A Decoupled 3D Facial Shape Model by Adversarial Training - Archive ouverte HAL Access content directly
Conference Papers Year :

A Decoupled 3D Facial Shape Model by Adversarial Training

Adnane Boukhayma
  • Function : Author
  • PersonId : 1045784
Stefanie Wuhrer
Edmond Boyer


Data-driven generative 3D face models are used to compactly encode facial shape data into meaningful parametric representations. A desirable property of these models is their ability to effectively decouple natural sources of variation, in particular identity and expression. While factorized representations have been proposed for that purpose, they are still limited in the variability they can capture and may present modeling artifacts when applied to tasks such as expression transfer. In this work, we explore a new direction with Generative Adversarial Networks and show that they contribute to better face modeling performances, especially in decoupling natural factors, while also achieving more diverse samples. To train the model we introduce a novel architecture that combines a 3D generator with a 2D discriminator that leverages conventional CNNs, where the two components are bridged by a geometry mapping layer. We further present a training scheme, based on auxiliary classifiers, to explicitly disentangle identity and expression attributes. Through quantitative and qualitative results on standard face datasets, we illustrate the benefits of our model and demonstrate that it outperforms competing state of the art methods in terms of decoupling and diversity.
Fichier principal
Vignette du fichier
paper-final.pdf (1.52 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02064711 , version 1 (12-03-2019)
hal-02064711 , version 2 (18-04-2019)
hal-02064711 , version 3 (07-09-2019)



Victoria Fernández Abrevaya, Adnane Boukhayma, Stefanie Wuhrer, Edmond Boyer. A Decoupled 3D Facial Shape Model by Adversarial Training. ICCV 2019 - International Conference on Computer Vision, Oct 2019, Seoul, South Korea. pp.9418-9427, ⟨10.1109/ICCV.2019.00951⟩. ⟨hal-02064711v3⟩
650 View
1172 Download



Gmail Facebook Twitter LinkedIn More