CASIA OpenIR  > 模式识别实验室
Pareidolia Face Reenactment
Song, Linsen1,2; Wu, Wayne3,4; Fu, Chaoyou1,2; Qian, Chen3; Loy, Chen Change4; He, Ran1,2
2021
Conference NameIEEE Conference on Computer Vision and Pattern Recognition
Conference Date2021.6.19
Conference Place线上
Abstract

We present a new application direction named Pareidolia Face Reenactment, which is defined as animating a static illusory face to move in tandem with a human face in the video. For the large differences between pareidolia face reenactment and traditional human face reenactment, two main challenges are introduced, i.e., shape variance and texture variance. In this work, we propose a novel Parametric Unsupervised Reenactment Algorithm to tackle these two challenges. Specifically, we propose to decompose the reenactment into three catenate processes: shape modeling, motion transfer and texture synthesis. With the decomposition, we introduce three crucial components, i.e., Parametric Shape Modeling, Expansionary Motion Transfer and Unsupervised Texture Synthesizer, to overcome the problems brought by the remarkably variances on pareidolia faces. Extensive experiments show the superior performance of our method both qualitatively and quantitatively. Code, model and data are available on our project page.

Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/48686
Collection模式识别实验室
Corresponding AuthorHe, Ran
Affiliation1.School of Artificial Intelligence, University of Chinese Academy of Sciences
2.NLPR & CRIPAC, CASIA
3.SenseTime Research
4.S-Lab, Nanyang Technological University
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Song, Linsen,Wu, Wayne,Fu, Chaoyou,et al. Pareidolia Face Reenactment[C],2021.
Files in This Item: Download All
File Name/Size DocType Version Access License
CVPR_PFR.pdf(5601KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Song, Linsen]'s Articles
[Wu, Wayne]'s Articles
[Fu, Chaoyou]'s Articles
Baidu academic
Similar articles in Baidu academic
[Song, Linsen]'s Articles
[Wu, Wayne]'s Articles
[Fu, Chaoyou]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Song, Linsen]'s Articles
[Wu, Wayne]'s Articles
[Fu, Chaoyou]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: CVPR_PFR.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.