Back to the Feature: Learning Robust Camera Localization from Pixels to Pose

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F21%3A00356128" target="_blank" >RIV/68407700:21730/21:00356128 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/CVPR46437.2021.00326" target="_blank" >https://doi.org/10.1109/CVPR46437.2021.00326</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR46437.2021.00326" target="_blank" >10.1109/CVPR46437.2021.00326</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose

Popis výsledku v původním jazyce

Camera pose estimation in known scenes is a 3D geometry task recently tackled by multiple learning algorithms. Many regress precise geometric quantities, like poses or 3D points, from an input image. This either fails to generalize to new viewpoints or ties the model parameters to a specific scene. In this paper, we go Back to the Feature: we argue that deep networks should focus on learning robust and invariant visual features, while the geometric estimation should be left to principled algorithms. We introduce PixLoc, a scene-agnostic neural network that estimates an accurate 6-DoF pose from an image and a 3D model. Our approach is based on the direct alignment of multiscale deep features, casting camera localization as metric learning. PixLoc learns strong data priors by end-to-end training from pixels to pose and exhibits exceptional generalization to new scenes by separating model parameters and scene geometry. The system can localize in large environments given coarse pose priors but also improve the accuracy of sparse feature matching by jointly refining keypoints and poses with little overhead. The code will be publicly available at github.com/cvg/pixloc.

Název v anglickém jazyce

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose

Popis výsledku anglicky

Camera pose estimation in known scenes is a 3D geometry task recently tackled by multiple learning algorithms. Many regress precise geometric quantities, like poses or 3D points, from an input image. This either fails to generalize to new viewpoints or ties the model parameters to a specific scene. In this paper, we go Back to the Feature: we argue that deep networks should focus on learning robust and invariant visual features, while the geometric estimation should be left to principled algorithms. We introduce PixLoc, a scene-agnostic neural network that estimates an accurate 6-DoF pose from an image and a 3D model. Our approach is based on the direct alignment of multiscale deep features, casting camera localization as metric learning. PixLoc learns strong data priors by end-to-end training from pixels to pose and exhibits exceptional generalization to new scenes by separating model parameters and scene geometry. The system can localize in large environments given coarse pose priors but also improve the accuracy of sparse feature matching by jointly refining keypoints and poses with little overhead. The code will be publicly available at github.com/cvg/pixloc.

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

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

ISBN

978-1-6654-4510-8

ISSN

1063-6919

e-ISSN

2575-7075

Počet stran výsledku

11

Strana od-do

3246-3256

Název nakladatele

IEEE Computer Society

Místo vydání

USA

Místo konání akce

Nashville

Datum konání akce

20. 6. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000739917303044