A Fast Texture Synthesis Technique using Spatial Neighborhood

In this technical report, we present a texture synthesis technique that stores all possible histories in memory structure acting as a Finite State Machine. The histories, which are the most probable spatial neighborhood for each pixel or patch, are stored in each state of the FSM. After constructing that structure, the synthesis goes very fast and smooth in a raster scan order. We found that our technique works well for a wide variety of textures, ranging from stochastic to regular structured textures, including near-regular textures. We show that our technique is faster, and gives better results than previous pixel- or patch-based techniques, with minimal user input.