-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xue_2021_WACV, author = {Xue, Alice}, title = {End-to-End Chinese Landscape Painting Creation Using Generative Adversarial Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2021}, pages = {3863-3871} }
End-to-End Chinese Landscape Painting Creation Using Generative Adversarial Networks
Abstract
Current GAN-based art generation methods produce unoriginal artwork due to their dependence on conditional input. Here, we propose Sketch-And-Paint GAN (SAPGAN), the first model which generates Chinese landscape paintings from end to end, without conditional input. SAPGAN is composed of two GANs: SketchGAN for generation of edge maps, and PaintGAN for subsequent edge-to-painting translation. Our model is trained on a new dataset of traditional Chinese landscape paintings never before used for generative research. A 242-person Visual Turing Test study reveals that SAPGAN paintings are mistaken as human artwork with 55% frequency, significantly outperforming paintings from baseline GANs. Our work lays a groundwork for truly machine-original art generation.
Related Material