Algorithmic Painter: a NPR method to generate various styles of painting

摘要

This paper proposes Algorithmic Painter, an algorithm that can produce various styles of painting from source photos. Algorithmic Painter is created by enhancing Synergistic Image Creator, a painterly rendering method, so that it is highly expressive but still preserves the essential characteristics of the source photo. To achieve this, our method extracts three types of image segments automatically from a source photo by a newly proposed classification method: edge areas, homogeneous areas, and highly contrastive areas. Next, each obtained image segment is converted into a brushstroke. Finally, the target picture is rendered by assigning a color to each pixel. Furthermore, this method can control the curvy shapes of brushstrokes, so that the obtained image can incorporate not only various artistic touches but also natural touches. As an example, the paper describes the composition technique for three considerably different painting styles.