CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
Low-frequency Guided Self-supervised Learning for High-fidelity 3D Face Reconstruction in the Wild
Wang, Pengrui1,2; Lin, Chunze3; Xu, Bo1; Che, Wujun1; Wang, Quan3
2020-07
Conference NameIEEE International Conference on Multimedia and Expo (ICME)
Conference Date2020-7-6~2020-7-10
Conference PlaceLondon, UK
Abstract

In this paper, we propose a low-frequency guided self-supervised learning method for high-fidelity 3D face reconstruction from an in-the-wild image. 
Unlike other self-supervised methods only using the color difference between the original image and the estimated image, we add low-frequency albedo information to enhance the self-supervised learning for more realistic albedo while insensitive to the non-skin regions. 
Specifically, based on a PCA albedo model, we first train a Boosting Network (B-Net) to provide illumination and intact albedo distribution. Then with above information, we learn an image-to-image non-linear Facial Albedo Network (FAN) by self-supervision to produce a high-fidelity albedo.
We further propose a Detail Recovering Network (DRN) to recover geometric details such as wrinkles.
FAN and DRN permit to reconstruct 3D faces with high-fidelity albedo and geometry details. 
Finally, experimental results demonstrate the effectiveness of the proposed method.

Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/40394
Collection数字内容技术与服务研究中心_听觉模型与认知计算
Corresponding AuthorChe, Wujun
Affiliation1.Institute of Automation, Chinese Academy of Sciences, China
2.University of Chinese Academy of Sciences, China
3.Sensetime Research
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Wang, Pengrui,Lin, Chunze,Xu, Bo,et al. Low-frequency Guided Self-supervised Learning for High-fidelity 3D Face Reconstruction in the Wild[C],2020.
Files in This Item: Download All
File Name/Size DocType Version Access License
icme2020.pdf(1568KB)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
[Wang, Pengrui]'s Articles
[Lin, Chunze]'s Articles
[Xu, Bo]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Pengrui]'s Articles
[Lin, Chunze]'s Articles
[Xu, Bo]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Pengrui]'s Articles
[Lin, Chunze]'s Articles
[Xu, Bo]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: icme2020.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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