Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Mohamed Dhouioui 1 ; Tarek Frikha 1 ; Hassen Drira 2 and Mohamed Abid 1

Affiliations: 1 CES-Lab, ENIS, University of Sfax, Sfax, Tunisia ; 2 Centre e Recherche en Informatique Signal et Automatique de Lille, IMT Lille Douai University, Lille, France

Keyword(s): Facial Reconstruction, 3D Morphable Model, 3D Face Imaging, Multi-Image 3D Reconstruction, Single-Image 3D Reconstruction.

Abstract: Recently, many researchers have focused on 3D face analysis and its applications, and put a lot of work on developing its methods. Even though 3D facial images provide a better representation of the face in terms of accuracy, they are harder to acquire than 2D pictures. This is why, wide efforts have been put to develop systems which reconstruct 3D face models from 2D images. However, the 2D to 3D face reconstruction problem is still not very advanced, it is both computationally intensive and needs great space exploration to acquire accurate representations. In this paper, we present a 3D multi-image face reconstruction method built over a single image reconstruction model. We propose a novel 3D face re-construction approach based on two levels, first, the use of a single image 3d re-construction CNN model to represent vectorial embeddings and generate a 3d Face morphable model. And second, an unsupervised K-means model on top of the single image reconstruction CNN Model to optimize its results by incorporating a multi-image reconstruction. Thanks to the introduction of a hybrid loss function, we are able to train the model without ground truth reference. Further-more, to our knowledge this is the first use of an unsupervised model alongside a weakly supervised one reaching such performance. Experiments show that our approach outperforms its counterparts in the literature both in single-image and multi-image reconstruction, and it proves that its unique and original nature are very promising to implement in other applications. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 70.40.220.129

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Dhouioui, M.; Frikha, T.; Drira, H. and Abid, M. (2023). A Novel 3D Face Reconstruction Model from a Multi-Image 2D Set. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7; ISSN 2184-4321, SciTePress, pages 745-753. DOI: 10.5220/0011749500003417

@conference{visapp23,
author={Mohamed Dhouioui. and Tarek Frikha. and Hassen Drira. and Mohamed Abid.},
title={A Novel 3D Face Reconstruction Model from a Multi-Image 2D Set},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={745-753},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011749500003417},
isbn={978-989-758-634-7},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - A Novel 3D Face Reconstruction Model from a Multi-Image 2D Set
SN - 978-989-758-634-7
IS - 2184-4321
AU - Dhouioui, M.
AU - Frikha, T.
AU - Drira, H.
AU - Abid, M.
PY - 2023
SP - 745
EP - 753
DO - 10.5220/0011749500003417
PB - SciTePress