Controllable Multi-Attribute Editing of High-Resolution Face Images | |
Deng, Qiyao1,3; Li, Qi1,2,3; Cao, Jie1,3; Liu, Yunfan1,3; Sun, Zhenan1,3 | |
刊名 | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY |
2021 | |
卷号 | 16期号:0页码:1410-1423 |
关键词 | Faces Image resolution Face recognition Wavelet transforms Generative adversarial networks Gallium nitride Computational modeling Face attribute editing face synthesis generative adversarial network |
ISSN号 | 1556-6013 |
DOI | 10.1109/TIFS.2020.3033184 |
英文摘要 | In recent years, significant progress has been achieved in face image editing due to the success of Generative Adversarial Network (GAN). However, state-of-the-art face editing methods mainly suffer from the following two limitations: 1) they are only applicable to face images with relative low-resolutions and 2) multi-attribute face editing may generate uncontrollable changes in non-target face attribute categories. To solve these problems, we propose a novel High-Quality Generative Adversarial Network (HQ-GAN) for controllable editing of multiple face attributes in high-resolution images. HQ-GAN has two novel ideas to break the limitations of resolution and controllability correspondingly: 1) fine-grained textures and realistic details of high-resolution face images are better preserved with the aid of textural features extracted by the wavelet transform module and 2) desired multi-attribute targets of face editing are emphasized using a weighted binary cross-entropy (BCE) loss so that the influence on non-target attributes is greatly reduced. To the best of our knowledge, HQ-GAN is the first attempt to achieve continuous editing of multiple face attributes on high-resolution images of the CelebA-HQ using only 28 000 training samples. Extensive qualitative results demonstrate the superiority of the proposed method in rendering realistic high-resolution face images with accurate attribute modification, and comprehensive quantitative results show that the proposed method significantly outperforms state-of-the-art face editing methods. |
资助项目 | National Key Research and Development Program of China[2020AAA0140002] ; Natural Science Foundation of China[U1836217] ; Natural Science Foundation of China[62076240] ; Natural Science Foundation of China[61721004] ; Natural Science Foundation of China[61427811] ; Natural Science Foundation of China[61702513] ; Artificial Intelligence Research, Chinese Academy of Sciences (CAS-AIR) ; Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project)[2019JZZY010119] |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000597145200006 |
资助机构 | National Key Research and Development Program of China ; Natural Science Foundation of China ; Artificial Intelligence Research, Chinese Academy of Sciences (CAS-AIR) ; Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project) |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/42701] |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | Sun, Zhenan |
作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Artificial Intelligence Res, Qingdao 266300, Peoples R China 3.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Deng, Qiyao,Li, Qi,Cao, Jie,et al. Controllable Multi-Attribute Editing of High-Resolution Face Images[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2021,16(0):1410-1423. |
APA | Deng, Qiyao,Li, Qi,Cao, Jie,Liu, Yunfan,&Sun, Zhenan.(2021).Controllable Multi-Attribute Editing of High-Resolution Face Images.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,16(0),1410-1423. |
MLA | Deng, Qiyao,et al."Controllable Multi-Attribute Editing of High-Resolution Face Images".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 16.0(2021):1410-1423. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论