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

Jan Brejcha, ibrejcha@fit.vutbr.cz
Michal Lukáč, lukac@adobe.com
Yannick Hold-Geoffroy, holdgeof@adobe.com
Oliver Wang, owang@adobe.com
Martin Čadík, cadikm@centrum.cz


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.