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

Jan Brejcha, Michal Lukáč, Yannick Hold-Geoffroy, Oliver Wang, Martin Čadík

ECCV 2020

doi:10.1007/978-3-030-58526-6_18 /eccv/2020/brejcha2020eccv-landscapear/

Abstract

We introduce a solution to large scale Augmented Reality for outdoor scenes by registering camera images to textured Digital Elevation Models (DEMs). To accomodate the inherent differences in appearance between real images and DEMs, we train a cross-domain feature descriptor using Structure From Motion (SFM) 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.

PDF ECCV Semantic Scholar

Cite

Text

Brejcha et al. "LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58526-6_18

Markdown

[Brejcha et al. "LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/brejcha2020eccv-landscapear/) doi:10.1007/978-3-030-58526-6_18

BibTeX

@inproceedings{brejcha2020eccv-landscapear,
  title     = {{LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors}},
  author    = {Brejcha, Jan and Lukáč, Michal and Hold-Geoffroy, Yannick and Wang, Oliver and Čadík, Martin},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58526-6_18},
  url       = {https://mlanthology.org/eccv/2020/brejcha2020eccv-landscapear/}
}