Style Transfer Network for Generating Opera Makeup Details

Authors

Fengquan Zhang, School of Digital Media and Design Arts, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaFollow
Duo Cao, School of Information Science, North China University of Technology, Beijing 100144, China
Xiaohan Ma, School of Information Science, North China University of Technology, Beijing 100144, China
Baijun Chen, School of Digital Media and Design Arts, Beijing University of Posts and Telecommunications, Beijing 100876, China
Jiangxiao Zhang, School of Mathematics and Information Technology Institute, Xingtai University, Xingtai 054001, China

Abstract

Abstract: To address the problem of the loss of local style details in cross-domain image simulation, a ChinOperaGAN network framework suitable for opera makeup is designed from the perspective of protecting the excellent traditional culture. In order to solve the style translation of differences in two image domains, multiple overlapping local adversarial discriminators are proposed in the generative adversarial network. Since paired opera makeup data are difficult to obtain, a synthetic image is generated by combining the source image makeup mapping to effectively guide the transfer of local makeup details between images. In view of the characteristics of opera makeup with strong and distinct colors, a loss function is introduced to ensure the generation of makeup images with high-frequency details. Experiments are carried out on open-source datasets and self-built datasets, and the classical method is better than the traditional classical method through qualitative and quantitative analysis. The experimental results show that the proposed method transfers the makeup by unsupervised adversarial learning and generates opera makeup style images with high-frequency details well. It can realize image transfer with consistent image features and matching style and can be applied to digital system simulation of intangible cultural heritage.

Recommended Citation

Zhang, Fengquan; Cao, Duo; Ma, Xiaohan; Chen, Baijun; and Zhang, Jiangxiao (2023) "Style Transfer Network for Generating Opera Makeup Details," Journal of System Simulation: Vol. 35: Iss. 9, Article 20.
DOI: 10.16182/j.issn1004731x.joss.22-1499
Available at: https://dc-china-simulation.researchcommons.org/journal/vol35/iss9/20

First Page

2064

Last Page

2076

CLC

TP391.41

Recommended Citation

Zhang Fengquan, Cao Duo, Ma Xiaohan, et al. Style Transfer Network for Generating Opera Makeup Details[J]. Journal of System Simulation, 2023, 35(9): 2064-2076.

DOI

10.16182/j.issn1004731x.joss.22-1499