A Unified Framework for High Fidelity Face Swap and Expression Reenactment

doi:10.1109/TCSVT.2021.3106047

CASIA OpenIR > 智能感知与计算研究中心

	A Unified Framework for High Fidelity Face Swap and Expression Reenactment
	Peng, Bo1,2 ; Fan, Hongxing 1; Wang, Wei1 ; Dong, Jing1 ; Lyu, Siwei 3
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN	1051-8215
	2022-06-01
卷号	32 期号:6 页码:3673-3684
通讯作者	Dong, Jing(jdong@nlpr.ia.ac.cn)
摘要	Face manipulation techniques improve fast with the development of powerful image generation models. Two particular face manipulation methods, namely face swap and expression reenactment attract much attention for their flexibility and ease to generate high quality synthesis results. Recently, these two subjects are actively studied. However, most existing methods treat the two tasks separately, ignoring their underlying similarity. In this paper, we propose to tackle the two problems within a unified framework that achieves high quality synthesis results. The enabling component for our unified framework is the clean disentanglement of 3D pose, shape, and expression factors and then recombining them for different tasks accordingly. We then use the same set of 2D representations for face swap and expression reenactment tasks that are input to a common image translation model to directly generate the final synthetic images. Once trained, the proposed model can accomplish both face swap and expression reenactment tasks for previously unseen subjects. Comprehensive experiments and comparisons show that the proposed method achieves high fidelity results in multiple aspects, and it is especially good at faithfully preserving source facial shape in the face swap task, and accurately transferring facial movements in the expression reenactment task.
关键词	Faces Task analysis Videos Shape Three-dimensional displays Face recognition Information integrity Face swap expression reenactment 3DMM video manipulation
DOI	10.1109/TCSVT.2021.3106047
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China (NSFC)[61902400] ; National Natural Science Foundation of China (NSFC)[U19B2038] ; National Natural Science Foundation of China (NSFC)[61972395] ; National Natural Science Foundation of China (NSFC)[61772529] ; National Natural Science Foundation of China (NSFC)[62076240] ; Beijing Natural Science Foundation[4192058]
项目资助者	National Natural Science Foundation of China (NSFC) ; Beijing Natural Science Foundation
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000805833400031
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：20[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/49585
专题	智能感知与计算研究中心
通讯作者	Dong, Jing
作者单位	1.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp CRIPAC, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Informat Engn, State Key Lab Informat Secur, Beijing 100093, Peoples R China 3.Univ Buffalo State Univ New York Buffalo, Sch Engn & Appl Sci, Buffalo, NY 14260 USA
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Peng, Bo,Fan, Hongxing,Wang, Wei,et al. A Unified Framework for High Fidelity Face Swap and Expression Reenactment[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2022,32(6):3673-3684.
APA	Peng, Bo,Fan, Hongxing,Wang, Wei,Dong, Jing,&Lyu, Siwei.(2022).A Unified Framework for High Fidelity Face Swap and Expression Reenactment.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,32(6),3673-3684.
MLA	Peng, Bo,et al."A Unified Framework for High Fidelity Face Swap and Expression Reenactment".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 32.6(2022):3673-3684.