Generating 3D Facial Expressions with Recurrent Neural Networks - Ecole Nationale du Génie de l'Eau et de l'Environnement de Strasbourg Accéder directement au contenu
Chapitre D'ouvrage Année : 2021

Generating 3D Facial Expressions with Recurrent Neural Networks

Résumé

Learning based methods have proved effective at high-quality image synthesis tasks, such as content-preserving image rendering with different style, and the generation of new images depicting learned objects. Some of the properties that make neural networks suitable for such tasks, for example robustness to the input's low-level feature, and the ability to retrieve contextual information, are also desirable in 3D shape domain. During last decades, data-driven methods have shown successful results in 3D shape modeling tasks, such as human face and body shape synthesis. Subtle, abstract properties on the geometry that are instantly detected by our eyes but are nontrivial to synthesize, have successfully been achieved by tuning a shape model built from example shapes. Recent successful learning techniques, e.g. deep neural networks, also exploit this shape model, since the regular grid assumption with 2D images does not have a straightforward equivalent in the common shape representation in 3D, thus do not easily generalize to 3D shapes. Here, we concentrate on the 3D facial expression generation task, an important problem in computer graphics and other application domains, where existing data-driven approaches mostly rely on direct shape capture or shape transfer. At the core of our approach is a recurrent neural network with a landmark-based shape representation. The network is trained to estimate a sequence of pose change, thus generate a specific facial expression, by using a set of motion-captured facial expression sequences. Our technique promises to significantly improve the quality of generated expressions while extending the potential applicability of neural networks to sequence of 3D shapes.
Fichier principal
Vignette du fichier
contributed_books_SEO_LUO.pdf (1.76 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03438293 , version 1 (21-11-2021)

Identifiants

Citer

Hyewon Seo, Guoliang Luo. Generating 3D Facial Expressions with Recurrent Neural Networks. Intelligent Scene Modeling and Human-Computer Interaction, Springer Nature, pp.181-196, 2021, Human–Computer Interaction Series, 978-3-030-71001-9. ⟨10.1007/978-3-030-71002-6_11⟩. ⟨hal-03438293⟩
31 Consultations
119 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More