Texture synthesis using image pyramids and self-organizing maps

Abstract

Markov random field (MRF) is a well known model for the generation of textures in the field of computer graphics. However, the estimation of its parameter is quite difficult in many cases. A new algorithm for the synthesis of textures is proposed, based on image pyramids and self-organizing maps. This procedure avoids the explicit computation of the MRF parameters. Preliminary results support the appropriateness of this new approach.