D. Guinnip, D. Rice, C. Jaynes, and R. Stevens. “Efficient Image-Based Projective Mapping Using the Master Texture Space Encoding,” Central European Conference on Computer Graphics, Visualization and Computer Vision, Pizen, Cz, Feb. 2003.
The master texture space is an encoding technique that supports efficient view-dependent image-based rendering applications that combine photorealistic images with an underlying surface mesh. The representation increases rendering efficiency, reduces the space required to store large numbers of object views, and supports direct image-based editing for realistic object manipulation. This encoding transforms an original set of exemplar images into a set of master textures that share a globally consistent set of texture coordinates regardless of underlying object geometry and camera positions used to create the exemplar views.
An important property of the master texture space is that an arbitrary, but fixed pixel position, in all master textures corresponds to the same point on the object surface. This property increases rendering efficiency for real-time image-based rendering applications because new texture coordinates do not have to be loaded as a function viewpoint. In addition, changes in a master texture image can be rapidly propagated to all views to add/remove features, generate new viewpoints, and remove artifacts to a pre-existing image-based scene.
Several videos showing applications of image-based editing with the master texture space are referenced on this page. One example adds a license plate image to a single exemplar image. The difference of the pre-edit and post-edit image is then encoded into the master texture space. This difference image is then propagated to all other master textures. A similar example shows a computer-generated shadow added to all master texture images.