• Subscribe

Image of the week - Virtualizing Rome in a day

Virtualizing Rome in a day


A screenshot of the 3-D model of Rome's Colosseum, generated using several thousand Flickr photos. The black points surrounding the Coliseum indicate the vantage points from which photographs were taken. Image courtesy Build Rome in a Day project

Researchers at the University of Washington generated a 3-D model of Rome's greatest landmarks in a day - and they did it by standing on the shoulders of Flickr users.

The researchers applied their algorithms to 150,000 Flickr images of Rome. It took a computer cluster containing 496 cores 13 hours to match common points in the images, sorting them into groups based on the landmark depicted. Another eight hours of computation time, and they had 3-D models of landmarks such as the Colosseum, St. Peter's Basilica, Trevi Fountain and the Pantheon.

The Building Rome in a Day project, which is still in progress, aims to build a parallel distributed system that can use Flickr photographs to reconstruct entire cities. According to the project website:

"The key contributions of our work is a new, parallel distributed matching system that can match massive collections of images very quickly and a new bundle adjust software that can solve extremely large non-linear least squares problems that are encountered in three dimensional reconstruction problems."

In addition to Rome, the researchers have generated simulations of Venice and Dubrovnik.

The results of the University of Washington team's work has already been featured in several media outlets, including Popular Science and a Seattle Times blog.

To see videos and images of the visualizations the researchers have generated so far, please visit their website.

Join the conversation

Do you have story ideas or something to contribute? Let us know!

Copyright © 2019 Science Node ™  |  Privacy Notice  |  Sitemap

Disclaimer: While Science Node ™ does its best to provide complete and up-to-date information, it does not warrant that the information is error-free and disclaims all liability with respect to results from the use of the information.

Republish

We encourage you to republish this article online and in print, it’s free under our creative commons attribution license, but please follow some simple guidelines:
  1. You have to credit our authors.
  2. You have to credit ScienceNode.org — where possible include our logo with a link back to the original article.
  3. You can simply run the first few lines of the article and then add: “Read the full article on ScienceNode.org” containing a link back to the original article.
  4. The easiest way to get the article on your site is to embed the code below.