期刊论文

Liang, Xiaoman(liangxm@hynu.edu.cn)

英文

Computers & Electrical Engineering

0045-7906

2022

104

108459

10.1016/j.compeleceng.2022.108459

This work was supported by the National Natural Science Foundation of China ( 61772179 ), Hunan Provincial Natural Science Foundation of China ( 2022JJ50016 , 2020JJ4152 ), the Science and Technology Innovation Program of Hunan Province ( 2016TP1020 ), Scientific Research Fund of Hunan Provincial Education Department ( 21B0649 ), Double First-Class University Project of Hunan Province (Xiangjiaotong [2018]469 ), Postgraduate Scientific Research Innovation Project of Hunan Province ( CX20190998 ), Degree and Postgraduate Education Reform Project of Hunan Province ( 2019JGYB266 , 2020JGZD072 ), Industry University Research Innovation Foundation of Ministry of Education Science and Technology Development Center ( 2020QT09 ), Hengyang Technology Innovation Guidance Projects ( 2020h052805 , Hengcaijiaozhi [2020]-67 ), Postgraduate Teaching Platform Project of Hunan Province (Xiangjiaotong [2019]370-321 ). The authors would also like to thank Gatys et al. [13] , Li and Wand [16] , Johnson et al. [35] , Zou et al. [21] , Liu et al. [36] , and Texler et al. [20] for sharing their codes, and VCG for providing images of the Peking Opera.

本校为第一机构

When using standard neural network transfer methods for portrait style transfer, semantically correct transfers often cannot be guaranteed; the texture details in the style examples tend to be ignored. This paper proposes a style transfer method for Peking Opera faces called POFMakeup. This method can transfer the style of a portrait with a Peking Opera face to another portrait. This method uses two guides, namely, a position guide and an appearance guide. The position guide ensures semantic consistency in the transfer process, while the appear...