From attributes to faces: a conditional generative network for face generation

Yaohui Wang 1 Antitza Dantcheva 1 Francois Bremond 1
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : Recent advances in computer vision have aimed at extracting and classifying auxiliary biometric information such as age, gender, as well as health attributes, referred to as soft biometrics or attributes. We here seek to explore the inverse problem, namely face generation based on attribute labels, which is of interest due to related applications in law enforcement and entertainment. Particularly, we propose a method based on deep conditional generative adversarial network (DC-GAN), which introduces additional data (e.g., labels) towards determining specific representations of generated images. We present experimental results of the method, trained on the dataset CelebA, and validate these based on two GAN-quality-metrics, as well as based on three face detectors and one commercial off the shelf (COTS) attribute classifier. While these are early results, our findings indicate the method's ability to generate realistic faces from attribute labels.
Document type :
Conference papers
Complete list of metadatas

Cited literature [1 references]  Display  Hide  Download

https://hal.inria.fr/hal-01894144
Contributor : Antitza Dantcheva <>
Submitted on : Friday, October 12, 2018 - 10:47:29 AM
Last modification on : Saturday, October 13, 2018 - 1:21:39 AM
Long-term archiving on : Sunday, January 13, 2019 - 1:05:48 PM

File

Wang_Dantcheva_Bremond_biosig_...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01894144, version 1

Collections

Citation

Yaohui Wang, Antitza Dantcheva, Francois Bremond. From attributes to faces: a conditional generative network for face generation. BIOSIG'18, 17th International Conference of the Biometrics Special Interest Group, Sep 2018, Darmstadt, Germany. ⟨hal-01894144⟩

Share

Metrics

Record views

138

Files downloads

400