Monocular 3D Head Reconstruction via ...
Type de document :
Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes
Titre :
Monocular 3D Head Reconstruction via Prediction and Integration of Normal Vector Field
Auteur(s) :
Bouafif, Oussema [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Khomutenko, Bogdan [Auteur]
Daoudi, Mohamed [Auteur]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Lille Douai]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Khomutenko, Bogdan [Auteur]
Daoudi, Mohamed [Auteur]

Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Lille Douai]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Titre de la manifestation scientifique :
15th International Conference on Computer Vision, Theory and Applications.
Ville :
Valletta
Pays :
Malte
Date de début de la manifestation scientifique :
2020-02-27
Mot(s)-clé(s) en anglais :
3D Head Reconstruction
Face Reconstruction
Monocular Reconstruction
Facial Surface Normals
Deep Learning
Synthetic Data
Face Reconstruction
Monocular Reconstruction
Facial Surface Normals
Deep Learning
Synthetic Data
Discipline(s) HAL :
Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
Résumé en anglais : [en]
Reconstructing the 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 an input image ...
Lire la suite >Reconstructing the 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 an input image using a hybrid approach based on learning and geometric techniques. We introduce a deep neural network trained on synthetic data only, which predicts the map of normal vectors of the face surface from a single photo. Afterward, using the network output we recover the 3D facial geometry by means of weighted least squares. Through qualitative and quantitative evaluation tests, we show the accuracy and robustness of our proposed method. Our method does not require accurate alignment due to the image-to-image translation network and also successfully recovers 3D geometry for real images, despite the fact that the model was trained only on synthetic data.Lire moins >
Lire la suite >Reconstructing the 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 an input image using a hybrid approach based on learning and geometric techniques. We introduce a deep neural network trained on synthetic data only, which predicts the map of normal vectors of the face surface from a single photo. Afterward, using the network output we recover the 3D facial geometry by means of weighted least squares. Through qualitative and quantitative evaluation tests, we show the accuracy and robustness of our proposed method. Our method does not require accurate alignment due to the image-to-image translation network and also successfully recovers 3D geometry for real images, despite the fact that the model was trained only on synthetic data.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- https://hal.archives-ouvertes.fr/hal-02928494/document
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-02928494/document
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-02928494/document
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- VISAPP2020-2.pdf
- Accès libre
- Accéder au document