Face attribute editing network based on style-content disentanglement and convolutional attention

Jiansheng Cui, Quansheng Dou
{"title":"Face attribute editing network based on style-content disentanglement and convolutional attention","authors":"Jiansheng Cui, Quansheng Dou","doi":"10.1117/12.2685479","DOIUrl":null,"url":null,"abstract":"Face attribute editing is a research hotspot in the field of computer vision, which aims to modify a certain attribute of a face image to generate a new face image. The current methods based on Generative Adversarial Networks (GAN) have attribute entanglement problems and the implementation process is relatively complicated. To this end, this paper proposes a face attribute editing network based on style-content disentanglement and convolutional attention. Adding convolutional attention (CAT) module to the StyleGAN generator makes the network's control of content features no longer affected by the overall style of the image, and realizes the separation of spatial content and style from coarse to fine. In addition, the hierarchical CAT modules control different levels of attribute features, and changing the input of any layer of CAT can change the corresponding attribute features. The experimental results on the CelebA-HQ dataset show that the method in this paper can achieve disentangled editing of face attributes, and the scores of various indicators are better than the existing models.","PeriodicalId":305812,"journal":{"name":"International Conference on Electronic Information Technology","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Electronic Information Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1117/12.2685479","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Face attribute editing is a research hotspot in the field of computer vision, which aims to modify a certain attribute of a face image to generate a new face image. The current methods based on Generative Adversarial Networks (GAN) have attribute entanglement problems and the implementation process is relatively complicated. To this end, this paper proposes a face attribute editing network based on style-content disentanglement and convolutional attention. Adding convolutional attention (CAT) module to the StyleGAN generator makes the network's control of content features no longer affected by the overall style of the image, and realizes the separation of spatial content and style from coarse to fine. In addition, the hierarchical CAT modules control different levels of attribute features, and changing the input of any layer of CAT can change the corresponding attribute features. The experimental results on the CelebA-HQ dataset show that the method in this paper can achieve disentangled editing of face attributes, and the scores of various indicators are better than the existing models.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于风格-内容解纠缠和卷积关注的人脸属性编辑网络
人脸属性编辑是计算机视觉领域的一个研究热点,其目的是修改人脸图像的某一属性,生成新的人脸图像。目前基于生成对抗网络(GAN)的方法存在属性纠缠问题,且实现过程相对复杂。为此,本文提出了一种基于风格-内容解缠和卷积关注的人脸属性编辑网络。在StyleGAN生成器中加入卷积注意(convolutional attention, CAT)模块,使得网络对内容特征的控制不再受图像整体风格的影响,实现了空间内容与风格由粗到细的分离。此外,分层CAT模块控制不同层次的属性特征,改变CAT任意一层的输入都可以改变相应的属性特征。在CelebA-HQ数据集上的实验结果表明,本文方法可以实现人脸属性的去纠缠编辑,且各项指标得分优于现有模型。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Research on automatic information extraction and combination based on semantic association analysis Realization of position observation algorithm for permanent magnet synchronous motor based on fixed-point nonlinear flux model Face attribute editing network based on style-content disentanglement and convolutional attention Environmental risk perception and warning strategy of power metering laboratory based on LSTM network Study on elbow erosion of rotation valve groups in shale gas well stations
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1