Optimal sample patches selection for tile-based texture synthesis

One significant problem in tile-based texture synthesis is the selection of sample patches. The reason is that the tiling process may produce results with poor quality when the sample patches used to fill the tiles can not find good cutting patches at the merging stage. In this paper, we use genetic algorithm to find the best group of sample patches from a considerable number of patch groups. Using tile set gene rated by these optimal sample patches can significantly improve the result quality of the tile-based texture synthesis.