使用StyleGAN2完成面膜,保留人物的特征

IF 0.6 4区 计算机科学 Q4 COMPUTER SCIENCE, INFORMATION SYSTEMS
Norihiko KAWAI, Hiroaki KOIKE
{"title":"使用StyleGAN2完成面膜,保留人物的特征","authors":"Norihiko KAWAI, Hiroaki KOIKE","doi":"10.1587/transinf.2023pcp0002","DOIUrl":null,"url":null,"abstract":"Due to the global outbreak of coronaviruses, people are increasingly wearing masks even when photographed. As a result, photos uploaded to web pages and social networking services with the lower half of the face hidden are less likely to convey the attractiveness of the photographed persons. In this study, we propose a method to complete facial mask regions using StyleGAN2, a type of Generative Adversarial Networks (GAN). In the proposed method, a reference image of the same person without a mask is prepared separately from a target image of the person wearing a mask. After the mask region in the target image is temporarily inpainted, the face orientation and contour of the person in the reference image are changed to match those of the target image using StyleGAN2. The changed image is then composited into the mask region while correcting the color tone to produce a mask-free image while preserving the person's features.","PeriodicalId":55002,"journal":{"name":"IEICE Transactions on Information and Systems","volume":null,"pages":null},"PeriodicalIF":0.6000,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Facial Mask Completion Using StyleGAN2 Preserving Features of the Person\",\"authors\":\"Norihiko KAWAI, Hiroaki KOIKE\",\"doi\":\"10.1587/transinf.2023pcp0002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Due to the global outbreak of coronaviruses, people are increasingly wearing masks even when photographed. As a result, photos uploaded to web pages and social networking services with the lower half of the face hidden are less likely to convey the attractiveness of the photographed persons. In this study, we propose a method to complete facial mask regions using StyleGAN2, a type of Generative Adversarial Networks (GAN). In the proposed method, a reference image of the same person without a mask is prepared separately from a target image of the person wearing a mask. After the mask region in the target image is temporarily inpainted, the face orientation and contour of the person in the reference image are changed to match those of the target image using StyleGAN2. The changed image is then composited into the mask region while correcting the color tone to produce a mask-free image while preserving the person's features.\",\"PeriodicalId\":55002,\"journal\":{\"name\":\"IEICE Transactions on Information and Systems\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.6000,\"publicationDate\":\"2023-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEICE Transactions on Information and Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1587/transinf.2023pcp0002\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEICE Transactions on Information and Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1587/transinf.2023pcp0002","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

由于新型冠状病毒的全球爆发,人们越来越多地戴着口罩拍照。因此,上传到网页和社交网络服务的照片中,遮住脸的下半部分不太可能传达出被拍照者的吸引力。在这项研究中,我们提出了一种使用StyleGAN2(一种生成式对抗网络(GAN))来完成人脸区域的方法。在所提出的方法中,将同一人不戴口罩的参考图像与戴口罩的人的目标图像分开制备。在目标图像中的掩模区域被临时填充后,使用StyleGAN2改变参考图像中人物的面部方向和轮廓,使其与目标图像相匹配。然后将改变后的图像合成到掩模区域,同时对色调进行校正,在保留人物特征的同时产生无掩模图像。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Facial Mask Completion Using StyleGAN2 Preserving Features of the Person
Due to the global outbreak of coronaviruses, people are increasingly wearing masks even when photographed. As a result, photos uploaded to web pages and social networking services with the lower half of the face hidden are less likely to convey the attractiveness of the photographed persons. In this study, we propose a method to complete facial mask regions using StyleGAN2, a type of Generative Adversarial Networks (GAN). In the proposed method, a reference image of the same person without a mask is prepared separately from a target image of the person wearing a mask. After the mask region in the target image is temporarily inpainted, the face orientation and contour of the person in the reference image are changed to match those of the target image using StyleGAN2. The changed image is then composited into the mask region while correcting the color tone to produce a mask-free image while preserving the person's features.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
IEICE Transactions on Information and Systems
IEICE Transactions on Information and Systems 工程技术-计算机:软件工程
CiteScore
1.80
自引率
0.00%
发文量
238
审稿时长
5.0 months
期刊介绍: Published by The Institute of Electronics, Information and Communication Engineers Subject Area: Mathematics Physics Biology, Life Sciences and Basic Medicine General Medicine, Social Medicine, and Nursing Sciences Clinical Medicine Engineering in General Nanosciences and Materials Sciences Mechanical Engineering Electrical and Electronic Engineering Information Sciences Economics, Business & Management Psychology, Education.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信