Full Text:   <207>

Summary:  <35>

CLC number: 

On-line Access: 2025-06-25

Received: 2025-01-08

Revision Accepted: 2025-03-06

Crosschecked: 2025-06-25

Cited: 0

Clicked: 252

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Jiayi CAI

https://orcid.org/0009-0009-0532-0015

Xuping FENG

https://orcid.org/0000-0001-9575-6916

-   Go to

Article info.
Open peer comments

Journal of Zhejiang University SCIENCE B 2025 Vol.26 No.6 P.609-612

http://doi.org/10.1631/jzus.B2500012


Seeing the macro in the micro: a diffusion model-based approach for style transfer in cellular images


Author(s):  Jiayi CAI, Yong HE, Feng LIU, Byung-Ho KANG, Xuping FENG

Affiliation(s):  College of Biosystems Engineering and Food Science, Zhejiang University,Hangzhou310058,China; more

Corresponding email(s):   fengxp@zju.edu.cn

Key Words:  Cellular images, Style transfer, Diffusion model, Artistic expression


Share this article to: More <<< Previous Article|

Jiayi CAI, Yong HE, Feng LIU, Byung-Ho KANG, Xuping FENG. Seeing the macro in the micro: a diffusion model-based approach for style transfer in cellular images[J]. Journal of Zhejiang University Science B, 2025, 26(6): 609-612.

@article{title="Seeing the macro in the micro: a diffusion model-based approach for style transfer in cellular images",
author="Jiayi CAI, Yong HE, Feng LIU, Byung-Ho KANG, Xuping FENG",
journal="Journal of Zhejiang University Science B",
volume="26",
number="6",
pages="609-612",
year="2025",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.B2500012"
}

%0 Journal Article
%T Seeing the macro in the micro: a diffusion model-based approach for style transfer in cellular images
%A Jiayi CAI
%A Yong HE
%A Feng LIU
%A Byung-Ho KANG
%A Xuping FENG
%J Journal of Zhejiang University SCIENCE B
%V 26
%N 6
%P 609-612
%@ 1673-1581
%D 2025
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.B2500012

TY - JOUR
T1 - Seeing the macro in the micro: a diffusion model-based approach for style transfer in cellular images
A1 - Jiayi CAI
A1 - Yong HE
A1 - Feng LIU
A1 - Byung-Ho KANG
A1 - Xuping FENG
J0 - Journal of Zhejiang University Science B
VL - 26
IS - 6
SP - 609
EP - 612
%@ 1673-1581
Y1 - 2025
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.B2500012


Abstract: 
The internal structures of cells as the basic units of life are a major wonder of the microscopic world. cellular images provide an intriguing window to help explore and understand the composition and function of these structures. Scientific imagery combined with artistic expression can further expand the potential of imaging in educational dissemination and interdisciplinary applications. This study presents an innovative diffusion model-based approach for style transfer in cellular images, combining scientific rigor with artistic expression. By leveraging training-free large-scale pre-trained diffusion models, the proposed method integrates the intricate morphological and textural features of cellular images with diverse artistic styles. Key techniques such as the inversion of denoising diffusion implicit models (DDIMs), adaptive instance normalization (AdaIN), self-attention style injection, and attention temperature scaling ensure the preservation of cellular structures while enhancing visual expressiveness. The results showcase the potential of this strategy for interdisciplinary applications, enriching both the visualization and educational dissemination of cellular imagery through compelling storytelling and aesthetic appeal.

见微知著:基于扩散模型的细胞图像风格迁移方法

蔡家一1,何勇1,刘峰2,姜秉昊3,冯旭萍1
1浙江大学生物系统工程与食品科学学院,中国杭州市,310058
2南京农业大学生命科学学院,中国南京市,210095
3香港中文大学生命科学学院,中国香港,999077
摘要:细胞作为生命的基本单位,其内部结构展现出微观世界的无穷奥秘。细胞图像则可为我们提供一扇探索和理解这些结构组成与功能的奇妙窗口。将科学图像与艺术表达相结合,能进一步拓展图像在科普传播和跨学科应用中的潜力。本研究创新性地提出了一种基于扩散模型的细胞图像风格迁移方法,将科学的严谨性与艺术的表现力相融合。该方法利用免训练的大规模扩散模型,将细胞图像中复杂的形态和纹理特征与多样化的艺术风格相结合,通过引入去噪扩散隐式模型(DDIM)反演、自适应实例归一化(AdaIN)、自注意力风格注入以及注意力温度调控等关键技术,在增强视觉表现力的同时,确保细胞结构的完整性。相关研究结果展示了该策略在跨学科应用中的巨大潜力,为细胞图像的可视化和科普传播增添了更具美学和故事性的表现力。

关键词:细胞图像;风格迁移;扩散模型;艺术表达

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]ChungJ,HyunS,HeoJP,et al.,2024.Style injection in diffusion: a training-free approach for adapting large-scale diffusion models for style transfer.IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, p.8795-8805.

[2]GaoSW,LiuF,2019.Novel insights into cell cycle regulation of cell fate determination.J Zhejiang Univ-Sci B (Biomed & Biotechnol),20(6):467-475.

[3]KimB,ShinW,JungY,et al.,2024.Explicitly color-inspired neural style transfer using patchified adain.Comput Model Eng Sci,141(3):2143-2164.

[4]ShenF,2018.Six Chapters of a Floating Life.China Publishing House,Beijing, China, p.53-54(in Chinese).

[5]TumanyanN,GeyerM,BagonS,et al.,2023.Plug-and-play diffusion features for text-driven image-to-image translation.IEEE/CVF Conference on Computer Vision and Pattern Recognition,Vancouver, p.1921-1930.

[6]ZhangTG,GaoY,GaoF,et al.,2021.Arbitrary style transfer with parallel self-attention.25th International Conference on Pattern Recognition,Milan, p.1406-1413.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2025 Journal of Zhejiang University-SCIENCE