software

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. This project implements our research paper LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors (http://cphoto.fit.vutbr.cz/LandscapeAR/), which has been published on the European Conference on Computer Vision - ECCV 2020. 

3D reconstruction, machine learning, camera pose estimation, visual localization from single image, virtual and augmented reality

14. 8. 2020

https://github.com/brejchajan/LandscapeAR

K využití výsledku jiným subjektem je vždy nutné nabytí licence

Poskytovatel licence na výsledek nepožaduje licenční poplatek

https://github.com/brejchajan/LandscapeAR