Worth a thousand million words: Researchers create 3-D models from online photo databases (w/ Video)

November 23, 2010, University of North Carolina at Chapel Hill
A screenshot of a 3-D model of the exterior of the Coliseum, Rome, Italy. Credit, Jan-Michael Frahm, UNC-Chapel Hill.

Who says Rome wasn't built in a day? Computer scientists have invented a technique that automatically creates 3-D models of landmarks and geographical locations, using ordinary two-dimensional pictures available through Internet photo sharing sites like Flickr.

The technique creates the models using millions of images, processing them on a single personal computer in less than a day.

It was devised by a team of researchers from the University of North Carolina at Chapel Hill and the Swiss university, ETH-Zurich, led by Jan-Michael Frahm, Ph.D., research assistant professor of computer science in the UNC College of Arts and Sciences.

To demonstrate their technique, the researchers used the 3 million images of Rome available online to reconstruct all of the city’s major landmarks. It took less than 24 hours on a single PC using commodity graphics hardware. They also reconstructed the landmarks of Berlin in the same manner.

Video of the 3-D models and the processing technique

Frahm said the process provides a far richer experience and is an improvement of more than a factor of 1,000 over current commercial systems, such as Microsoft PhotoSynth, and alternative techniques developed by other researchers.

“Our technique would be the equivalent of processing a stack of photos as high as the 828-meter Dubai Towers, using a single PC, versus the next best technique, which is the equivalent of processing a stack of photos 42 meters tall – as high as the ceiling of Notre Dame – using 62 PCs,” he said. “This efficiency is essential if one is to fully utilize the billions of user-provided images continuously being uploaded to the Internet.”

One advantage of the 3-D models compared to viewing a video of a landmark is that the Internet photo collections used to construct them show the scene at different times and under different lighting and weather conditions, potentially creating a richer experience for viewers, he said. If video is available, however, the technology can utilize it as well, and using video shortens the processing time needed for reconstruction of the models.

Frahm said eventually the models could be embedded, for example, into common consumer applications such as Google Earth or Bing Maps, allowing users to explore cities from the comfort of their homes. Other applications could prove useful to travelers.

“You might be able to take a picture with your cell phone of a monument that would not only give you information about that monument, identifying it from the image, but could also tell you your location more precisely than even GPS,” Frahm said.

He also noted that the technology could be a building block for disaster response software. For example, an aircraft could be sent to take video of the aftermath of a hurricane, and the resulting 3-D model could be used to assess damage from a remote location, saving time and money.

Frahm collaborated on the project with Marc Pollefeys, professor of computer science at ETH-Zurich and an adjunct professor at UNC, and Svetlana Lazebnik, assistant professor of at UNC. They recently presented a paper on their research titled “Building Rome on a Cloudless Day” at the 11th European Conference on Computer Vision.

Explore further: Rome was built in a day, with hundreds of thousands of digital photos

More information: Project website: www.cs.unc.edu/~jmf/rome_on_a_cloudless_day

Related Stories

AMD showcases 'Llano' Fusion APU

October 19, 2010

At the 6th Annual AMD Technical Forum & Exhibition (TFE) 2010, AMD today showcased for its ecosystem partners the first public demonstration of the forthcoming AMD Fusion Accelerated Processing Unit (APU) codenamed “Llano”, ...

Big steps in creating small chips

November 4, 2010

(PhysOrg.com) -- Plastic, heated in a simple microwave oven, is the technique researchers at the University of Alberta and the National Institute for Nanotechnology believe could help to re-invent the manufacture of computer ...

Recommended for you

Technology near for real-time TV political fact checks

January 18, 2019

A Duke University team expects to have a product available for election year that will allow television networks to offer real-time fact checks onscreen when a politician makes a questionable claim during a speech or debate.

Privacy becomes a selling point at tech show

January 7, 2019

Apple is not among the exhibitors at the 2019 Consumer Electronics Show, but that didn't prevent the iPhone maker from sending a message to attendees on a large billboard.

China's Huawei unveils chip for global big data market

January 7, 2019

Huawei Technologies Ltd. showed off a new processor chip for data centers and cloud computing Monday, expanding into new and growing markets despite Western warnings the company might be a security risk.


Adjust slider to filter visible comments by rank

Display comments: newest first

1 / 5 (1) Nov 23, 2010
As "security" concerns cause more oppressive restrictions on travel, both domestic and international, this technology may be used to allow people to "visit" places that in the near future they may never be allowed to visit in person. In time, this may be the only way people get to visit these places.
3 / 5 (2) Nov 23, 2010
No creepy TSA idiots wanting to stick their finger up your butt, no uncomfortable planes with bad air, no hotel room burglarized, no purse snatched, no stolen camera, no pickpocketing, no inflated cab fares, no street urchins begging for money, no smell of urine in narrow streets....sounds like the way to go sightseeing to me.
not rated yet Nov 24, 2010
didn't microsoft come up with this a few years ago -- a friend of mine showed me the MS url that took photos and did this same thing -- and even identified the location if there was enough detail.
not rated yet Nov 24, 2010
didn't microsoft come up with this a few years ago -- a friend of mine showed me the MS url that took photos and did this same thing -- and even identified the location if there was enough detail.

Yes. It's called Microsoft Photosynth... They talked about it in this article. They mentioned that their new method is much more efficient.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.