A Decoupled 3D Facial Shape Model by Adversarial Training

Victoria Fernández Abrevaya 1 Adnane Boukhayma 2 Stefanie Wuhrer 1 Edmond Boyer 1
1 MORPHEO - Capture and Analysis of Shapes in Motion
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : 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.
Complete list of metadatas

Cited literature [45 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02064711
Contributor : Victoria Fernandez Abrevaya <>
Submitted on : Saturday, September 7, 2019 - 6:19:39 PM
Last modification on : Tuesday, November 5, 2019 - 3:19:14 PM

File

paper-final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02064711, version 3

Collections

Citation

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.1-10. ⟨hal-02064711v3⟩

Share

Metrics

Record views

97

Files downloads

192