Texturing and line art rendering using patch-based image analogies

Abstract

We present a simple patch-based matching scheme for generating novel visual appearance in which a new image is synthesized by the optimal pasting of small patches of input sample texture image. First, we use this patch-based matching method as an efficient and simple textured synthesis algorithm to produce a wide range of textures with superb visual appearance. Second, we extend the algorithm for the texture transfer - rendering an image in the style of a different texture image. Third, we generalize the algorithm for processing images by examples, called "patch-based image analogies". From this perspective, the texture synthesis and texture transfer are the special cases of the image texturing. Experimental results show that the proposed scheme is extremely efficient and effective for the image texturing problems, such as texture synthesis, texture transfer, line art rendering, etc. Due to the efficiency of the patch-based sampling, our method outperforms many existing algorithms with comparable visual quality.