The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
En raison de l’épidémie mondiale de coronavirus, les gens portent de plus en plus de masques, même lorsqu’ils sont photographiés. En conséquence, les photos téléchargées sur des pages Web et des services de réseaux sociaux avec la moitié inférieure du visage cachée sont moins susceptibles de transmettre l'attrait des personnes photographiées. Dans cette étude, nous proposons une méthode pour compléter les régions du masque facial à l'aide de StyleGAN2, un type de réseaux contradictoires génératifs (GAN). Dans le procédé proposé, une image de référence de la même personne sans masque est préparée séparément d'une image cible de la personne portant un masque. Une fois la région du masque dans l'image cible temporairement peinte, l'orientation du visage et le contour de la personne dans l'image de référence sont modifiés pour correspondre à ceux de l'image cible à l'aide de StyleGAN2. L'image modifiée est ensuite composée dans la région du masque tout en corrigeant la tonalité de couleur pour produire une image sans masque tout en préservant les caractéristiques de la personne.
Norihiko KAWAI
Osaka Institute of Technology
Hiroaki KOIKE
Osaka Institute of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Norihiko KAWAI, Hiroaki KOIKE, "Facial Mask Completion Using StyleGAN2 Preserving Features of the Person" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 10, pp. 1627-1637, October 2023, doi: 10.1587/transinf.2023PCP0002.
Abstract: Due to the global outbreak of coronaviruses, people are increasingly wearing masks even when photographed. As a result, photos uploaded to web pages and social networking services with the lower half of the face hidden are less likely to convey the attractiveness of the photographed persons. In this study, we propose a method to complete facial mask regions using StyleGAN2, a type of Generative Adversarial Networks (GAN). In the proposed method, a reference image of the same person without a mask is prepared separately from a target image of the person wearing a mask. After the mask region in the target image is temporarily inpainted, the face orientation and contour of the person in the reference image are changed to match those of the target image using StyleGAN2. The changed image is then composited into the mask region while correcting the color tone to produce a mask-free image while preserving the person's features.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023PCP0002/_p
Copier
@ARTICLE{e106-d_10_1627,
author={Norihiko KAWAI, Hiroaki KOIKE, },
journal={IEICE TRANSACTIONS on Information},
title={Facial Mask Completion Using StyleGAN2 Preserving Features of the Person},
year={2023},
volume={E106-D},
number={10},
pages={1627-1637},
abstract={Due to the global outbreak of coronaviruses, people are increasingly wearing masks even when photographed. As a result, photos uploaded to web pages and social networking services with the lower half of the face hidden are less likely to convey the attractiveness of the photographed persons. In this study, we propose a method to complete facial mask regions using StyleGAN2, a type of Generative Adversarial Networks (GAN). In the proposed method, a reference image of the same person without a mask is prepared separately from a target image of the person wearing a mask. After the mask region in the target image is temporarily inpainted, the face orientation and contour of the person in the reference image are changed to match those of the target image using StyleGAN2. The changed image is then composited into the mask region while correcting the color tone to produce a mask-free image while preserving the person's features.},
keywords={},
doi={10.1587/transinf.2023PCP0002},
ISSN={1745-1361},
month={October},}
Copier
TY - JOUR
TI - Facial Mask Completion Using StyleGAN2 Preserving Features of the Person
T2 - IEICE TRANSACTIONS on Information
SP - 1627
EP - 1637
AU - Norihiko KAWAI
AU - Hiroaki KOIKE
PY - 2023
DO - 10.1587/transinf.2023PCP0002
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2023
AB - Due to the global outbreak of coronaviruses, people are increasingly wearing masks even when photographed. As a result, photos uploaded to web pages and social networking services with the lower half of the face hidden are less likely to convey the attractiveness of the photographed persons. In this study, we propose a method to complete facial mask regions using StyleGAN2, a type of Generative Adversarial Networks (GAN). In the proposed method, a reference image of the same person without a mask is prepared separately from a target image of the person wearing a mask. After the mask region in the target image is temporarily inpainted, the face orientation and contour of the person in the reference image are changed to match those of the target image using StyleGAN2. The changed image is then composited into the mask region while correcting the color tone to produce a mask-free image while preserving the person's features.
ER -