{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:27:46Z","timestamp":1760059666926,"version":"build-2065373602"},"reference-count":33,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62272040","62201525","61972050","62172005","CUC24QT08"],"award-info":[{"award-number":["62272040","62201525","61972050","62172005","CUC24QT08"]}]},{"name":"Fundamental Research Funds for the Central Universities","award":["62272040","62201525","61972050","62172005","CUC24QT08"],"award-info":[{"award-number":["62272040","62201525","61972050","62172005","CUC24QT08"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>The image style transfer task aims to apply the style characteristics of a reference image to a content image, generating a new stylized result. While many existing methods focus on designing feature transfer modules and have achieved promising results, they often overlook the entanglement between content and style features after transfer, making effective separation challenging. To address this issue, we propose a Dual-Branch Decoupled Image Style Transfer Network (DBDST-Net) to better disentangle content and style representations. The network consists of two branches: a Content Feature Decoupling Branch, which captures fine-grained content structures for more precise content separation, and a Style Feature Decoupling Branch, which enhances sensitivity to style-specific attributes. To further improve the decoupling performance, we introduce a dense-regressive loss that minimizes the discrepancy between the original content image and the content reconstructed from the stylized output, thereby promoting the independence of content and style features while enhancing image quality. Additionally, to mitigate the limited availability of style data, we employ the Stable Diffusion model to generate stylized samples for data augmentation. Extensive experiments demonstrate that our method achieves a better balance between content preservation and style rendering compared to existing approaches.<\/jats:p>","DOI":"10.3390\/info16070561","type":"journal-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T13:06:17Z","timestamp":1751288777000},"page":"561","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DBDST-Net: Dual-Branch Decoupled Image Style Transfer Network"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6855-8321","authenticated-orcid":false,"given":"Na","family":"Su","sequence":"first","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China"},{"name":"School of Computer Science and Cybersecurity, Communication University of China, Beijing 100024, China"},{"name":"GraphOrigin (Beijing) Technology Co., Ltd., Beijing 100041, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingtao","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China"},{"name":"School of Computer Science and Cybersecurity, Communication University of China, Beijing 100024, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China"},{"name":"School of Computer Science and Cybersecurity, Communication University of China, Beijing 100024, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China"},{"name":"School of Computer Science and Cybersecurity, Communication University of China, Beijing 100024, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Pan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China"},{"name":"School of Computer Science and Cybersecurity, Communication University of China, Beijing 100024, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Meier, B.J. (1996, January 4\u20139). Painterly rendering for animation. Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, New Orleans, LA, USA.","key":"ref_1","DOI":"10.1145\/237170.237288"},{"doi-asserted-by":"crossref","unstructured":"Hertzmann, A., Jacobs, C.E., Oliver, N., Curless, B., and Salesin, D.H. (2001, January 12\u201317). Image analo-gies. Proceedings of the 28th Annual Conference on Computer Graphics Andinteractive Techniques, Los Angeles, CA, USA.","key":"ref_2","DOI":"10.1145\/383259.383295"},{"doi-asserted-by":"crossref","unstructured":"Efros, A.A., and Leung, T.K. (1999, January 20\u201327). Texture synthesis by nonparametric sam- pling. Proceedings of the 7th IEEE International Conference on Computer Vision, Kerkyra (Corfu), Greece.","key":"ref_3","DOI":"10.1109\/ICCV.1999.790383"},{"doi-asserted-by":"crossref","unstructured":"Wei, L.Y., and Levoy, M. (2000, January 23\u201328). Fast texture synthesis using treestructured vector quantiza- tion. Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, New Orleans, LA, USA.","key":"ref_4","DOI":"10.1145\/344779.345009"},{"doi-asserted-by":"crossref","unstructured":"Han, C., Risser, E., Ramamoorthi, R., and Grinspun, E. (2008, January 11\u201315). Multiscale texture synthesis. Proceedings of the ACM SIGGRAPH 2008, Los Angeles, CA, USA.","key":"ref_5","DOI":"10.1145\/1399504.1360650"},{"unstructured":"Gatys, L., Ecker, A.S., and Bethge, M. (2015, January 7\u201312). Texture synthesis using convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems, Montr\u00e9al, QC, Canada.","key":"ref_6"},{"doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., and Li, F.-F. (2016, January 8\u201316). Perceptual losses for real-time style transfer and super- resolution. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","key":"ref_7","DOI":"10.1007\/978-3-319-46475-6_43"},{"unstructured":"Ulyanov, D., Lebedev, V., Vedaldi, A., and Lempitsky, V. (2016, January 19\u201324). Texture networks: Feed-forward synthesis of textures and stylized images. Proceedings of the International Conference on Machine Learning (ICML), New York, NY, USA.","key":"ref_8"},{"doi-asserted-by":"crossref","unstructured":"Jing, Y., Liu, X., Ding, Y., Wang, X., Ding, E., Song, M., and Wen, S. (2020, January 7\u201312). Dynamic instance normalization for arbitrary style transfer. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.","key":"ref_9","DOI":"10.1609\/aaai.v34i04.5862"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3618342","article-title":"A unified arbitrary style transfer framework via adaptive contrastive learning","volume":"42","author":"Zhang","year":"2023","journal-title":"ACM Trans. Graph."},{"doi-asserted-by":"crossref","unstructured":"Deng, Y., Tang, F., Dong, W., Ma, C., Pan, X., Wang, L., and Xu, C. (2021, January 19\u201324). StyTr2: Image Style Transfer with Transformers. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","key":"ref_11","DOI":"10.1109\/CVPR52688.2022.01104"},{"unstructured":"Chen, J., Liu, G., and Chen, X. (2020). AnimeGAN: A novel lightweight GAN for photo animation. Artificial Intelligence Algorithms and Applications: 11th International Symposium, ISICA 2019, Guangzhou, China, November 16\u201317, 2019, Springer. Revised Selected Papers 11.","key":"ref_12"},{"doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhao, L., Zuo, Z., Li, A., Chen, H., Xing, W., and Lu, D. (2023, January 7\u201314). MicroAST: Towards super-fast ultra-resolution arbitrary style transfer. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.","key":"ref_13","DOI":"10.1609\/aaai.v37i3.25374"},{"unstructured":"Ruta, D.S., Gilbert, A., Collomosse, J.P., Shechtman, E., and Kolkin, N. (2023). Neat: Neural artistic tracing for beautiful style transfer. arXiv.","key":"ref_14"},{"doi-asserted-by":"crossref","unstructured":"Park, D.Y., and Lee, K.H. (2019, January 15\u201321). Arbitrary style transfer with style-attentional networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","key":"ref_15","DOI":"10.1109\/CVPR.2019.00603"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tang, F., Dong, W., Huang, H., Ma, C., Lee, T.Y., and Xu, C. (2022, January 8\u201311). Domain enhanced arbitrary image style transfer via contrastive learning. Proceedings of the ACM SIGGRAPH 2022 Conference Proceedings, Vancouver, BC, Canada.","key":"ref_16","DOI":"10.1145\/3528233.3530736"},{"key":"ref_17","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref_18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"Volume 33","author":"Larochelle","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhao, L., and Xing, W. (2023, January 2-6). Stylediffusion: Controllable disentangled style transfer via diffusion models. Proceedings of the IEEE\/CVF International Conference on Computer Vision., Paris, France.","key":"ref_19","DOI":"10.1109\/ICCV51070.2023.00706"},{"unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., and Chen, M. (2022). Hierarchical text-conditional image generation with clip latents. arXiv.","key":"ref_20"},{"doi-asserted-by":"crossref","unstructured":"Kang, M., Zhang, R., Barnes, C., Paris, S., Kwak, S., Park, J., Shechtman, E., Zhu, J.Y., and Park, T. (2024). Distilling diffusion models into conditional gans. European Conference on Computer Vision, Springer Nature.","key":"ref_21","DOI":"10.1007\/978-3-031-73390-1_25"},{"doi-asserted-by":"crossref","unstructured":"Ashikhmin, M. (2001, January 19\u201321). Synthesizing natural textures. Proceedings of the 2001 Symposium on Interactive 3D Graphics, Research Triangle Park, NC, USA.","key":"ref_22","DOI":"10.1145\/364338.364405"},{"doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22\u201329). Unpaired image-to-image translation using cycle-consistent adversarial networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","key":"ref_23","DOI":"10.1109\/ICCV.2017.244"},{"doi-asserted-by":"crossref","unstructured":"Chen, Y., Lai, Y.K., and Liu, Y.J. (2018). CartoonGAN: Generative Adversarial Networks for Photo Carbonization. Proceedings of the IEEE\/CVF Conference on Computer Vision & Pattern Recognition, Salt Lake City, UT, USA, 18\u201322 June 2018, IEEE.","key":"ref_24","DOI":"10.1109\/CVPR.2018.00986"},{"doi-asserted-by":"crossref","unstructured":"Lin, T., Ma, Z., Li, F., He, D., Li, X., Ding, E., Wang, N., Li, J., and Gao, X. (2021, January 19\u201325). Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Virtual.","key":"ref_25","DOI":"10.1109\/CVPR46437.2021.00510"},{"unstructured":"Li, S. (2024). Diffstyler: Diffusion-based localized image style transfer. arXiv.","key":"ref_26"},{"unstructured":"Trockman, A., and Kolter, J.Z. (2022). Patches are all you need?. arXiv.","key":"ref_27"},{"doi-asserted-by":"crossref","unstructured":"Kolkin, N., Salavon, J., and Shakhnarovich, G. (2019, January 15\u201321). Style transfer by relaxed optimal transport and self-similarity. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","key":"ref_28","DOI":"10.1109\/CVPR.2019.01029"},{"doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2022, January 19\u201324). High-resolution image synthesis with latent diffusion models. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","key":"ref_29","DOI":"10.1109\/CVPR52688.2022.01042"},{"doi-asserted-by":"crossref","unstructured":"Huang, X., and Belongie, S. (2017, January 22\u201329). Arbitrary style transfer in real-time with adaptive instance normalization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","key":"ref_30","DOI":"10.1109\/ICCV.2017.167"},{"doi-asserted-by":"crossref","unstructured":"Yoo, J., Uh, Y., Chun, S., Kang, B., and Ha, J.W. (2019). Photorealistic Style Transfer via Wavelet Trans- forms. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea, 27 October\u20132 November 2019, IEEE.","key":"ref_31","DOI":"10.1109\/ICCV.2019.00913"},{"doi-asserted-by":"crossref","unstructured":"Wen, L., Gao, C., and Zou, C. (2023, January 18\u201322). CAP-VSTNet: Content affinity preserved versatile style transfer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","key":"ref_32","DOI":"10.1109\/CVPR52729.2023.01755"},{"doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, J., Ji, Z., Bai, J., and Shan, S. (2023). Cclap: Controllable chinese landscape painting generation via latent diffusion model. Proceedings of the 2023 IEEE International Conference on Multimedia and Expo (ICME), Brisbane, QLD, Australia, 10\u201314 July 2023, IEEE.","key":"ref_33","DOI":"10.1109\/ICME55011.2023.00362"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/7\/561\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:01:43Z","timestamp":1760032903000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/7\/561"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":33,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["info16070561"],"URL":"https:\/\/doi.org\/10.3390\/info16070561","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2025,6,30]]}}}