Texture Transfer Based on Energy Minimization for Painterly Rendering

Non-photorealistic rendering (NPR) creates images with artistic styles of paintings. In this field, a number of methods of converting photographed images into non-photorealistic ones have been developed, and can be categorized into filter-based and exemplar-based approaches. In this paper, we focus on the exemplar-based approach and propose a novel method which transfers a style of a reference pictorial image to a photographed image. Specifically, we first input a pair of target and reference images. The target image is converted by minimizing an energy function which is defined based on the difference in intensities between an output image and a target image, and the pattern dissimilarity between an output image and a reference image. The proposed method transfers structures and colors of textures in the reference image and generates continuous textures by minimizing the energy function. In experiments, we demonstrate the effectiveness of the proposed method using a variety of images and examine the influence of parameter changes and intensity adjustment for pre-processing on resultant images.