Generative Adversarial Networks for face generation: A survey
University of Sfax · Université Paris-Saclay · +1 more institution
Abstract
Recently, Generative Adversarial Networks (GANs) have received enormous progress, which makes them able to learn complex data distributions in particular faces. More and more efficient GAN architectures have been designed and proposed to learn the different variations of faces, such as cross pose, age, expression and style. These GAN based approaches need to be reviewed, discussed, and categorized in terms of architectures, applications, and metrics. Several reviews that focus on the use and advances of GAN in general have been proposed. However, the GAN models applied to the face, that we call facial GANs, have never been addressed. In this article, we review facial GANs and their different applications. We…
Citation impact
- FWCI
- 23.65
- Percentile
- 100%
- References
- 785
Authors
5Topics & keywords
- Computer science
- Adversarial system
- Generative grammar
- Face (sociological concept)
- Generative adversarial network
- Artificial intelligence
- Machine learning
- Theoretical computer science
Funding
- NRNational Research Foundation
- NNNational Natural Science Foundation of China
- NRNational Research Foundation of KoreaAwards: 2020R1C1C1008296, 2019-0-00075, NRF-2020R1C1C1008296
- KAKorea Advanced Institute of Science and TechnologyAward: 2019-0-00075
- MOMinistry of Science and ICT, South KoreaAward: 2019-0-00075
- EAEngineering and Physical Sciences Research CouncilAward: EP/P020631/1
- IFInstitute for Information and Communications Technology PromotionAward: 2019-0-00075