Previous Article in Journal
Predicting the Next Location of Urban Individuals via a Representation-Enhanced Multi-View Learning Network
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Diffusion Model-Based Cartoon Style Transfer for Real-World 3D Scenes

by
Yuhang Chen
1,
Haoran Zhou
2,*,
Jing Chen
1,
Nai Yang
1,
Jing Zhao
3 and
Yi Chao
1
1
School of Geography and Information Engineering, China University of Geosciences, Wuhan 430078, China
2
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China
3
Provincial Surveying and Mapping Production Archives of Hubei, Wuhan 430074, China
*
Author to whom correspondence should be addressed.
ISPRS Int. J. Geo-Inf. 2025, 14(8), 303; https://doi.org/10.3390/ijgi14080303
Submission received: 9 May 2025 / Revised: 14 July 2025 / Accepted: 28 July 2025 / Published: 4 August 2025

Abstract

Traditional map style transfer methods are mostly based on GAN,which are either overly artistic at the expense of conveying information, or insufficiently aesthetic by simply changing the color scheme of the map image. These methods often struggle to balance style transfer with semantic preservation and lack consistency in their transfer effects. In recent years, diffusion models have made significant progress in the field of image processing and have shown great potential in image-style transfer tasks. Inspired by these advances, this paper presents a method for transferring real-world 3D scenes to a cartoon style without the need for additional input condition guidance. The method combines pre-trained LDM with LoRA models to achieve stable and high-quality style infusion. By integrating DDIM Inversion, ControlNet, and MultiDiffusion strategies, it achieves the cartoon style transfer of real-world 3D scenes through initial noise control, detail redrawing, and global coordination. Qualitative and quantitative analyses, as well as user studies, indicate that our method effectively injects a cartoon style while preserving the semantic content of the real-world 3D scene, maintaining a high degree of consistency in style transfer. This paper offers a new perspective for map style transfer.
Keywords: LDM; geographic scenes; stylization; semantic preservation; image maps LDM; geographic scenes; stylization; semantic preservation; image maps

Share and Cite

MDPI and ACS Style

Chen, Y.; Zhou, H.; Chen, J.; Yang, N.; Zhao, J.; Chao, Y. Diffusion Model-Based Cartoon Style Transfer for Real-World 3D Scenes. ISPRS Int. J. Geo-Inf. 2025, 14, 303. https://doi.org/10.3390/ijgi14080303

AMA Style

Chen Y, Zhou H, Chen J, Yang N, Zhao J, Chao Y. Diffusion Model-Based Cartoon Style Transfer for Real-World 3D Scenes. ISPRS International Journal of Geo-Information. 2025; 14(8):303. https://doi.org/10.3390/ijgi14080303

Chicago/Turabian Style

Chen, Yuhang, Haoran Zhou, Jing Chen, Nai Yang, Jing Zhao, and Yi Chao. 2025. "Diffusion Model-Based Cartoon Style Transfer for Real-World 3D Scenes" ISPRS International Journal of Geo-Information 14, no. 8: 303. https://doi.org/10.3390/ijgi14080303

APA Style

Chen, Y., Zhou, H., Chen, J., Yang, N., Zhao, J., & Chao, Y. (2025). Diffusion Model-Based Cartoon Style Transfer for Real-World 3D Scenes. ISPRS International Journal of Geo-Information, 14(8), 303. https://doi.org/10.3390/ijgi14080303

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop