UV Completion with Self-referenced Discrimination

Jiwoo Kang, Seongmin Lee, Sanghoon Lee
{"title":"UV Completion with Self-referenced Discrimination","authors":"Jiwoo Kang, Seongmin Lee, Sanghoon Lee","doi":"10.2312/egs.20201018","DOIUrl":null,"url":null,"abstract":"A facial UV map is used in many applications such as facial reconstruction, synthesis, recognition, and editing. However, it is difficult to collect a number of the UVs needed for accuracy using 3D scan device, or a multi-view capturing system should be required to construct the UV. An occluded facial UV with holes could be obtained by sampling an image after fitting a 3D facial model by recent alignment methods. In this paper, we introduce a facial UV completion framework to train the deep neural network with a set of incomplete UV textures. By using the fact that the facial texture distributions of the left and right half-sides are almost equal, we devise an adversarial network to model the complete UV distribution of the facial texture. Also, we propose the self-referenced discrimination scheme that uses the facial UV completed from the generator for training real distribution. It is demonstrated that the network can be trained to complete the facial texture with incomplete UVs comparably to when utilizing the ground-truth UVs. CCS Concepts • Computing methodologies → Image processing; Neural networks;","PeriodicalId":72958,"journal":{"name":"Eurographics ... Workshop on 3D Object Retrieval : EG 3DOR. Eurographics Workshop on 3D Object Retrieval","volume":"64 1","pages":"61-64"},"PeriodicalIF":0.0000,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Eurographics ... Workshop on 3D Object Retrieval : EG 3DOR. Eurographics Workshop on 3D Object Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2312/egs.20201018","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7

Abstract

A facial UV map is used in many applications such as facial reconstruction, synthesis, recognition, and editing. However, it is difficult to collect a number of the UVs needed for accuracy using 3D scan device, or a multi-view capturing system should be required to construct the UV. An occluded facial UV with holes could be obtained by sampling an image after fitting a 3D facial model by recent alignment methods. In this paper, we introduce a facial UV completion framework to train the deep neural network with a set of incomplete UV textures. By using the fact that the facial texture distributions of the left and right half-sides are almost equal, we devise an adversarial network to model the complete UV distribution of the facial texture. Also, we propose the self-referenced discrimination scheme that uses the facial UV completed from the generator for training real distribution. It is demonstrated that the network can be trained to complete the facial texture with incomplete UVs comparably to when utilizing the ground-truth UVs. CCS Concepts • Computing methodologies → Image processing; Neural networks;
紫外线补全与自我参考歧视
人脸UV图用于人脸重建、合成、识别和编辑等许多应用。然而,使用3D扫描设备很难收集精度所需的大量UV,或者需要多视图捕获系统来构建UV。利用最新的对准方法对三维人脸模型进行拟合后,对图像进行采样,即可得到带孔遮挡的人脸UV。本文引入一种人脸UV补全框架,利用一组不完整的UV纹理对深度神经网络进行训练。利用人脸左右半边的纹理分布几乎相等的事实,我们设计了一个对抗网络来模拟人脸纹理的完整UV分布。此外,我们还提出了一种自参考识别方案,该方案使用从生成器完成的面部UV来训练真实分布。实验证明,与使用真实紫外时相比,该网络可以在不完全紫外下完成面部纹理的训练。•计算方法→图像处理;神经网络;
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:481959085
Book学术官方微信