Semi-Stochastic Tilings for Example-Based Texture Synthesis

Abstract

We investigate semi-stochastic tilings based on Wang or corner tiles for the real-time synthesis of example-based textures. In particular, we propose two new tiling approaches: (1) to replace stochastic tilings with pseudo-random tilings based on the Halton low-discrepancy sequence, and (2) to allow the controllable generation of tilings based on a user-provided probability distribution. Our first method prevents local repetition of texture content as common with stochastic approaches and yields better results with smaller sets of utilized tiles. Our second method allows to directly influence the synthesis result which—in combination with an enhanced tile construction method that merges multiple source textures—extends synthesis tasks to globally-varying textures. We show that both methods can be implemented very efficiently in connection with tile-based texture mapping and also present a general rule that allows to significantly reduce resulting tile sets.