The rendered image above are taken from still photos and then stitched by Microsoft’s new Photosynth Preview. On The Photosynth site, Microsoft’s explains how it works:
When you upload a set of photos to our cloud service, our technology starts by looking for points (called "features") in successive photos that appear to be the same object.
If it finds many features that reoccur in your set of photos, it passes this information on to the second step: bundle adjustment. Bundle adjustment, a standard technique in photogrammetry, determines where in 3D space each feature is, exactly where each photo was taken from, and how the camera was oriented for each photo.
Third, the technology uses the feature points in each photo to generate 3D shapes. It does so on a per-photo basis rather than trying to generate a global 3D model for the scene.
Registration to this Preview is on a first-come, first served basis. Sign up now and be notified when slots open.