Rome, Built In a Day

spmallick writes "Researchers at the University of Washington, in collaboration with Microsoft, have recreated the city of Rome in 3D using images obtained from Flickr. The data set consists of 150,000 images from Flickr.com associated with the tags 'Rome' or 'Roma,' and it took 21 hours on 496 compute cores to create a 3D digital model. Unlike Photosynth / Photo Tourism, the goal was to reconstruct an entire city and not just individual landmarks. Previous versions of the Photo Tourism software matched each photo to every other photo in the set. But as the number of photos increases the number of matches explodes, increasing with the square of the number of photos. A set of 250,000 images would take at least a year for 500 computers to process... A million photos would take more than a decade! The newly developed code works more than a hundred times faster than the previous version. It first establishes likely matches and then concentrates on those parts."

TED talk with a 2007 version

[jhsiao]

Photosynth was showcased in a mid 2007 TED talk. You can find it here [ted.com].

It would be nice to have photosynths of monuments, art, or architecture that have been damaged or destroyed (e.g. the Buddhas dynamited in Afghanistan, the churches that collapsed in the 2009 Italy earthquake) from tourist photos that may be floating out in the interwebs.

Re:As far as I can tell...

[Tim4444]

No, it's designed to help you find images of a particular location and then it shows you the original photos. The 3d model part is kinda misleading as they're just using it to calculate the relative positions of where the pictures were taken and then browse it like a giant 3d menu. The summary gave me the impression that they built a photo realistic 3d model of the city, but it's just a glorified image browser. You could argue it's like Google image search, but it seems that they did actually copy the pictures instead of just linking to the originals on Flickr. Still, it's some pretty neat photo processing.

UW website

[guido1]

The teams actual site has more pics and videos, including St. Peter's Basilica, Trevi Fountain, and info on Venice.

http://grail.cs.washington.edu/rome/ [washington.edu]

Re:Cool, but...

[afidel]

496 cores isn't all that much, with HT enabled a 1U server can hold 16 cores so a 42U rack can hold 672 cores, blade servers are even more dense. The budget for most midsized IT departments probably has room for a few compute clusters of that size.

Re:As far as I can tell...

[TooMuchToDo]

Also, their import app is most likely checking the Creative Commons license on the photos they're pulling from Flickr.

Re:Cool, but...

[Anonymous Coward]

There are 2 opensource projects aiming to do similar 3d reconstructions:

http://code.google.com/p/libmv/ [google.com]
http://insight3d.sourceforge.net/ [sourceforge.net]

So while getting those 496 cores would still be a task for you, opensource software _is_ nearly there too.

Re:Cool, but...

[Anonymous Coward]

Most of the brains on this project are AT the University of Washington. If you recall (or read the article), Photosynth is a UW project licensed to Microsoft. Not that there aren't amazingly smart people over at MSR, too. They can't help that they're right across the lake from each other (UW & MSR).

Re:As far as I can tell...

[Tim4444]

I mean that the goal of the project is not to have a 3d model to view, but rather to use a 3d model to make it easier to find 2d pictures. Check the videos on their site.