At the Intel Developer Forum in San Francisco, Intel CEO Paul Otellini demoed how the company’s processors are being used to render a 3D model from millions of user-generated images taken from photo-sharing sites such as Flicker and Picasa. We like the view that this could lead to crowd sourced 3D modelling, indeed it seems to be the current trend:
The work is being done at the University of Washington, where researchers have crowd-sourced images from the Web and created 3D re-construction of St. Peter’s Basilica in Vatican City.
Interesting. Is it possible to extract the resulting 3D object and import it into, say, Poser? Or create from it a Collada file and import that into Second Life?
The main focus of most efforts like the one portraied seem to be Internet images, maybe because of the untapped resource it is, for the sheer volume of images available. But you can do it with your one images also, as we have been doing it in my research group here in Portugal: http://archc3d.fa.utl.pt/archc3d.html We already did 3d models of a world heritage castle/convent and a historic city centre (Tomar), with photos taken with a balloon and a RC airplane!