A hybrid attention generative adversarial network for Chinese landscape painting
Abstract In traditional Chinese painting, the genre of landscapes is unique and universally valued. For an untrained person to achieve such results is very difficult, requiring mastery of such things as brushwork, composition, and color. In this paper, we propose HA-GAN to transform sketches into Ch...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-84676-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559595498078208 |
|---|---|
| author | Qiongshuai Lyu Na Zhao Zhiyuan Sun Yu Yang Chi Zhang Ruolin Shi |
| author_facet | Qiongshuai Lyu Na Zhao Zhiyuan Sun Yu Yang Chi Zhang Ruolin Shi |
| author_sort | Qiongshuai Lyu |
| collection | DOAJ |
| description | Abstract In traditional Chinese painting, the genre of landscapes is unique and universally valued. For an untrained person to achieve such results is very difficult, requiring mastery of such things as brushwork, composition, and color. In this paper, we propose HA-GAN to transform sketches into Chinese landscape paintings, a new GAN-based framework that builds upon a hybrid attention generator and a discriminator. To generate more realistic landscape paintings, we have designed a hybrid attention module (HA) containing style attention, spatial attention, and channel attention. The proposed hybrid attention module organically integrates the correlation between channels, the spatial long-distance dependence, and the extraction of image-style features into one module. HA combines the advantages of three attention mechanisms and can extract important features of traditional Chinese landscape paintings from multiple dimensions. This combination approach helps the proposed model to understand the input data more accurately and thus improves the model performance. Moreover, a novel loss function is proposed to guide the training process of the model. The experimental results show the advantages of the proposed method compared to the comparison methods both in terms of quantitative and qualitative evaluation. The proposed method can generate realistic landscape paintings similar to those created by human artists. |
| format | Article |
| id | doaj-art-4bd3aadef2984653aa2ac9dfd494a3ad |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-4bd3aadef2984653aa2ac9dfd494a3ad2025-01-05T12:20:09ZengNature PortfolioScientific Reports2045-23222025-01-0115111710.1038/s41598-024-84676-7A hybrid attention generative adversarial network for Chinese landscape paintingQiongshuai Lyu0Na Zhao1Zhiyuan Sun2Yu Yang3Chi Zhang4Ruolin Shi5School of Software, Pingdingshan UniversitySchool of Journalism and Communication, Pingdingshan UniversitySchool of Software, Pingdingshan UniversitySchool of Software, Pingdingshan UniversitySchool of Software, Pingdingshan UniversitySchool of Software, Pingdingshan UniversityAbstract In traditional Chinese painting, the genre of landscapes is unique and universally valued. For an untrained person to achieve such results is very difficult, requiring mastery of such things as brushwork, composition, and color. In this paper, we propose HA-GAN to transform sketches into Chinese landscape paintings, a new GAN-based framework that builds upon a hybrid attention generator and a discriminator. To generate more realistic landscape paintings, we have designed a hybrid attention module (HA) containing style attention, spatial attention, and channel attention. The proposed hybrid attention module organically integrates the correlation between channels, the spatial long-distance dependence, and the extraction of image-style features into one module. HA combines the advantages of three attention mechanisms and can extract important features of traditional Chinese landscape paintings from multiple dimensions. This combination approach helps the proposed model to understand the input data more accurately and thus improves the model performance. Moreover, a novel loss function is proposed to guide the training process of the model. The experimental results show the advantages of the proposed method compared to the comparison methods both in terms of quantitative and qualitative evaluation. The proposed method can generate realistic landscape paintings similar to those created by human artists.https://doi.org/10.1038/s41598-024-84676-7Generative adversarial networkAttentionSketchLandscape painting |
| spellingShingle | Qiongshuai Lyu Na Zhao Zhiyuan Sun Yu Yang Chi Zhang Ruolin Shi A hybrid attention generative adversarial network for Chinese landscape painting Scientific Reports Generative adversarial network Attention Sketch Landscape painting |
| title | A hybrid attention generative adversarial network for Chinese landscape painting |
| title_full | A hybrid attention generative adversarial network for Chinese landscape painting |
| title_fullStr | A hybrid attention generative adversarial network for Chinese landscape painting |
| title_full_unstemmed | A hybrid attention generative adversarial network for Chinese landscape painting |
| title_short | A hybrid attention generative adversarial network for Chinese landscape painting |
| title_sort | hybrid attention generative adversarial network for chinese landscape painting |
| topic | Generative adversarial network Attention Sketch Landscape painting |
| url | https://doi.org/10.1038/s41598-024-84676-7 |
| work_keys_str_mv | AT qiongshuailyu ahybridattentiongenerativeadversarialnetworkforchineselandscapepainting AT nazhao ahybridattentiongenerativeadversarialnetworkforchineselandscapepainting AT zhiyuansun ahybridattentiongenerativeadversarialnetworkforchineselandscapepainting AT yuyang ahybridattentiongenerativeadversarialnetworkforchineselandscapepainting AT chizhang ahybridattentiongenerativeadversarialnetworkforchineselandscapepainting AT ruolinshi ahybridattentiongenerativeadversarialnetworkforchineselandscapepainting AT qiongshuailyu hybridattentiongenerativeadversarialnetworkforchineselandscapepainting AT nazhao hybridattentiongenerativeadversarialnetworkforchineselandscapepainting AT zhiyuansun hybridattentiongenerativeadversarialnetworkforchineselandscapepainting AT yuyang hybridattentiongenerativeadversarialnetworkforchineselandscapepainting AT chizhang hybridattentiongenerativeadversarialnetworkforchineselandscapepainting AT ruolinshi hybridattentiongenerativeadversarialnetworkforchineselandscapepainting |