The movie below is well worth watching – it details the deep photo system with a simple interactive registration process is used to align a photograph with such a model. Once the photograph and the model have been registered, an abundance of information, such as depth, texture, and GIS data, becomes immediately available to our system. This information, in turn, enables a variety of operations, ranging from dehazing and relighting the photograph, to novel view synthesis, and overlaying with geographic information. The movie describes the implementation of a number of these applications and discuss possible extensions.
Results show that augmenting photographs with already available 3D models of the world supports a wide variety of new ways for us to experience and interact with our everyday snapshots. Note everything is geospatially linked, the paper was presented at SIGGRAPH Asia 2008.
See http://johanneskopf.de/publications/deep_photo/ for more info.