Reconstruction of 3D faces by shape estimation and texture interpolation

This paper aims to address the ill-posed problem of reconstructing 3D faces from single 2D face images. An extended Tikhonov regularization method is connected with the standard 3D morphable model in order to reconstruct the 3D face shapes from a small set of 2D facial points. Further, by interpol...

Full description

Bibliographic Details
Main Authors: Maghari,, Ashraf Y. A., Venkat, Ibrahim, Belaton, Bahari
Format: Article
Language:English
Published: Penerbit Universiti Kebangsaan Malaysia 2014
Online Access:http://journalarticle.ukm.my/6805/
http://journalarticle.ukm.my/6805/
http://journalarticle.ukm.my/6805/1/4802-11322-1-PB.pdf
id ukm-6805
recordtype eprints
spelling ukm-68052016-12-14T06:42:14Z http://journalarticle.ukm.my/6805/ Reconstruction of 3D faces by shape estimation and texture interpolation Maghari,, Ashraf Y. A. Venkat, Ibrahim Belaton, Bahari This paper aims to address the ill-posed problem of reconstructing 3D faces from single 2D face images. An extended Tikhonov regularization method is connected with the standard 3D morphable model in order to reconstruct the 3D face shapes from a small set of 2D facial points. Further, by interpolating the input 2D texture with the model texture and warping the interpolated texture to the reconstructed face shapes, 3D face reconstruction is achieved. For the texture warping, the 2D face deformation has been learned from the model texture using a set of facial landmarks. Our experimental results justify the robustness of the proposed approach with respect to the reconstruction of realistic 3D face shapes. Penerbit Universiti Kebangsaan Malaysia 2014-06 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/6805/1/4802-11322-1-PB.pdf Maghari,, Ashraf Y. A. and Venkat, Ibrahim and Belaton, Bahari (2014) Reconstruction of 3D faces by shape estimation and texture interpolation. Asia-Pacific Journal of Information Technology and Multimedia, 3 (1). pp. 15-21. ISSN 2289-2192 http://ejournal.ukm.my/apjitm
repository_type Digital Repository
institution_category Local University
institution Universiti Kebangasaan Malaysia
building UKM Institutional Repository
collection Online Access
language English
description This paper aims to address the ill-posed problem of reconstructing 3D faces from single 2D face images. An extended Tikhonov regularization method is connected with the standard 3D morphable model in order to reconstruct the 3D face shapes from a small set of 2D facial points. Further, by interpolating the input 2D texture with the model texture and warping the interpolated texture to the reconstructed face shapes, 3D face reconstruction is achieved. For the texture warping, the 2D face deformation has been learned from the model texture using a set of facial landmarks. Our experimental results justify the robustness of the proposed approach with respect to the reconstruction of realistic 3D face shapes.
format Article
author Maghari,, Ashraf Y. A.
Venkat, Ibrahim
Belaton, Bahari
spellingShingle Maghari,, Ashraf Y. A.
Venkat, Ibrahim
Belaton, Bahari
Reconstruction of 3D faces by shape estimation and texture interpolation
author_facet Maghari,, Ashraf Y. A.
Venkat, Ibrahim
Belaton, Bahari
author_sort Maghari,, Ashraf Y. A.
title Reconstruction of 3D faces by shape estimation and texture interpolation
title_short Reconstruction of 3D faces by shape estimation and texture interpolation
title_full Reconstruction of 3D faces by shape estimation and texture interpolation
title_fullStr Reconstruction of 3D faces by shape estimation and texture interpolation
title_full_unstemmed Reconstruction of 3D faces by shape estimation and texture interpolation
title_sort reconstruction of 3d faces by shape estimation and texture interpolation
publisher Penerbit Universiti Kebangsaan Malaysia
publishDate 2014
url http://journalarticle.ukm.my/6805/
http://journalarticle.ukm.my/6805/
http://journalarticle.ukm.my/6805/1/4802-11322-1-PB.pdf
first_indexed 2023-09-18T19:47:57Z
last_indexed 2023-09-18T19:47:57Z
_version_ 1777406026344038400