Example Based Image Analysis and Synthesis

Abstract

Image analysis and graphics synthesis can be achieved with learning techniques using directly image examples without physically-based, 3D models. We describe here novel techniques for the analysis and the synthesis of new grey-level (and color) images. With the first technique, ffl the mapping from novel images to a vector of "pose" and "expression" parameters can be learned from a small set of example images using a function approximation technique that we call an analysis network; ffl the inverse mapping from input "pose" and "expression" parameters to output grey-level images can be synthesized from a small set of example images and used to produce new images under real-time control using a similar learning network, called in this case a synthesis network. This technique relies on (i) using a correspondence algorithm that matches corresponding pixels among pairs of grey-level images and effectively "vectorizes" them, and (ii) exploiting a class of multidimensional interpolation n...