掉期(金融)
计算机科学
忠诚
表达式(计算机科学)
面部表情
面子(社会学概念)
人工智能
机器学习
计算机视觉
模式识别(心理学)
高保真
电气工程
财务
工程类
社会学
经济
电信
程序设计语言
社会科学
作者
Bo Peng,Hong-Xing Fan,Wei Wang,Jing Dong,Siwei Lyu
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology
[Institute of Electrical and Electronics Engineers]
日期:2022-06-01
卷期号:32 (6): 3673-3684
被引量:19
标识
DOI:10.1109/tcsvt.2021.3106047
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI