Slashdot Mirror
Recreating Cities Using Online Photos
Roland Piquepaille writes "The billion of images available from a site like Flickr has stimulated the imagination of many researchers. After designing tools using Flickr to edit your photos, another team at the University of Washington (UW) is using our vacation photos to create 3D models of world landmarks. But recreating original scenes is challenging because all the photos we put on Flickr and similar sites don't exhibit the same quality. With such a large number of pictures available, the researchers have been able to reconstruct with great accuracy virtual 3D model of landmarks, including Notre Dame Cathedral in Paris and the Statue of Liberty in New York City."
It looks like an incredible idea with a lot of promise, but the shots they've shown so far look like some lumpy rejects from a plastic vacuum forming machine. There is some great potential here to involve people to generate better models by asking them to contribute pics of certain monuments with certain characteristics such as resolution, position and so on.
You are confusing two things. This new paper adds 3D modeling. Now you don't just know the relative pose of pictures, you can also use them to compute the 3-D shape of things in those pictures.
I was actually trying to be sarcastic, but i got modded insightful??
---- Booth was a patriot ----
It's not easy (there's a lot of work involved), but with a calibrated camera, you can, in fact, take lots of pictures of an object and turn them into a 3D model with existing software. So that part of the problem is already solved; it's really just a (very big) linear algebra problem.
In fact, if you have a stereoscopic setup, it's quite easy, in computer vision terms, to perform the necessary calculations and correlations to do this automatically. It's a little harder with a single camera, positioned at free-form positions in space; to make it easy, you'd need to figure out a way for an AI to automatically figure out what points correlated between two pictures. Not a trivial task.
The SIFT algorithm created by David Lowe, might work for that; it's commonly used in panorama stitching software to automatically determine the common points between two overlapping photos. Provided you had only a small amount of rotation between photos, it could probably give you some good results.
Interesting how ingrained the "MS bought it" mindset is. Looks like a blind spot that's going to catch some people unawares in the future.