Chinese Paper-Cutting Style Transfer via Vision Transformer
Style transfer technology has seen substantial attention in image synthesis, notably in applications like oil painting, digital printing, and Chinese landscape painting. However, it is often difficult to generate migrated images that retain the essence of paper-cutting art and have strong visual app...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/27/7/754 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849406885241815040 |
|---|---|
| author | Chao Wu Yao Ren Yuying Zhou Ming Lou Qing Zhang |
| author_facet | Chao Wu Yao Ren Yuying Zhou Ming Lou Qing Zhang |
| author_sort | Chao Wu |
| collection | DOAJ |
| description | Style transfer technology has seen substantial attention in image synthesis, notably in applications like oil painting, digital printing, and Chinese landscape painting. However, it is often difficult to generate migrated images that retain the essence of paper-cutting art and have strong visual appeal when trying to apply the unique style of Chinese paper-cutting art to style transfer. Therefore, this paper proposes a new method for Chinese paper-cutting style transformation based on the Transformer, aiming at realizing the efficient transformation of Chinese paper-cutting art styles. Specifically, the network consists of a frequency-domain mixture block and a multi-level feature contrastive learning module. The frequency-domain mixture block explores spatial and frequency-domain interaction information, integrates multiple attention windows along with frequency-domain features, preserves critical details, and enhances the effectiveness of style conversion. To further embody the symmetrical structures and hollowed hierarchical patterns intrinsic to Chinese paper-cutting, the multi-level feature contrastive learning module is designed based on a contrastive learning strategy. This module maximizes mutual information between multi-level transferred features and content features, improves the consistency of representations across different layers, and thus accentuates the unique symmetrical aesthetics and artistic expression of paper-cutting. Extensive experimental results demonstrate that the proposed method outperforms existing state-of-the-art approaches in both qualitative and quantitative evaluations. Additionally, we created a Chinese paper-cutting dataset that, although modest in size, represents an important initial step towards enriching existing resources. This dataset provides valuable training data and a reference benchmark for future research in this field. |
| format | Article |
| id | doaj-art-2b1d4370426348669f44d9b8adcafb53 |
| institution | Kabale University |
| issn | 1099-4300 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj-art-2b1d4370426348669f44d9b8adcafb532025-08-20T03:36:14ZengMDPI AGEntropy1099-43002025-07-0127775410.3390/e27070754Chinese Paper-Cutting Style Transfer via Vision TransformerChao Wu0Yao Ren1Yuying Zhou2Ming Lou3Qing Zhang4Engineering Training Center, Nanjing Vocational University of Industry Technology, Nanjing 210023, ChinaAcademy of Art and Design, Anhui University of Technology, Ma’anshan 243002, ChinaAcademy of Art and Design, Anhui University of Technology, Ma’anshan 243002, ChinaAcademy of Art and Design, Anhui University of Technology, Ma’anshan 243002, ChinaAcademy of Art and Design, Anhui University of Technology, Ma’anshan 243002, ChinaStyle transfer technology has seen substantial attention in image synthesis, notably in applications like oil painting, digital printing, and Chinese landscape painting. However, it is often difficult to generate migrated images that retain the essence of paper-cutting art and have strong visual appeal when trying to apply the unique style of Chinese paper-cutting art to style transfer. Therefore, this paper proposes a new method for Chinese paper-cutting style transformation based on the Transformer, aiming at realizing the efficient transformation of Chinese paper-cutting art styles. Specifically, the network consists of a frequency-domain mixture block and a multi-level feature contrastive learning module. The frequency-domain mixture block explores spatial and frequency-domain interaction information, integrates multiple attention windows along with frequency-domain features, preserves critical details, and enhances the effectiveness of style conversion. To further embody the symmetrical structures and hollowed hierarchical patterns intrinsic to Chinese paper-cutting, the multi-level feature contrastive learning module is designed based on a contrastive learning strategy. This module maximizes mutual information between multi-level transferred features and content features, improves the consistency of representations across different layers, and thus accentuates the unique symmetrical aesthetics and artistic expression of paper-cutting. Extensive experimental results demonstrate that the proposed method outperforms existing state-of-the-art approaches in both qualitative and quantitative evaluations. Additionally, we created a Chinese paper-cutting dataset that, although modest in size, represents an important initial step towards enriching existing resources. This dataset provides valuable training data and a reference benchmark for future research in this field.https://www.mdpi.com/1099-4300/27/7/754Chinese paper-cuttingstyle transferfrequency-domain mixture encoderfeature contrastive learning |
| spellingShingle | Chao Wu Yao Ren Yuying Zhou Ming Lou Qing Zhang Chinese Paper-Cutting Style Transfer via Vision Transformer Entropy Chinese paper-cutting style transfer frequency-domain mixture encoder feature contrastive learning |
| title | Chinese Paper-Cutting Style Transfer via Vision Transformer |
| title_full | Chinese Paper-Cutting Style Transfer via Vision Transformer |
| title_fullStr | Chinese Paper-Cutting Style Transfer via Vision Transformer |
| title_full_unstemmed | Chinese Paper-Cutting Style Transfer via Vision Transformer |
| title_short | Chinese Paper-Cutting Style Transfer via Vision Transformer |
| title_sort | chinese paper cutting style transfer via vision transformer |
| topic | Chinese paper-cutting style transfer frequency-domain mixture encoder feature contrastive learning |
| url | https://www.mdpi.com/1099-4300/27/7/754 |
| work_keys_str_mv | AT chaowu chinesepapercuttingstyletransferviavisiontransformer AT yaoren chinesepapercuttingstyletransferviavisiontransformer AT yuyingzhou chinesepapercuttingstyletransferviavisiontransformer AT minglou chinesepapercuttingstyletransferviavisiontransformer AT qingzhang chinesepapercuttingstyletransferviavisiontransformer |