DLP-GAN: learning to draw modern Chinese landscape photos with generative adversarial network
This addresses a niche problem in image translation for art and cultural applications, but it is incremental as it builds on existing GAN methods for a specific domain.
The paper tackles the problem of translating Chinese landscape paintings into modern photos, proposing DLP-GAN with an unsupervised cross-domain framework and novel components like asymmetric cycle mapping, achieving state-of-the-art performance as shown in user studies.
Chinese landscape painting has a unique and artistic style, and its drawing technique is highly abstract in both the use of color and the realistic representation of objects. Previous methods focus on transferring from modern photos to ancient ink paintings. However, little attention has been paid to translating landscape paintings into modern photos. To solve such problems, in this paper, we (1) propose DLP-GAN (Draw Modern Chinese Landscape Photos with Generative Adversarial Network), an unsupervised cross-domain image translation framework with a novel asymmetric cycle mapping, and (2) introduce a generator based on a dense-fusion module to match different translation directions. Moreover, a dual-consistency loss is proposed to balance the realism and abstraction of model painting. In this way, our model can draw landscape photos and sketches in the modern sense. Finally, based on our collection of modern landscape and sketch datasets, we compare the images generated by our model with other benchmarks. Extensive experiments including user studies show that our model outperforms state-of-the-art methods.