MeshLoc: Mesh-Based Visual Localization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00360761" target="_blank" >RIV/68407700:21230/22:00360761 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/22:00360761

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-031-20047-2_34" target="_blank" >https://doi.org/10.1007/978-3-031-20047-2_34</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-20047-2_34" target="_blank" >10.1007/978-3-031-20047-2_34</a>

Jazyk výsledku

angličtina

Název v původním jazyce

MeshLoc: Mesh-Based Visual Localization

Popis výsledku v původním jazyce

Visual localization, i.e., the problem of camera pose estimation, is a central component of applications such as autonomous robots and augmented reality systems. A dominant approach in the literature, shown to scale to large scenes and to handle complex illumination and seasonal changes, is based on local features extracted from images. The scene representation is a sparse Structure-from-Motion point cloud that is tied to a specific local feature. Switching to another feature type requires an expensive feature matching step between the database images used to construct the point cloud. In this work, we thus explore a more flexible alternative based on dense 3D meshes that does not require features matching between database images to build the scene representation. We show that this approach can achieve state-of-the-art results. We further show that surprisingly competitive results can be obtained when extracting features on renderings of these meshes, without any neural rendering stage, and even when rendering raw scene geometry without color or texture. Our results show that dense 3D model-based representations are a promising alternative to existing representations and point to interesting and challenging directions for future research.

Název v anglickém jazyce

MeshLoc: Mesh-Based Visual Localization

Popis výsledku anglicky

Visual localization, i.e., the problem of camera pose estimation, is a central component of applications such as autonomous robots and augmented reality systems. A dominant approach in the literature, shown to scale to large scenes and to handle complex illumination and seasonal changes, is based on local features extracted from images. The scene representation is a sparse Structure-from-Motion point cloud that is tied to a specific local feature. Switching to another feature type requires an expensive feature matching step between the database images used to construct the point cloud. In this work, we thus explore a more flexible alternative based on dense 3D meshes that does not require features matching between database images to build the scene representation. We show that this approach can achieve state-of-the-art results. We further show that surprisingly competitive results can be obtained when extracting features on renderings of these meshes, without any neural rendering stage, and even when rendering raw scene geometry without color or texture. Our results show that dense 3D model-based representations are a promising alternative to existing representations and point to interesting and challenging directions for future research.

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

Computer Vision - ECCV 2022, Part XXII

ISBN

978-3-031-20046-5

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

21

Strana od-do

589-609

Název nakladatele

Springer, Cham

Místo vydání

—

Místo konání akce

Tel Aviv

Datum konání akce

23. 10. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000904116000034