E2F-GAN: Eyes-to-Face Inpainting via Edge-Aware Coarse-to-Fine GANs

Face inpainting is a challenging task aiming to ll the damaged or masked regions in face images with plausibly synthesized contents. Based on the given information, the reconstructed regions should look realistic and more importantly preserve the demographic and biometric properties of the individua...

ver descrição completa

Detalhes bibliográficos
Autores: Hassanpour, Ahmad, Daryani, Amir Etefaghi, Mirmahdi, Mahdieh, Raja, Kiram, Yang, Bian, Busch, Christoph, Fiérrez Aguilar, Julián
Tipo de documento: artigo
Data de publicação:2022
País:España
Recursos:Universidad Autónoma de Madrid
Repositório:Biblos-e Archivo. Repositorio Institucional de la UAM
Idioma:inglês
OAI Identifier:oai:repositorio.uam.es:10486/711186
Acesso em linha:http://hdl.handle.net/10486/711186
https://dx.doi.org/10.1109/ACCESS.2022.3160174
Access Level:Acceso aberto
Palavra-chave:Face inpainting
generative adversarial networks
image inpainting
Telecomunicaciones
id ES_079408e4adf03e4e34963b718a6b2b0f
oai_identifier_str oai:repositorio.uam.es:10486/711186
network_acronym_str ES
network_name_str España
repository_id_str
spelling E2F-GAN: Eyes-to-Face Inpainting via Edge-Aware Coarse-to-Fine GANsHassanpour, AhmadDaryani, Amir EtefaghiMirmahdi, MahdiehRaja, KiramYang, BianBusch, ChristophFiérrez Aguilar, JuliánFace inpaintinggenerative adversarial networksimage inpaintingTelecomunicacionesFace inpainting is a challenging task aiming to ll the damaged or masked regions in face images with plausibly synthesized contents. Based on the given information, the reconstructed regions should look realistic and more importantly preserve the demographic and biometric properties of the individual. The aim of this paper is to reconstruct the face based on the periocular region (eyes-to-face). To do this, we proposed a novel GAN-based deep learning model called Eyes-to-Face GAN (E2F-GAN) which includes two main modules: a coarse module and a re nement module. The coarse module along with an edge predictor module attempts to extract all required features from a periocular region and to generate a coarse output which will be re ned by a re nement module. Additionally, a dataset of eyes-to-face synthesis has been generated based on the public face dataset called CelebA-HQ for training and testing. Thus, we perform both qualitative and quantitative evaluations on the generated dataset. Experimental results demonstrate that our method outperforms previous learning-based face inpainting methods and generates realistic and semantically plausible images. We also provide the implementation of the proposed approach to support reproducible research via (https://github.com/amiretefaghi/E2F-GAN). INDEXThis work was supported by the Project Privacy Matters (PRIMA) under Grant H2020-MSCA-ITN-2019-860315. The work of Julian Fierrez was supported by the Project Biometrics and Behavior for Unbiased and Trusted AI with Applications (BBforTAI) under Grant PID2021-127641OB-I00 MICINN/FEDER.IEEEDepartamento de Tecnología Electrónica y de las ComunicacionesEscuela Politécnica Superior20222022-03-16research articlehttp://purl.org/coar/resource_type/c_2df8fbb1VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10486/711186https://dx.doi.org/10.1109/ACCESS.2022.3160174reponame:Biblos-e Archivo. Repositorio Institucional de la UAMinstname:Universidad Autónoma de MadridInglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:repositorio.uam.es:10486/7111862026-06-23T12:46:27Z
dc.title.none.fl_str_mv E2F-GAN: Eyes-to-Face Inpainting via Edge-Aware Coarse-to-Fine GANs
title E2F-GAN: Eyes-to-Face Inpainting via Edge-Aware Coarse-to-Fine GANs
spellingShingle E2F-GAN: Eyes-to-Face Inpainting via Edge-Aware Coarse-to-Fine GANs
Hassanpour, Ahmad
Face inpainting
generative adversarial networks
image inpainting
Telecomunicaciones
title_short E2F-GAN: Eyes-to-Face Inpainting via Edge-Aware Coarse-to-Fine GANs
title_full E2F-GAN: Eyes-to-Face Inpainting via Edge-Aware Coarse-to-Fine GANs
title_fullStr E2F-GAN: Eyes-to-Face Inpainting via Edge-Aware Coarse-to-Fine GANs
title_full_unstemmed E2F-GAN: Eyes-to-Face Inpainting via Edge-Aware Coarse-to-Fine GANs
title_sort E2F-GAN: Eyes-to-Face Inpainting via Edge-Aware Coarse-to-Fine GANs
dc.creator.none.fl_str_mv Hassanpour, Ahmad
Daryani, Amir Etefaghi
Mirmahdi, Mahdieh
Raja, Kiram
Yang, Bian
Busch, Christoph
Fiérrez Aguilar, Julián
author Hassanpour, Ahmad
author_facet Hassanpour, Ahmad
Daryani, Amir Etefaghi
Mirmahdi, Mahdieh
Raja, Kiram
Yang, Bian
Busch, Christoph
Fiérrez Aguilar, Julián
author_role author
author2 Daryani, Amir Etefaghi
Mirmahdi, Mahdieh
Raja, Kiram
Yang, Bian
Busch, Christoph
Fiérrez Aguilar, Julián
author2_role author
author
author
author
author
author
dc.contributor.none.fl_str_mv Departamento de Tecnología Electrónica y de las Comunicaciones
Escuela Politécnica Superior
dc.subject.none.fl_str_mv Face inpainting
generative adversarial networks
image inpainting
Telecomunicaciones
topic Face inpainting
generative adversarial networks
image inpainting
Telecomunicaciones
description Face inpainting is a challenging task aiming to ll the damaged or masked regions in face images with plausibly synthesized contents. Based on the given information, the reconstructed regions should look realistic and more importantly preserve the demographic and biometric properties of the individual. The aim of this paper is to reconstruct the face based on the periocular region (eyes-to-face). To do this, we proposed a novel GAN-based deep learning model called Eyes-to-Face GAN (E2F-GAN) which includes two main modules: a coarse module and a re nement module. The coarse module along with an edge predictor module attempts to extract all required features from a periocular region and to generate a coarse output which will be re ned by a re nement module. Additionally, a dataset of eyes-to-face synthesis has been generated based on the public face dataset called CelebA-HQ for training and testing. Thus, we perform both qualitative and quantitative evaluations on the generated dataset. Experimental results demonstrate that our method outperforms previous learning-based face inpainting methods and generates realistic and semantically plausible images. We also provide the implementation of the proposed approach to support reproducible research via (https://github.com/amiretefaghi/E2F-GAN). INDEX
publishDate 2022
dc.date.none.fl_str_mv 2022
2022-03-16
dc.type.none.fl_str_mv research article
http://purl.org/coar/resource_type/c_2df8fbb1
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10486/711186
https://dx.doi.org/10.1109/ACCESS.2022.3160174
url http://hdl.handle.net/10486/711186
https://dx.doi.org/10.1109/ACCESS.2022.3160174
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv IEEE
publisher.none.fl_str_mv IEEE
dc.source.none.fl_str_mv reponame:Biblos-e Archivo. Repositorio Institucional de la UAM
instname:Universidad Autónoma de Madrid
instname_str Universidad Autónoma de Madrid
reponame_str Biblos-e Archivo. Repositorio Institucional de la UAM
collection Biblos-e Archivo. Repositorio Institucional de la UAM
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869402990806302720
score 15,300724

Registros relacionados