Converting photos into 3D models

In Archive by Fredy Ore

Antonio Criminisi and Andrew Blake from Microsoft’s research labs in Cambridge have found a way to extract 3D information from an image such as a photograph.

The method determines what is behind an object in a photograph and automatically fills in what’s not seen by the camera, or within the image, or painting. The result is virtual recreation that explores what a flat image looks like from different views and angles.