Human head reconstruction based on elastic deformable 3D model

Author

Yuan, Lin ; Wang, Shengjin ; Ding, Xioaqing

Author_Institution

Dept. of Electron. Eng., Tsinghua Univ., Beijing

fYear

2009

fDate

11-12 April 2009

Firstpage

265

Lastpage

268

Abstract

This paper proposes a framework for generating a photo-realistic 3D head model from one frontal and two side view pictures. First a set of feature points on the 3D general head model, including frontal contour and profile contour are selected; then their correspondences are found in the photo images. Based on these correspondence pairs, RBFN is adopted to deform the mesh of general head model to fit the human head. After that a panorama image construction method is used to generate a seamless texture by linearly blending images around the frontal head contour region. Lastly, this seamless texture is mapped to the head mesh to get a specific 3D head model.

Keywords

face recognition; image reconstruction; image texture; radial basis function networks; realistic images; solid modelling; RBFN; elastic deformable photo-realistic 3D head model; frontal contour; human head reconstruction; image blending; image texture; mesh deformation; panorama image construction; photo image; profile contour; Computer graphics; Computer vision; Deformable models; Face detection; Hair; Head; Humans; Image reconstruction; Reconstruction algorithms; Spatial databases; 3D face model; 3D reconstruction; morphable model; seamless texture blending; texture mapping;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis and Signal Processing, 2009. IASP 2009. International Conference on

Conference_Location

Taizhou

Print_ISBN

978-1-4244-3987-4

Type

conf

DOI

10.1109/IASP.2009.5054629

Filename

5054629