Publication Details

LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors

BREJCHA Jan, LUKÁČ Michal, HOLD-GEOFFROY Yannick, WANG Oliver and ČADÍK Martin. LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors. In: Computer Vision - ECCV 2020. Lecture Notes in Computer Science, vol. 12374. Cham: Springer Nature Switzerland AG, 2020, pp. 295-312. ISBN 978-3-030-58525-9. Available from: https://link.springer.com/chapter/10.1007/978-3-030-58526-6_18
Czech title
LandscapeAR: rozšířená realita v přírodních scénách za pomoci párování fotografií s terénním modelem pomocí naučených příznakových vektorů
Type
conference paper
Language
english
Authors
Brejcha Jan, Ing., Ph.D. (DCGM FIT BUT)
Lukáč Michal (Adobe)
Hold-Geoffroy Yannick (Adobe)
Wang Oliver (Adobe)
Čadík Martin, doc. Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords

augmented reality, descriptor matching, cross domain matching, camera calibration, visual localization, structure-from-motion, terrain model, digital elevation model, photograph, computational photography

Abstract

We introduce a solution to large scale Augmented Reality for outdoor scenes by registering camera images to textured Digital Elevation Models (DEMs). To accommodate the inherent differences in appearance between real images and DEMs, we train a cross-domain feature descriptor using Structure From Motion (SFM) guided reconstructions to acquire training data. Our method runs efficiently on a mobile device and outperforms existing learned and hand-designed feature descriptors for this task.

Published
2020
Pages
295-312
Proceedings
Computer Vision - ECCV 2020
Series
Lecture Notes in Computer Science
Volume
12374
Conference
European Conference on Computer Vision 2020, online, CZ
ISBN
978-3-030-58525-9
Publisher
Springer Nature Switzerland AG
Place
Cham, DE
DOI
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB12342,
   author = "Jan Brejcha and Michal Luk\'{a}\v{c} and Yannick Hold-Geoffroy and Oliver Wang and Martin \v{C}ad\'{i}k",
   title = "LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors",
   pages = "295--312",
   booktitle = "Computer Vision - ECCV 2020",
   series = "Lecture Notes in Computer Science",
   volume = 12374,
   year = 2020,
   location = "Cham, DE",
   publisher = "Springer Nature Switzerland AG",
   ISBN = "978-3-030-58525-9",
   doi = "10.1007/978-3-030-58526-6\_18",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12342"
}
Back to top