English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/202226
Share/Impact:
Statistics
logo share SHARE logo core CORE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE
Exportar a otros formatos:

Title

GANimation: One-Shot Anatomically Consistent Facial Animation

AuthorsPumarola, Albert; Agudo, Antonio ; Martínez, Aleix M.; Sanfeliu, Alberto ; Moreno-Noguer, Francesc
KeywordsGAN
Face animation
Action-unit condition
Issue Date24-Aug-2019
PublisherSpringer Nature
CitationInternational Journal of Computer Vision 128: 698-713 (2020)
AbstractRecent advances in generative adversarial networks (GANs) have shown impressive results for the task of facial expression synthesis. The most successful architecture is StarGAN (Choi et al. in CVPR, 2018), that conditions GANs’ generation process with images of a specific domain, namely a set of images of people sharing the same expression. While effective, this approach can only generate a discrete number of expressions, determined by the content and granularity of the dataset. To address this limitation, in this paper, we introduce a novel GAN conditioning scheme based on action units (AU) annotations, which describes in a continuous manifold the anatomical facial movements defining a human expression. Our approach allows controlling the magnitude of activation of each AU and combining several of them. Additionally, we propose a weakly supervised strategy to train the model, that only requires images annotated with their activated AUs, and exploit a novel self-learned attention mechanism that makes our network robust to changing backgrounds, lighting conditions and occlusions. Extensive evaluation shows that our approach goes beyond competing conditional generators both in the capability to synthesize a much wider range of expressions ruled by anatomically feasible muscle movements, as in the capacity of dealing with images in the wild. The code of this work is publicly available at https://github.com/albertpumarola/GANimation.
Publisher version (URL)http://dx.doi.org/10.1007/s11263-019-01210-3
URIhttp://hdl.handle.net/10261/202226
DOI10.1007/s11263-019-01210-3
Identifiersdoi: 10.1007/s11263-019-01210-3
e-issn: 1573-1405
issn: 0920-5691
Appears in Collections:(IRII) Artículos
Files in This Item:
File Description SizeFormat 
GANimation_Pumarola.pdf17,09 MBAdobe PDFThumbnail
View/Open
Show full item record
Review this work
 

Related articles:


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.