Region-based painting style transfer

Abstract

In this paper, we present a novel method for creating a painted im- Age from a photograph using an existing painting as a style source. The core idea is to identify the corresponding objects in the two images in order to select patches more appropriately. We automat- ically make a region correspondence between the painted source image and the target photograph by computing color and texture feature distances. Next, we conduct a patch-based synthesis that preserves the appropriate source and target features. Unlike previ- ous example-based approaches of painting style transfer, our results successfully reflect the features of the source images even if the in- put images have various colors and textures. Our method allows us to automatically render a new painted image preserving the features of the source image.