The problem of acquiring and manipulating photorealistic visual models of real scenes is a fast-growing new research area that has spawned successful commercial products like Apple's QuickTime VR. An ideal solution is one that enables (1) photographic realism, (2) real-time user-control of viewpoint, and (3) the ability to modify scene appearance. Photographs provide a convenient way of realistically capturing scene appearance, but lack the other two capabilities and are therefore of limited use for interactive graphics applications.
In this talk I will present newly developed techniques for digitally altering photographs to simulate physically-correct changes in camera perspective and 3D scene modifications. Camera viewpoint changes are achieved by automatically combining or ``steering'' a set of basis images to synthesize new scene views of photographic quality and detail. 3D scene modifications are performed interactively, via user pixel edits to individual images. These user edits are automatically propagated to other images in order to preserve physical coherence between different views of the scene. These techniques provide a way of augmenting photographs to provide both user-control of viewpoint and the ability to modify scene appearance. Applications to scene visualization, image databases, and teleconferencing will be touched upon in the talk.