Detail patentu

Large-scale outdoor augmented reality scenes using camera pose based on learned descriptors

LUKÁČ, M. WANG, O. BREJCHA, J. HOLD-GEOFFROY, Y. ČADÍK, M.

Typ patentu

patent

Abstrakt

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.

Klíčová slova

camera pose estimation, outdoor scenes, augmented reality, learned descriptors

Číslo patentu

US11568642B2

Datum přihlášky

12. 10. 2020

Datum zápisu

31. 1. 2023

Vlastník

Adobe VUT Brno

Možnosti využití

K využití výsledku jiným subjektem je vždy nutné nabytí licence

Licenční poplatek

Poskytovatel licence na výsledek požaduje licenční poplatek

www

https://ppubs.uspto.gov/dirsearch-public/print/downloadPdf/11568642