基于改进StarGAN-V2的多域面部表情转移  

Multi-domain Facial Expression Transfer Based on Improved StarGAN-V2

作　　者：王春东 张浩龙 WANG Chun-Dong;ZHANG Hao-Long(School of Computer Science and Engineering,Tianjin University of Technology,Tianjin 300384,China;National Engineering Laboratory for Computer Virus Prevention and Control,Tianjin 300384,China)

机构地区：[1]天津理工大学计算机科学与工程学院,天津300384 [2]计算机病毒防治技术国家工程实验室,天津300384

出　　处：《计算机系统应用》2025年第4期228-238,共11页Computer Systems & Applications

基　　金：国家重点研发计划“区块链”重点专项(2023YFB2703900);天津市科委重大专项(15ZXDSGX00030)。

摘　　要：多域面部表情转移涉及不同图像之间的相互转换,目的是生成具有源面部表情和目标面部身份特征的高逼真度面部图像,解决传统方法生成图像相似度高和图像真实性低的问题.本文提出了一种基于改进StarGAN-V2的多域面部表情转移模型,该模型由生成器、鉴别器、映射网络和风格编码器组成,引入了空间注意力机制,并将循环一致性损失改进为对抗性循环一致性损失,在生成器后增加了一个新的域反馈鉴别器.该改进后的Star GAN-V2模型能够基于源图像和目标图像,生成具有源面部表情和目标面部身份特征的高逼真度面部图像.实验结果表明,改进后的模型潜在引导合成和参考引导合成FID值为11.9与17.4,LPIPS值为0.491与0.426,均优于对照模型,改进后的模型解决了图像相似度高的问题,生成的图像也更加真实.Multi-domain facial expression transfer entails the mutual transformation between different images to generate high-fidelity facial images with source facial expressions and target facial identity features,solve the problem of high similarity and low image authenticity of images generated by traditional methods.This study proposes a multi-domain facial expression transfer model based on the improved StarGAN-V2.The model consists of a generator,a discriminator,a mapping network,and a style encoder.The spatial attention mechanism is introduced,and the cycle consistency loss is upgraded to an adversarial cycle consistency loss.A new domain feedback discriminator is appended after the generator.The improved StarGAN-V2 model can generate high-fidelity facial images with source facial expressions and target facial identity features based on the source and target images.Experimental results show that for the improved model,the FID values of latent guided synthesis and reference guided synthesis are 11.9 and 17.4 respectively,and the LPIPS values are 0.491 and 0.426 respectively.These values are better than those of the control model.The improved model solves the problem of high image similarity and generates more realistic images.

关 键 词：面部表情转移 StarGAN-V2 多域风格 网络安全 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]