Hybrid Approach for 3D Head Reconstruction: Using Neural Networks and Visual Geometry - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Hybrid Approach for 3D Head Reconstruction: Using Neural Networks and Visual Geometry

Résumé

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.
Fichier principal
Vignette du fichier
ICPR2020-5.pdf (2.68 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02983294 , version 1 (29-10-2020)

Identifiants

  • HAL Id : hal-02983294 , version 1

Citer

Oussema Bouafif, Bogdan Khomutenko, Mohamed Daoudi. Hybrid Approach for 3D Head Reconstruction: Using Neural Networks and Visual Geometry. 25th International Conference on Pattern Recognition (ICPR2020), Jan 2021, Milano, Italy. ⟨hal-02983294⟩
140 Consultations
253 Téléchargements

Partager

Gmail Facebook X LinkedIn More