieval representations on multiple datasets. We show that retrieval performance on classical landmark retrieval/recognition tasks correlates only for some but not all tasks to localization performance. This indicates a need for retrieval approaches specifically designed for localization tasks. Our benchmark and evaluation protocols are available at https://github.com/naver/kapture-localization.

Název v anglickém jazyce

Benchmarking Image Retrieval for Visual Localization

Popis výsledku anglicky

Visual localization, i.e., camera pose estimation in a known scene, is a core component of technologies such as autonomous driving and augmented reality. State-of-the-art localization approaches often rely on image retrieval techniques for one of two tasks: (1) provide an approximate pose estimate or (2) determine which parts of the scene are potentially visible in a given query image. It is common practice to use state-of-the-art image retrieval algorithms for these tasks. These algorithms are often trained for the goal of retrieving the same landmark under a large range of viewpoint changes. However, robustness to viewpoint changes is not necessarily desirable in the context of visual localization. This paper focuses on understanding the role of image retrieval for multiple visual localization tasks. We introduce a benchmark setup and compare state-of-the-art retrieval representations on multiple datasets. We show that retrieval performance on classical landmark retrieval/recognition tasks correlates only for some but not all tasks to localization performance. This indicates a need for retrieval approaches specifically designed for localization tasks. Our benchmark and evaluation protocols are available at https://github.com/naver/kapture-localization.

Druh

D - Stať ve sborníku

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)

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

2020 International Conference on 3D Vision (3DV)

ISBN

978-1-7281-8128-8

ISSN

2378-3826

e-ISSN

2475-7888

Počet stran výsledku

12

Strana od-do

483-494

Název nakladatele

IEEE Computer Soc.

Místo vydání

Los Alamitos, CA

Místo konání akce

Kyoto

Datum konání akce

25. 11. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000653085200049