Pose- and Attribute-consistent Person Image Synthesis

PersonImageSynthesisaimsattransferringtheappearanceofthesourcepersonimageintoatargetpose. Existingmethods cannot handle largeposevariations and therefore suffer fromtwocritical problems: (1)synthesisdistortionduetotheentanglementofposeandappearanceinformationamongdifferentbody componentsand(2)failur...

Full description

Saved in:

Bibliographic Details
Main Authors:	XU, Cheng, CHEN, Zejun, MAI, Jiajie, XU, Xuemiao, HE, Shengfeng
Format:	text
Language:	English
Published:	Institutional Knowledge at Singapore Management University 2023
Subjects:	Computing methodologies Artificial intelligence Computer vision Computer graphics Image manipulation Image processing Artificial Intelligence and Robotics
Online Access:	https://ink.library.smu.edu.sg/sis_research/8369 https://ink.library.smu.edu.sg/context/sis_research/article/9372/viewcontent/Pose__and_Attribute_consistent_Person_Image_Synthesis.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Singapore Management University
Language:	English

id	sg-smu-ink.sis_research-9372
record_format	dspace
spelling	sg-smu-ink.sis_research-93722023-12-13T02:55:19Z Pose- and Attribute-consistent Person Image Synthesis XU, Cheng CHEN, Zejun MAI, Jiajie XU, Xuemiao HE, Shengfeng PersonImageSynthesisaimsattransferringtheappearanceofthesourcepersonimageintoatargetpose. Existingmethods cannot handle largeposevariations and therefore suffer fromtwocritical problems: (1)synthesisdistortionduetotheentanglementofposeandappearanceinformationamongdifferentbody componentsand(2)failureinpreservingoriginalsemantics(e.g.,thesameoutfit).Inthisarticle,weexplicitly addressthesetwoproblemsbyproposingaPose-andAttribute-consistentPersonImageSynthesisNetwork (PAC-GAN).Toreduceposeandappearancematchingambiguity,weproposeacomponent-wisetransferring modelconsistingoftwostages.Theformerstagefocusesonlyonsynthesizingtargetposes,whilethelatter renderstargetappearancesbyexplicitlytransferringtheappearanceinformationfromthesourceimageto thetargetimageinacomponent-wisemanner. Inthisway,source-targetmatchingambiguityiseliminated duetothecomponent-wisedisentanglementofposeandappearancesynthesis.Second,tomaintainattribute consistency,werepresenttheinputimageasanattributevectorandimposeahigh-levelsemanticconstraint usingthisvectortoregularizethetargetsynthesis.ExtensiveexperimentalresultsontheDeepFashiondataset demonstratethesuperiorityofourmethodoverthestateoftheart,especiallyformaintainingposeandattributeconsistenciesunderlargeposevariations. 2023-02-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8369 info:doi/10.1145/3554739 https://ink.library.smu.edu.sg/context/sis_research/article/9372/viewcontent/Pose__and_Attribute_consistent_Person_Image_Synthesis.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Computing methodologies Artificial intelligence Computer vision Computer graphics Image manipulation Image processing Artificial Intelligence and Robotics
institution	Singapore Management University
building	SMU Libraries
continent	Asia
country	Singapore Singapore
content_provider	SMU Libraries
collection	InK@SMU
language	English
topic	Computing methodologies Artificial intelligence Computer vision Computer graphics Image manipulation Image processing Artificial Intelligence and Robotics
spellingShingle	Computing methodologies Artificial intelligence Computer vision Computer graphics Image manipulation Image processing Artificial Intelligence and Robotics XU, Cheng CHEN, Zejun MAI, Jiajie XU, Xuemiao HE, Shengfeng Pose- and Attribute-consistent Person Image Synthesis
description	PersonImageSynthesisaimsattransferringtheappearanceofthesourcepersonimageintoatargetpose. Existingmethods cannot handle largeposevariations and therefore suffer fromtwocritical problems: (1)synthesisdistortionduetotheentanglementofposeandappearanceinformationamongdifferentbody componentsand(2)failureinpreservingoriginalsemantics(e.g.,thesameoutfit).Inthisarticle,weexplicitly addressthesetwoproblemsbyproposingaPose-andAttribute-consistentPersonImageSynthesisNetwork (PAC-GAN).Toreduceposeandappearancematchingambiguity,weproposeacomponent-wisetransferring modelconsistingoftwostages.Theformerstagefocusesonlyonsynthesizingtargetposes,whilethelatter renderstargetappearancesbyexplicitlytransferringtheappearanceinformationfromthesourceimageto thetargetimageinacomponent-wisemanner. Inthisway,source-targetmatchingambiguityiseliminated duetothecomponent-wisedisentanglementofposeandappearancesynthesis.Second,tomaintainattribute consistency,werepresenttheinputimageasanattributevectorandimposeahigh-levelsemanticconstraint usingthisvectortoregularizethetargetsynthesis.ExtensiveexperimentalresultsontheDeepFashiondataset demonstratethesuperiorityofourmethodoverthestateoftheart,especiallyformaintainingposeandattributeconsistenciesunderlargeposevariations.
format	text
author	XU, Cheng CHEN, Zejun MAI, Jiajie XU, Xuemiao HE, Shengfeng
author_facet	XU, Cheng CHEN, Zejun MAI, Jiajie XU, Xuemiao HE, Shengfeng
author_sort	XU, Cheng
title	Pose- and Attribute-consistent Person Image Synthesis
title_short	Pose- and Attribute-consistent Person Image Synthesis
title_full	Pose- and Attribute-consistent Person Image Synthesis
title_fullStr	Pose- and Attribute-consistent Person Image Synthesis
title_full_unstemmed	Pose- and Attribute-consistent Person Image Synthesis
title_sort	pose- and attribute-consistent person image synthesis
publisher	Institutional Knowledge at Singapore Management University
publishDate	2023
url	https://ink.library.smu.edu.sg/sis_research/8369 https://ink.library.smu.edu.sg/context/sis_research/article/9372/viewcontent/Pose__and_Attribute_consistent_Person_Image_Synthesis.pdf
_version_	1787136844193857536

Pose- and Attribute-consistent Person Image Synthesis

Similar Items