Texture Compilation for Example-Based Synthesis

In this paper, a new exemplar-based framework is presented, which treats image completion, texture synthesis and texture Analysis in a unified manner. In order to be able to avoid the occurrence of visually inconsistent results, we pose all of the image-editing tasks in the form of a discrete global optimization problem. The objective function of this problem is always well-defined, and corresponds to the energy of a discrete Markov Random Field (MRF). For efficiently optimizing this MRF, a novel optimization scheme, called Priority-BP, is then proposed, which carries two very important extensions over the standard Belief Propagation (BP) algorithm: "priority-based message scheduling" and "dynamic label pruning". These two extensions work in cooperation to deal with the intolerable computational cost of BP, which is caused by the huge number of labels associated with our MRF. In an Experimental results on a wide variety of input images are presented, which demonstrate the effectiveness of our image-completion framework for tasks such as object removal, texture synthesis, text removal and texture Analysis.