Survey of Face Synthesis

Face synthesis is one of the hot topics in the field of computer vision because of its application and technical value. In recent years, the breakthrough of deep learning has attracted much attention in this field. This paper divides the research in this field into four subcategories: face identity...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	FEI Jianwei1, XIA Zhihua2+, YU Peipeng1, DAI Yunshu1
Formato:	article
Lenguaje:	ZH
Publicado:	Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press 2021
Materias:	face synthesis generative adversarial network (gan) deep learning Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/9d385d8ee8fb4c6ca46e44f200284b57
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9d385d8ee8fb4c6ca46e44f200284b57
record_format	dspace
spelling	oai:doaj.org-article:9d385d8ee8fb4c6ca46e44f200284b572021-11-10T07:56:50ZSurvey of Face Synthesis10.3778/j.issn.1673-9418.21050591673-9418https://doaj.org/article/9d385d8ee8fb4c6ca46e44f200284b572021-11-01T00:00:00Zhttp://fcst.ceaj.org/CN/abstract/abstract2945.shtmlhttps://doaj.org/toc/1673-9418Face synthesis is one of the hot topics in the field of computer vision because of its application and technical value. In recent years, the breakthrough of deep learning has attracted much attention in this field. This paper divides the research in this field into four subcategories: face identity synthesis, face movements synthesis, face attributes synthesis and face generation, and systematically summarizes the development process, status quo, and existing problems of these subcategories. First of all, for face identity synthesis, three approaches are summarized, including computer graphics, digital image processing and deep learning. This paper summarizes their respective routine processes, and analyzes the technical principles of milestone work in detail. Secondly, face movements synthesis is further divided into label driven expression editing and real face driven face reenactment, where the shortcomings and problems in each field are pointed out. Then, the development of face attribute synthesis based on generative model is introduced, especially generative adversarial network. Finally, this paper briefly describes all kinds of researches on face generation. In addition, this paper also introduces the practical application and related problems of face synthesis field and provides the possible research direction in this field.FEI Jianwei1, XIA Zhihua2+, YU Peipeng1, DAI Yunshu1Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Pressarticleface synthesisgenerative adversarial network (gan)deep learningElectronic computers. Computer scienceQA75.5-76.95ZHJisuanji kexue yu tansuo, Vol 15, Iss 11, Pp 2025-2047 (2021)
institution	DOAJ
collection	DOAJ
language	ZH
topic	face synthesis generative adversarial network (gan) deep learning Electronic computers. Computer science QA75.5-76.95
spellingShingle	face synthesis generative adversarial network (gan) deep learning Electronic computers. Computer science QA75.5-76.95 FEI Jianwei1, XIA Zhihua2+, YU Peipeng1, DAI Yunshu1 Survey of Face Synthesis
description	Face synthesis is one of the hot topics in the field of computer vision because of its application and technical value. In recent years, the breakthrough of deep learning has attracted much attention in this field. This paper divides the research in this field into four subcategories: face identity synthesis, face movements synthesis, face attributes synthesis and face generation, and systematically summarizes the development process, status quo, and existing problems of these subcategories. First of all, for face identity synthesis, three approaches are summarized, including computer graphics, digital image processing and deep learning. This paper summarizes their respective routine processes, and analyzes the technical principles of milestone work in detail. Secondly, face movements synthesis is further divided into label driven expression editing and real face driven face reenactment, where the shortcomings and problems in each field are pointed out. Then, the development of face attribute synthesis based on generative model is introduced, especially generative adversarial network. Finally, this paper briefly describes all kinds of researches on face generation. In addition, this paper also introduces the practical application and related problems of face synthesis field and provides the possible research direction in this field.
format	article
author	FEI Jianwei1, XIA Zhihua2+, YU Peipeng1, DAI Yunshu1
author_facet	FEI Jianwei1, XIA Zhihua2+, YU Peipeng1, DAI Yunshu1
author_sort	FEI Jianwei1, XIA Zhihua2+, YU Peipeng1, DAI Yunshu1
title	Survey of Face Synthesis
title_short	Survey of Face Synthesis
title_full	Survey of Face Synthesis
title_fullStr	Survey of Face Synthesis
title_full_unstemmed	Survey of Face Synthesis
title_sort	survey of face synthesis
publisher	Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
publishDate	2021
url	https://doaj.org/article/9d385d8ee8fb4c6ca46e44f200284b57
work_keys_str_mv	AT feijianwei1xiazhihua2yupeipeng1daiyunshu1 surveyoffacesynthesis
_version_	1718440401835130880

Survey of Face Synthesis

Ejemplares similares