A Style Transfer Method for Chinese Landscape Painting Based on Detail Feature Extraction and Fusion

The goal of Chinese painting image style transfer is to render a real landscape scene image with Chinese painting artistic features, guided by a style reference, while maintaining the original, realistic scene image content. Recently, due to the rapid development of deep learning, convolutional neur...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinghao HU, Guohua GENG, Meijun XIONG, Siyi LI, Yuhe ZHANG
Format: Article
Language:English
Published: Editorial Department of Journal of Sichuan University (Engineering Science Edition) 2025-01-01
Series:工程科学与技术
Subjects:
Online Access:http://jsuese.scu.edu.cn/thesisDetails#10.12454/j.jsuese.202300295
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850070498240626688
author Jinghao HU
Guohua GENG
Meijun XIONG
Siyi LI
Yuhe ZHANG
author_facet Jinghao HU
Guohua GENG
Meijun XIONG
Siyi LI
Yuhe ZHANG
author_sort Jinghao HU
collection DOAJ
description The goal of Chinese painting image style transfer is to render a real landscape scene image with Chinese painting artistic features, guided by a style reference, while maintaining the original, realistic scene image content. Recently, due to the rapid development of deep learning, convolutional neural networks (CNNs) and adversarial generative networks (GANs) have almost dominated image generation tasks, including style transfer. However, several uncontrollable problems persist, such as the loss of some semantics during the style transfer process, model collapse in GAN network training, and the checkerboard effect in CNN-based style transfer methods. The visual transformer model provides a new solution for image processing tasks, but its training requires a large amount of data and involves significant computational complexity. A Chinese landscape painting style transfer network, SSTR (swin style transfer transformer), is proposed based on the fusion of detailed feature extraction to address these issues and generate high-quality Chinese paintings. This approach introduces the Swin–Transformer within the StyTr<sup>2</sup> network framework and uses the visual transformer to preserve the features of landscapes. In addition, the layered architecture of the Swin–Transformer and the sliding window attention mechanism are utilized to extract finer details of the artistic features of landscape paintings while reducing the model’s training complexity. Finally, a CNN decoder is incorporated after the Swin–Transformer decoder to refine the resulting image. The public visual dataset COCO and a public landscape painting dataset are employed for training, validation, and testing, with the results compared to several baseline methods. The experimental findings demonstrated that SSTR outperforms StyTr<sup>2</sup> regarding style loss for the Chinese landscape painting style transfer task, showing superior feature extraction capabilities and image generation performance
format Article
id doaj-art-5fc607eba9ca40fdb42c655dd550da37
institution DOAJ
issn 2096-3246
language English
publishDate 2025-01-01
publisher Editorial Department of Journal of Sichuan University (Engineering Science Edition)
record_format Article
series 工程科学与技术
spelling doaj-art-5fc607eba9ca40fdb42c655dd550da372025-08-20T02:47:32ZengEditorial Department of Journal of Sichuan University (Engineering Science Edition)工程科学与技术2096-32462025-01-01579810659347192A Style Transfer Method for Chinese Landscape Painting Based on Detail Feature Extraction and FusionJinghao HUGuohua GENGMeijun XIONGSiyi LIYuhe ZHANGThe goal of Chinese painting image style transfer is to render a real landscape scene image with Chinese painting artistic features, guided by a style reference, while maintaining the original, realistic scene image content. Recently, due to the rapid development of deep learning, convolutional neural networks (CNNs) and adversarial generative networks (GANs) have almost dominated image generation tasks, including style transfer. However, several uncontrollable problems persist, such as the loss of some semantics during the style transfer process, model collapse in GAN network training, and the checkerboard effect in CNN-based style transfer methods. The visual transformer model provides a new solution for image processing tasks, but its training requires a large amount of data and involves significant computational complexity. A Chinese landscape painting style transfer network, SSTR (swin style transfer transformer), is proposed based on the fusion of detailed feature extraction to address these issues and generate high-quality Chinese paintings. This approach introduces the Swin–Transformer within the StyTr<sup>2</sup> network framework and uses the visual transformer to preserve the features of landscapes. In addition, the layered architecture of the Swin–Transformer and the sliding window attention mechanism are utilized to extract finer details of the artistic features of landscape paintings while reducing the model’s training complexity. Finally, a CNN decoder is incorporated after the Swin–Transformer decoder to refine the resulting image. The public visual dataset COCO and a public landscape painting dataset are employed for training, validation, and testing, with the results compared to several baseline methods. The experimental findings demonstrated that SSTR outperforms StyTr<sup>2</sup> regarding style loss for the Chinese landscape painting style transfer task, showing superior feature extraction capabilities and image generation performancehttp://jsuese.scu.edu.cn/thesisDetails#10.12454/j.jsuese.202300295computer visionStyle TransferVisual TransformerSwin–TransformerChinese paintingTwin-encoder
spellingShingle Jinghao HU
Guohua GENG
Meijun XIONG
Siyi LI
Yuhe ZHANG
A Style Transfer Method for Chinese Landscape Painting Based on Detail Feature Extraction and Fusion
工程科学与技术
computer vision
Style Transfer
Visual Transformer
Swin–Transformer
Chinese painting
Twin-encoder
title A Style Transfer Method for Chinese Landscape Painting Based on Detail Feature Extraction and Fusion
title_full A Style Transfer Method for Chinese Landscape Painting Based on Detail Feature Extraction and Fusion
title_fullStr A Style Transfer Method for Chinese Landscape Painting Based on Detail Feature Extraction and Fusion
title_full_unstemmed A Style Transfer Method for Chinese Landscape Painting Based on Detail Feature Extraction and Fusion
title_short A Style Transfer Method for Chinese Landscape Painting Based on Detail Feature Extraction and Fusion
title_sort style transfer method for chinese landscape painting based on detail feature extraction and fusion
topic computer vision
Style Transfer
Visual Transformer
Swin–Transformer
Chinese painting
Twin-encoder
url http://jsuese.scu.edu.cn/thesisDetails#10.12454/j.jsuese.202300295
work_keys_str_mv AT jinghaohu astyletransfermethodforchineselandscapepaintingbasedondetailfeatureextractionandfusion
AT guohuageng astyletransfermethodforchineselandscapepaintingbasedondetailfeatureextractionandfusion
AT meijunxiong astyletransfermethodforchineselandscapepaintingbasedondetailfeatureextractionandfusion
AT siyili astyletransfermethodforchineselandscapepaintingbasedondetailfeatureextractionandfusion
AT yuhezhang astyletransfermethodforchineselandscapepaintingbasedondetailfeatureextractionandfusion
AT jinghaohu styletransfermethodforchineselandscapepaintingbasedondetailfeatureextractionandfusion
AT guohuageng styletransfermethodforchineselandscapepaintingbasedondetailfeatureextractionandfusion
AT meijunxiong styletransfermethodforchineselandscapepaintingbasedondetailfeatureextractionandfusion
AT siyili styletransfermethodforchineselandscapepaintingbasedondetailfeatureextractionandfusion
AT yuhezhang styletransfermethodforchineselandscapepaintingbasedondetailfeatureextractionandfusion