Privacy-Preserving Face and Hair Swapping in Real-Time With a GAN-Generated Face Image

被引:3
作者
Tran, Dinh Tuan [1 ]
Phung, Duc Tung [2 ]
Duong, Duc Manh [2 ]
Inoue, Katsumi [3 ]
Lee, Joo-Ho [1 ]
Nguyen, Anh Quang [2 ]
机构
[1] Ritsumeikan Univ, Coll Informat Sci & Engn, Kusatsu 5258577, Japan
[2] Hanoi Univ Sci & Technol, Sch Elect & Elect Engn, Hanoi 100000, Vietnam
[3] Natl Inst Informat, Tokyo 1018430, Japan
来源
IEEE ACCESS | 2024年 / 12卷
关键词
Face recognition; Privacy; Real-time systems; Data privacy; Interviews; Online services; Image processing; Anonymization; online interview; face swapping; hair swapping; synthetic images;
D O I
10.1109/ACCESS.2024.3420452
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In contemporary scenarios, privacy is paramount, especially in applications such as video interviews. This study introduces a privacy-focused real-time face and hair swapping method designed to conceal identity while retaining essential facial attributes of the original subject. Unlike conventional face swapping methods that rely on a reference image of a realistic person, our proposed method eliminates this need for enhanced privacy. Instead, this work introduces the use of a synthetic face image generated by a Generative Adversarial Networks (GANs), offering a secure solution that addresses the heightened importance of privacy in face and hair swapping applications, particularly in sensitive contexts like interviews. The proposed method in this study is an efficient 3-phase pipeline capable of performing these operations in real-time from a standard camera. This novel approach ensures a seamless integration of anonymity and attribute preservation, paving the way for more discreet and privacy-centric real-time face and hair swapping technologies, not only in video interviews but also in entertainment and communication applications such as video teleconferencing and streaming media.
引用
收藏
页码:179265 / 179280
页数:16
相关论文
共 37 条
[1]   FaceOff: A Video-to-Video Face Swapping System [J].
Agarwal, Aditya ;
Sen, Bipasha ;
Mukhopadhyay, Rudrabha ;
Namboodiri, Vinay ;
Jawahar, C. V. .
2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, :3484-3493
[2]  
[Anonymous], [22] [Online]. Available: https://github.com/pytorch (6/26/2018)
[3]  
[Anonymous], 2020, [121] https://github.com/WIKI2020/FacePose_pytorch, December 2020. [Online
[4]  
accessed 10-May-2021].
[5]  
Brock A, 2019, Arxiv, DOI arXiv:1809.11096
[6]   VGGFace2: A dataset for recognising faces across pose and age [J].
Cao, Qiong ;
Shen, Li ;
Xie, Weidi ;
Parkhi, Omkar M. ;
Zisserman, Andrew .
PROCEEDINGS 2018 13TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE & GESTURE RECOGNITION (FG 2018), 2018, :67-74
[7]  
Cao W., 2023, P IEEE 17 INT C AUT, P1
[8]   SimSwap: An Efficient Framework For High Fidelity Face Swapping [J].
Chen, Renwang ;
Chen, Xuanhong ;
Ni, Bingbing ;
Ge, Yanhao .
MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, :2003-2011
[9]   ArcFace: Additive Angular Margin Loss for Deep Face Recognition [J].
Deng, Jiankang ;
Guo, Jia ;
Xue, Niannan ;
Zafeiriou, Stefanos .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :4685-4694
[10]  
Goodfellow IJ, 2014, ADV NEUR IN, V27, P2672