3D Model of Landmarks Built With Flickr Images
Researchers have developed a way to build 3D images based on similar photos.
Using millions of images pulled from Flickr, a team from the University of North Carolina at Chapel Hill (UNC) were able to build 3D models of historical landmarks, and even the majority of an entire city.
The algorithm developed by the UNC team isn’t perfect, but it can get a lot done within 24 hours. It starts by grouping similar-looking photos into “appearance clusters”. Only groups with any geometric compatibility—clusters containing photos of the building’s front and sides for instance—are retained. These remaining clusters are used to build the 3D models themselves, with the source photos manipulated to “paint” the structure determined by the algorithm.
The detail of the resulting models is quite surprising, though it’s clear that the UNC team has a long way to go. Some of team’s models are incomplete, while commissioning 3D modelers would still produce more accurate (and expensive) results. Still, the project is yet another example of crowd-sourcing’s advantages.
- WikiLeaks Asking Community to Establish Mirrors
- Get The iPhone 4 for $25 at Radio Shack
- Tougher-than-Kevlar Fiber Developed
- Turn your iPhone into a Windmill with the iFan
- MSFT Aims to Patent Every Aspect of Kinect
- Sony Launches 22" Bravia with Built-In PS2
- SIL-BOT: First Robotic Tango in Korea?
- Android 2.3 Hitting Nexus Ones? (Update: Nope)
- UnderAbove Lets you Shoot Above and Below
- Google's Next Pure Android is Officially Nexus S
- Websites Found Guilty of Browser History Sniffing
- Samsung Sells a Million Galaxy Tabs
- Sony's PlayStation Phone Caught on Video (Again)
- Facebook Profiles Get a Fancy New Layout
- The Special Keyboard for Chrome OS Laptops
- Three Russian Satellites Crash Into Pacific Ocean
- Is the PSP Phone a Eureka Moment For Microsoft?
- iPad Gets Hole Punched With Water Cutter
- Honeycomb Demoed on Tablet; Coming 2011
Dam spammers fire you all!
Though the concept is not new, these projects are really interesting, making 3d-buildings out of pictures, and if you look who is behind all of these you'll find a lot of people with a lot of experience in it.
it looks like photosynth from microsoft labs... not new
I did this in my city center with photosynth in 2008
the photosynth similarity is actually addressed in the youtube comments:
"The major differences are that we create a dense 3D model and in contrast PhotoSynth uses the images for visualization. Additionally we can handle orders of magnitude more data millions of images compared to thousands. We can handle more disturbances in the data."
I wonder what technology Google's gonna buy next and rebrand? They'll definitely want this for their maps. Google's really good at catching things before everyone's heard of them and developing it to something useful (although not always profitable).
Anyways, I expect to be able to do 3D visits to Amsterdam on Google Earth in 3 years or less. Although I guess a lot of cities are more known for what you can do there instead of what you can see.