HyperAIHyperAI

Command Palette

Search for a command to run...

3 months ago

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

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

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

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.

Benchmarks

BenchmarkMethodologyMetrics
patch-matching-on-hpatchesLSAR-aux-render
Patch Matching: 45.3
Patch Retrieval: 55.6
Patch Verification: 95.6

Build AI with AI

From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.

AI Co-coding
Ready-to-use GPUs
Best Pricing
Get Started

Hyper Newsletters

Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp
LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors | Papers | HyperAI