LMGAN: A Progressive End-to-End Chinese Landscape Painting Generation Model

AI Generated Content (AIGC) has caught the attention of researchers around the world. Very good results have been achieved in the generation of Western art painting, but little research has been done on the generation of Chinese Landscape Painting (CLP). In addition, the quality of CLP generated by existing studies is still not high enough, they only imitate the color and often lack of details in their scenes. To overcome those weaknesses, we propose a progressive end-to-end Long Memory Adversarial Generation Network (LMGAN) to generate CLP. First, we create a new high-quality CLP dataset. Then we design a memory module and a mapping module to capture more low-dimensional features, as well as a layer extraction module to improve the layers of the generated results. Experiments show that LMGAN can generate richer and more detailed CLP compared to former methods.