Toward U-Net-based GANs for Diverse Facial Image Synthesis from Sketch

W. Phusomsai, Y. Limpiyakorn
{"title":"Toward U-Net-based GANs for Diverse Facial Image Synthesis from Sketch","authors":"W. Phusomsai, Y. Limpiyakorn","doi":"10.1145/3424311.3424323","DOIUrl":null,"url":null,"abstract":"Face physical changes may result from aging, surgery, or disguise. The criminal suspects conceal their identity with false appearances such as wearing a wig, glasses, beard and mustache. This research benefits the generation of various fictitious appearances of the suspects or facial changes of lost persons. The technique of GANs is applied for synthesizing a color image from a sketch. The output image can be varied in five facial attributes with a toggle: bald, makeup, straight hair, wearing glasses, beard and mustache. The approach enhances the Generator of StarGan2 with the U-Net architecture. The experiments were carried out to evaluate the performance of the proposed model compared to that of StarGan2. FID scores are used for measuring the quality of the generated images. The FID scores measured on the test data reported about 40% less than that of the baseline model and the synthesized images with varied facial attributes look natural and realistic.","PeriodicalId":330920,"journal":{"name":"Proceedings of the 2020 International Conference on Internet Computing for Science and Engineering","volume":"34 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2020 International Conference on Internet Computing for Science and Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3424311.3424323","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Face physical changes may result from aging, surgery, or disguise. The criminal suspects conceal their identity with false appearances such as wearing a wig, glasses, beard and mustache. This research benefits the generation of various fictitious appearances of the suspects or facial changes of lost persons. The technique of GANs is applied for synthesizing a color image from a sketch. The output image can be varied in five facial attributes with a toggle: bald, makeup, straight hair, wearing glasses, beard and mustache. The approach enhances the Generator of StarGan2 with the U-Net architecture. The experiments were carried out to evaluate the performance of the proposed model compared to that of StarGan2. FID scores are used for measuring the quality of the generated images. The FID scores measured on the test data reported about 40% less than that of the baseline model and the synthesized images with varied facial attributes look natural and realistic.
基于u - net的人脸图像合成算法研究
面部的生理变化可能是由于衰老、手术或伪装造成的。犯罪嫌疑人通过戴假发、戴眼镜、蓄胡须等伪装来掩盖自己的身份。这项研究有利于生成各种虚构的嫌疑人或失踪者的面部变化。将gan技术应用于从草图合成彩色图像。输出的图像可以切换为五种面部属性:秃顶、化妆、直发、戴眼镜、胡须和胡子。该方法利用U-Net架构增强了StarGan2的生成器。通过实验,将该模型与StarGan2模型进行了比较。FID分数用于测量生成图像的质量。根据测试数据测量的FID分数比基线模型低约40%,具有不同面部属性的合成图像看起来自然而真实。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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:604180095
Book学术官方微信