Constrained random sampling and gap filling technique for near-regular texture synthesis

Abstract

This thesis addresses the synthesis of near-regular textures, i.e. textures that consist of a regular global structure plus subtle yet very characteristic stochastic irregularities, from a small exemplar image. Such textures are difficult to synthesize due to the complementary characteristics of these structures. The main purpose of this thesis is to present a novel method which we call Random Sampling and Gap Filling (RSGF) to synthesize near-regular textures. The synthesis approach is guided by a lattice of the global structure estimated from a generalized normalized autocorrelation of the sample image. This lattice constrains a random sampling process to maintain the global regular structure yet ensuring the characteristic randomness of the irregular structures. An alternative method to find the piece of texture within the input sample whose simple tiling presents less visible seams is also presented for illustration of quality enhancement purposes. Results presented in this work show that our method does not only produce convincing results for regular or near-regular textures but also for irregular textures.