Hybrid Approach for 3D Head Reconstruction: ...
Type de document :
Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes
Titre :
Hybrid Approach for 3D Head Reconstruction: Using Neural Networks and Visual Geometry
Auteur(s) :
Bouafif, Oussema [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Khomutenko, Bogdan [Auteur]
Daoudi, Mohamed [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Lille Douai]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Khomutenko, Bogdan [Auteur]
Daoudi, Mohamed [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Lille Douai]
Titre de la manifestation scientifique :
25th International Conference on Pattern Recognition (ICPR2020)
Ville :
Milano
Pays :
Italie
Date de début de la manifestation scientifique :
2021-01-10
Discipline(s) HAL :
Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
Résumé en anglais : [en]
Recovering the 3D geometric structure of a face from a single input image is a challenging active research area in computer vision. In this paper, we present a novel method for reconstructing 3D heads from a single or ...
Lire la suite >Recovering the 3D geometric structure of a face from a single input image is a challenging active research area in computer vision. In this paper, we present a novel method for reconstructing 3D heads from a single or multiple image(s) using a hybrid approach based on deep learning and geometric techniques. We propose an encoder-decoder network based on the U-net architecture and trained on synthetic data only. It predicts both pixel-wise normal vectors and landmarks maps from a single input photo. Landmarks are used for the pose computation and the initialization of the optimization problem, which, in turn, reconstructs the 3D head geometry by using a parametric morphable model and normal vector fields. State-of-the-art results are achieved through qualitative and quantitative evaluation tests on both single and multi-view settings. Despite the fact that the model was trained only on synthetic data, it successfully recovers 3D geometry and precise poses for real-world images.Lire moins >
Lire la suite >Recovering the 3D geometric structure of a face from a single input image is a challenging active research area in computer vision. In this paper, we present a novel method for reconstructing 3D heads from a single or multiple image(s) using a hybrid approach based on deep learning and geometric techniques. We propose an encoder-decoder network based on the U-net architecture and trained on synthetic data only. It predicts both pixel-wise normal vectors and landmarks maps from a single input photo. Landmarks are used for the pose computation and the initialization of the optimization problem, which, in turn, reconstructs the 3D head geometry by using a parametric morphable model and normal vector fields. State-of-the-art results are achieved through qualitative and quantitative evaluation tests on both single and multi-view settings. Despite the fact that the model was trained only on synthetic data, it successfully recovers 3D geometry and precise poses for real-world images.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- https://hal.archives-ouvertes.fr/hal-02983294/document
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-02983294/document
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-02983294/document
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- ICPR2020-5.pdf
- Accès libre
- Accéder au document