CASIA OpenIR  > 模式识别国家重点实验室  > 生物识别与安全技术研究
Discriminative 3D Morphable Model Fitting
Zhu XY(朱翔昱); Yan JJ(闫俊杰); Yi D(易东); Lei Z(雷震); Li ZQ(李子青)
2015
Conference NameIEEE International Conference on Automatic Face and Gesture Recognition (FG)
Conference Date4-8 May, 2015
Conference PlaceLjubljana, Slovenia
Abstract
This paper presents a novel discriminative method for estimating 3D shape from a single image with 3D Morphable Model (3DMM). Until now, most traditional 3DMM fitting methods depend on the analysis-by-synthesis framework which searches for the best parameters by minimizing the difference between the input image and the model appearance. They are highly sensitive to initialization and have to rely on the stochastic optimization to handle local minimum problem, which is usually a time-consuming process. To solve the problem, we find a different direction to estimate shape parameters through learning a regressor instead of minimizing the appearance difference. Compared with the traditional analysis-by-synthesis framework, the new discriminative approach makes it possible to utilize large databases to train a robust fitting model and directly reconstruct shape from image features accurately and efficiently. We compare our method with two popular 3DMM fitting algorithms on FRGC database. Experimental results show that our approach significantly outperforms the state-of-the-art in terms of efficiency, robustness and accuracy.
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/14783
Collection模式识别国家重点实验室_生物识别与安全技术研究
AffiliationCenter for Biometrics and Security Research, Institute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhu XY,Yan JJ,Yi D,et al. Discriminative 3D Morphable Model Fitting[C],2015.
Files in This Item: Download All
File Name/Size DocType Version Access License
07163096.pdf(7311KB)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
[Zhu XY(朱翔昱)]'s Articles
[Yan JJ(闫俊杰)]'s Articles
[Yi D(易东)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhu XY(朱翔昱)]'s Articles
[Yan JJ(闫俊杰)]'s Articles
[Yi D(易东)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhu XY(朱翔昱)]'s Articles
[Yan JJ(闫俊杰)]'s Articles
[Yi D(易东)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 07163096.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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