Texture synthesis using particle swarm optimization

In this paper, we present a survey of traditional and contemporary texture synthesis methods. It is a texture synthesis form sample. The algorithm uses a particle swarm optimization (PSO) algorithm to search the best matching patch from the input sample textures and paste it onto the output texture. It changes the throughout search method of the original patch-based sampling. It synthesises high-quality textures with a mid-level PC in real-time. We have analyzed how the number of the particles influences the speed of the synthesis. In the end of the paper, we assess the computing time and list the performance comparison between others´ algorithms and ours.