基于深度生成模型的人脸编辑研究进展  

Research Progress of Face Editing Based on Deep Generative Model

作　　者：唐雨潇 王斌君[1] TANG Yu-xiao;WANG Bin-jun(College of Information Network Security,People's Public Security University of China,Beijing 100038,China)

机构地区：[1]中国人民公安大学信息网络安全学院,北京100038

出　　处：《计算机科学》2022年第2期51-61,共11页Computer Science

基　　金：国家自然科学基金(62076154,62106131,62106134);中央引导地方科技发展资金项目(YDZX20201400001224);山西省国际科技合作计划项目(201903D421050)。

摘　　要：人脸编辑广泛应用于公安追逃、人脸美化等领域,传统的统计学方法、基于原型的方法是解决人脸编辑的主要手段,然而这些传统技术面临着操作难度大、计算成本高等问题。近年来,深度学习快速发展,特别是生成网络的出现,为人脸编辑提供了一种全新的思路,采用深度生成模型的人脸编辑技术具有速度快、模型泛化能力强的优势。为总结近年利用深度生成模型解决人脸编辑问题的相关理论与研究,首先介绍了基于深度生成模型的人脸编辑技术采用的网络框架与原理;然后对该项技术所运用的方法进行详述,将其归纳为图像翻译、在网络内部引入条件信息、操纵潜在空间3个方面;最后总结了该项技术所面临的身份一致性、属性解耦、属性编辑精确性的挑战,并指出未来该方向亟待解决的若干问题。Face editing is widely used in public security pursuits,face beautification and other fields.Traditional statistical me-thods and prototype-based methods are the main means to solve face editing.However,these traditional technologies face pro-blems such as difficult operation and high computational cost.In recent years,with the development of deep learning,especially the emergence of generative networks,a brand new idea has been provided for face editing.Face editing technology using deep generative models has the advantages of fast speed and strong model generalization ability.In order to summarize and review the related theories and research on the use of deep generative models to solve the problem of face editing in recent years,firstly,we introduce the network framework and principles adopted by the face editing technology based on deep generative models.Then,the methods used in this technology are described in detail,and we summarize it into three aspects:image translation,introduction of conditional information within the network,and manipulation of potential space.Finally,we summarize the challenges faced by this technology,which consists of identity consistency,attribute decoupling,and attribute editing accuracy,and point out the issues of the technology that need to be resolved urgently in future.

关 键 词：人脸编辑 生成对抗网络 变分自编码器 深度学习 潜在空间 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]