Search This Blog

Saturday, November 3, 2007

Photos Lead to 3D Models of World Landmarks

More than 10 million members of the photo-sharing Web site Flickr snap
pictures of their surroundings and then post those photos on the
Internet. One group of researchers is doing the reverse -- downloading
thousands of photos from Flickr and using them to recreate the original
scenes. In a technical paper "Multi-View Stereo for Community Photo
Collections" then describe how photos from online sites such as Flickr
can be used to create a virtual 3D model of landmarks, including Notre
Dame Cathedral in Paris and the Statue of Liberty in New York City.
The long-term vision is to be able to reconstruct the detailed geometry
of all the structures on the surface of the Earth. Many people are
working toward that goal, but by using online collections this work
brings in a whole new source of imagery and level of detail. The paper
abstract: "We present a multi-view stereo algorithm that addresses the
extreme changes in lighting, scale, clutter, and other effects in
large online community photo collections. Our idea is to intelligently
choose images to match, both at a per-view and per-pixel level. We show
that such adaptive view selection enables robust performance even with
dramatic appearance variability. The stereo matching technique takes as
input sparse 3D points reconstructed from structure-from-motion methods
and iteratively grows surfaces from these points. Optimizing for surface
normals within a photoconsistency measure significantly improves the
matching results. While the focus of our approach is to estimate
high-quality depth maps, we also show examples of merging the resulting
depth maps into compelling scene reconstructions. We demonstrate our
algorithm on standard multi-view stereo datasets and on casually acquired
photo collections of famous scenes gathered from the Internet." More Information

No comments: