TwinGAN: Twin Generative Adversarial Network for Chinese Landscape Painting Style Transfer
Der‐Lor Way, Chang-Hao Lo, Yu-Hsien Wei, Zen-Chung Shih
Abstract
Recently, style transfers have received considerable attention. However, most of these studies are suitable for Western paintings. In this paper, a deep learning method is proposed to imitate multiple styles of Chinese landscape paintings. Twin generative adversarial network style transfer was proposed based on the characteristics of Chinese landscape ink paintings. SketchGAN and renderGAN were performed respectively using generative models based on the generative adversarial network. SketchGAN involves determining the structure and simplifying the content of an input photo. RenderGAN involves transferring the results of sketchGAN into the final stylized image. Moreover, a loss function was designed to maintain the shape of an input content image. Finally, the proposed TwinGAN was successfully used to imitate five styles of Chinese landscape ink paintings. This study also provides ablation studies and comparisons with previous works. Experimental results exhibit that our algorithm synthesizes Chinese landscape stylized paintings that are higher in quality than those produced by previous algorithms.