Research on Latent Space-based Anime Face Style Transfer and Editing Techniques

Authors

Haixin Deng, Beijing University of Posts and Telecommunications, Beijing 100876, China
Fengquan Zhang, Beijing University of Posts and Telecommunications, Beijing 100876, China
Nan Wang, Beijing University of Posts and Telecommunications, Beijing 100876, China
Wancai Zhang, NARI Technology Co. , Ltd, Nanjing 211106, China
Jierui Lei, North China University of Technology, Beijing 100144, China

Abstract

Abstract: To address issues such as image distortion and style uniformity in existing anime style transfer networks within the field of image simulation, we propose the TGFE-TrebleStyleGAN (textguided facial editing with TrebleStyleGAN) for anime facial style transfer and editing. This framework leverages vector guidance within the latent space to generate facial imagery and incorporates a detail control module and a feature control module to constrain the aesthetic attributes of the generated images. The images generated by the transfer network serve as style control signals and constraints for fine-grained segmentation. Text-to-image generation technology captures correlations between styletransferred images and semantic information. Experimental results on both open-source datasets and self-constructed datasets with paired attribute tags for anime faces demonstrate that the proposed model reduces the FID score by 2.819 compared to DualStyleGAN, improve the SSIM and NIMA scores by 0.028 and 0.074 respectively. Combining style transfer and editing retains anime facial details while allowing flexible adjustments, minimizing distortion and enhancing feature consistency and style similarity.

Recommended Citation

Deng, Haixin; Zhang, Fengquan; Wang, Nan; Zhang, Wancai; and Lei, Jierui (2024) "Research on Latent Space-based Anime Face Style Transfer and Editing Techniques," Journal of System Simulation: Vol. 36: Iss. 12, Article 8.
DOI: 10.16182/j.issn1004731x.joss.24-FZ0797
Available at: https://dc-china-simulation.researchcommons.org/journal/vol36/iss12/8

First Page

2834

Last Page

2849

CLC

TP391.9

Recommended Citation

Deng Haixin, Zhang Fengquan, Wang Nan, et al. Research on Latent Space-based Anime Face Style Transfer and Editing Techniques[J]. Journal of System Simulation, 2024, 36(12): 2834-2849.

Corresponding Author

Zhang Fengquan

DOI

10.16182/j.issn1004731x.joss.24-FZ0797