Summary of Dlp-gan: Learning to Draw Modern Chinese Landscape Photos with Generative Adversarial Network, by Xiangquan Gui et al.
DLP-GAN: learning to draw modern Chinese landscape photos with generative adversarial network
by Xiangquan Gui, Binxuan Zhang, Li Li, Yi Yang
First submitted to arxiv on: 6 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed DLP-GAN framework utilizes an unsupervised cross-domain image translation approach to translate Chinese landscape paintings into modern photos, addressing a long-standing problem in the field of artistic style transfer. This innovative method leverages a novel asymmetric cycle mapping and a dense-fusion module-based generator to achieve realistic and abstract representations. A dual-consistency loss is introduced to balance these competing factors, allowing for more accurate and nuanced translations. The authors demonstrate the effectiveness of their approach through extensive experiments and user studies, outperforming state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us learn how to turn old Chinese landscape paintings into modern photos using a special kind of artificial intelligence called generative adversarial networks (GANs). For a long time, people have been trying to translate old ink paintings into modern photos, but no one has focused on the other way around – translating modern landscape paintings back into ancient style. The authors create a new system that can do this translation and makes it look very realistic. They tested their system with many examples and showed that it works better than existing methods. |
Keywords
» Artificial intelligence » Gan » Style transfer » Translation » Unsupervised
