3D face reconstruction from single image with generative adversarial networks

Traditional reconstruction techniques extract information from the object’s geometry or one or more 2D images. On the other hand, the limit of the existing methods is that they generate less precise objects. Thus the lack of robustness towards several face reconstruction problems, such as the positi...

Full description

Saved in:
Bibliographic Details
Main Authors: Mehdi Malah, Mounir Hemam, Fayçal Abbas
Format: Article
Language:English
Published: Springer 2023-01-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S131915782200413X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849322751085510656
author Mehdi Malah
Mounir Hemam
Fayçal Abbas
author_facet Mehdi Malah
Mounir Hemam
Fayçal Abbas
author_sort Mehdi Malah
collection DOAJ
description Traditional reconstruction techniques extract information from the object’s geometry or one or more 2D images. On the other hand, the limit of the existing methods is that they generate less precise objects. Thus the lack of robustness towards several face reconstruction problems, such as the position of the head, occlusion, noise, and lighting variation. Therefore, generative neural networks and graphical convolution networks have marked a significant evolution in the field of 3D reconstruction. This paper proposes a model for 3D face reconstruction from a single 2D image. Our model is composed of a generator and a discriminator based on convolutional graphic layers. Indeed, in order to generate a face mesh with expression, our idea is to use the landmarks associated with this image as input to the generator to reconstruct a face geometry with expression and improve the convergence rate. As a result, our model offers an accurate reconstruction of facial geometry with expression; thus, our model outperforms state-of-the-art methods through qualitative and quantitative comparison.
format Article
id doaj-art-11cb5cf34c424a398d4398bc16d5ed2c
institution Kabale University
issn 1319-1578
language English
publishDate 2023-01-01
publisher Springer
record_format Article
series Journal of King Saud University: Computer and Information Sciences
spelling doaj-art-11cb5cf34c424a398d4398bc16d5ed2c2025-08-20T03:49:17ZengSpringerJournal of King Saud University: Computer and Information Sciences1319-15782023-01-0135125025610.1016/j.jksuci.2022.11.0143D face reconstruction from single image with generative adversarial networksMehdi Malah0Mounir Hemam1Fayçal Abbas2University Abbes Laghrour - Khenchela, ICOSI Laboratory, BP 1252 El Houria, 40004, Algeria; Corresponding authors.University Abbes Laghrour - Khenchela, ICOSI Laboratory, BP 1252 El Houria, 40004, AlgeriaUniversity Abbes Laghrour - Khenchela, LESIA Laboratory, BP 1252 El Houria, 40004, Algeria; Corresponding authors.Traditional reconstruction techniques extract information from the object’s geometry or one or more 2D images. On the other hand, the limit of the existing methods is that they generate less precise objects. Thus the lack of robustness towards several face reconstruction problems, such as the position of the head, occlusion, noise, and lighting variation. Therefore, generative neural networks and graphical convolution networks have marked a significant evolution in the field of 3D reconstruction. This paper proposes a model for 3D face reconstruction from a single 2D image. Our model is composed of a generator and a discriminator based on convolutional graphic layers. Indeed, in order to generate a face mesh with expression, our idea is to use the landmarks associated with this image as input to the generator to reconstruct a face geometry with expression and improve the convergence rate. As a result, our model offers an accurate reconstruction of facial geometry with expression; thus, our model outperforms state-of-the-art methods through qualitative and quantitative comparison.http://www.sciencedirect.com/science/article/pii/S131915782200413XSingle image 3D reconstructionFace reconstructionGenerative adversarial networksGraph convolution networks
spellingShingle Mehdi Malah
Mounir Hemam
Fayçal Abbas
3D face reconstruction from single image with generative adversarial networks
Journal of King Saud University: Computer and Information Sciences
Single image 3D reconstruction
Face reconstruction
Generative adversarial networks
Graph convolution networks
title 3D face reconstruction from single image with generative adversarial networks
title_full 3D face reconstruction from single image with generative adversarial networks
title_fullStr 3D face reconstruction from single image with generative adversarial networks
title_full_unstemmed 3D face reconstruction from single image with generative adversarial networks
title_short 3D face reconstruction from single image with generative adversarial networks
title_sort 3d face reconstruction from single image with generative adversarial networks
topic Single image 3D reconstruction
Face reconstruction
Generative adversarial networks
Graph convolution networks
url http://www.sciencedirect.com/science/article/pii/S131915782200413X
work_keys_str_mv AT mehdimalah 3dfacereconstructionfromsingleimagewithgenerativeadversarialnetworks
AT mounirhemam 3dfacereconstructionfromsingleimagewithgenerativeadversarialnetworks
AT faycalabbas 3dfacereconstructionfromsingleimagewithgenerativeadversarialnetworks