A Sampling-Based Gem Algorithm with Classification for Texture Synthesis

Research on texture synthesis has made substantial progress in recent years, and many patch-based sampling algorithms now produce quality results in an acceptable computation time. However, when such algorithms are applied, whether they provide good results for specific textures, and why they do so, are questions that have yet to be answered. In this article, we deal specifically with the second question by modeling the synthesis problem as one of learning from incomplete data, and propose an algorithm that is a generalization of patch-work approach. Through this algorithm, we demonstrate that the solution of patch-based sampling approaches is an approximation of finding the maximum-likelihood optimum by the generalized expectation and maximization (GEM) algorithm