Example-based art pattern synthesis using level sets

Abstract

Line drawings and digital arts appear everywhere, from simple icons to cartoons, maps and illustrations. We define art patterns as the subset of line drawings and digital arts that are comprised of repeated elements. Inspired by recent success of exemplar-based texture synthesis, in this paper, we focus on synthesizing art patterns with curvilinear features from exemplars, which we cast as a global optimization problem. Our energy function for this problem measures both the appearance similarity of color patterns and shape similarity of curvilinear features. We develop an overall EM-style algorithm for minimizing this energy function. The shape similarity part of the energy is minimized through an innovative application of the level set method. We further generalize our energy function and optimization algorithm so that they can effectively synthesize art patterns that consist of multiple layers.