Presentation 2012-05-17
Reconstruction of dynamic 3D expression images from one facial image using subspace learning
Shunya OSAWA, Mamoru ISHIMOTO, Guifang DUAN, Yen-Wei CHEN,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Dynamic 3D facial expression images are important in many computer vision and graphic applications, such as expression recognition and animation. However, it is difficult to establish dynamic 3D expression images since it takes much cost and time. Thus, in my research, We try to reconstructed dynamic 3D images from only one facial image using machine learning approach. The results show that the proposed method can effectively generate the dynamic 3D expression images using only one input 2D image of 2816 by 2112 in size, and the average error is 8 pixel.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) PCA(principal component analysis) / pseudo-inverse matrix / dynamic 3D expression
Paper # IE2012-16,PRMU2012-1,MI2012-1
Date of Issue

Conference Information
Committee IE
Conference Date 2012/5/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Image Engineering (IE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Reconstruction of dynamic 3D expression images from one facial image using subspace learning
Sub Title (in English)
Keyword(1) PCA(principal component analysis)
Keyword(2) pseudo-inverse matrix
Keyword(3) dynamic 3D expression
1st Author's Name Shunya OSAWA
1st Author's Affiliation Infomation Science and Engineering, Ritsumeikan University()
2nd Author's Name Mamoru ISHIMOTO
2nd Author's Affiliation Infomation Science and Engineering, Ritsumeikan University
3rd Author's Name Guifang DUAN
3rd Author's Affiliation Infomation Science and Engineering, Ritsumeikan University
4th Author's Name Yen-Wei CHEN
4th Author's Affiliation Infomation Science and Engineering, Ritsumeikan University
Date 2012-05-17
Paper # IE2012-16,PRMU2012-1,MI2012-1
Volume (vol) vol.112
Number (no) 36
Page pp.pp.-
#Pages 6
Date of Issue