Deformable GANs for Pose-Based Human Image Generation

In this paper we address the problem of generating person images conditioned on a given pose. Specifically, given an image of a person and a target pose, we synthesize a new image of that person in the novel pose. In order to deal with pixel-to-pixel misalignments caused by the pose differences, we...

Full description

Saved in:
Bibliographic Details
Published in:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 3408 - 3416
Main Authors: Siarohin, Aliaksandr, Sangineto, Enver, Lathuiliere, Stephane, Sebe, Nicu
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2018
Subjects:
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract In this paper we address the problem of generating person images conditioned on a given pose. Specifically, given an image of a person and a target pose, we synthesize a new image of that person in the novel pose. In order to deal with pixel-to-pixel misalignments caused by the pose differences, we introduce deformable skip connections in the generator of our Generative Adversarial Network. Moreover, a nearest-neighbour loss is proposed instead of the common L1 and L2 losses in order to match the details of the generated image with the target image. We test our approach using photos of persons in different poses and we compare our method with previous work in this area showing state-of-the-art results in two benchmarks. Our method can be applied to the wider field of deformable object generation, provided that the pose of the articulated object can be extracted using a keypoint detector.
AbstractList In this paper we address the problem of generating person images conditioned on a given pose. Specifically, given an image of a person and a target pose, we synthesize a new image of that person in the novel pose. In order to deal with pixel-to-pixel misalignments caused by the pose differences, we introduce deformable skip connections in the generator of our Generative Adversarial Network. Moreover, a nearest-neighbour loss is proposed instead of the common L1 and L2 losses in order to match the details of the generated image with the target image. We test our approach using photos of persons in different poses and we compare our method with previous work in this area showing state-of-the-art results in two benchmarks. Our method can be applied to the wider field of deformable object generation, provided that the pose of the articulated object can be extracted using a keypoint detector.
Author Sebe, Nicu
Sangineto, Enver
Siarohin, Aliaksandr
Lathuiliere, Stephane
Author_xml – sequence: 1
  givenname: Aliaksandr
  surname: Siarohin
  fullname: Siarohin, Aliaksandr
– sequence: 2
  givenname: Enver
  surname: Sangineto
  fullname: Sangineto, Enver
– sequence: 3
  givenname: Stephane
  surname: Lathuiliere
  fullname: Lathuiliere, Stephane
– sequence: 4
  givenname: Nicu
  surname: Sebe
  fullname: Sebe, Nicu
BookMark eNotjktLw0AURkdRsNasXbjJH0i8MzfzWtZY20LRIuq2zONGI00imbrw3xvQ1cfhwOG7ZGf90BNj1xxKzsHe1m-751IANyUASnvCMqsNl2iUqgTYUzbjoLBQltsLlqX0CQBCGTSVnDF5T80wds4fKF8tHlM-Ub4bEhV3LlHM19-d6_NN594nTz2N7tgO_RU7b9whUfa_c_b6sHyp18X2abWpF9viQ0g4Fhi1r4xDbQOisdxLDFIH3ShuYiNFI6OW2rrgBVnPRZRVCF7Z6I2rBALO2c1ftyWi_dfYdm782Rupp-8afwF_9EZZ
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2018.00359
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 9781538664209
1538664208
EISSN 1063-6919
EndPage 3416
ExternalDocumentID 8578457
Genre orig-research
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-h250t-3d7b48a379c33891b53c57c7f618df52f5d7579acb2e9b12d54ccb69db8a42303
IEDL.DBID RIE
ISICitedReferencesCount 356
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000457843603057&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:52:15 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-h250t-3d7b48a379c33891b53c57c7f618df52f5d7579acb2e9b12d54ccb69db8a42303
OpenAccessLink http://hdl.handle.net/11380/1264592
PageCount 9
ParticipantIDs ieee_primary_8578457
PublicationCentury 2000
PublicationDate 2018-Jun
PublicationDateYYYYMMDD 2018-06-01
PublicationDate_xml – month: 06
  year: 2018
  text: 2018-Jun
PublicationDecade 2010
PublicationTitle 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
PublicationTitleAbbrev CVPR
PublicationYear 2018
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0002683845
ssj0003211698
Score 2.6194992
Snippet In this paper we address the problem of generating person images conditioned on a given pose. Specifically, given an image of a person and a target pose, we...
SourceID ieee
SourceType Publisher
StartPage 3408
SubjectTerms Computer architecture
Decoding
Gallium nitride
Generators
Strain
Task analysis
Title Deformable GANs for Pose-Based Human Image Generation
URI https://ieeexplore.ieee.org/document/8578457
WOSCitedRecordID wos000457843603057&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED61FQNTgRbxlgdGQtM4ztkjFAosVYQAdav8uAgkaFHT8vuxk6gwsLD5LFmyPtt353sCnMeF_6EJjCNNiY1SyymSStiIO0riQnMnXd1sAicTOZ2qvAUXm1wYIqqCz-gyDCtfvlvYdTCVDaS_XqnANrQRsc7V2thTkkxy2XjIAs39zyZTsqnmM4zVYPSSP4ZYrhA8yUNt0l_tVCppMu7-bx870P9Jy2P5RuDsQovme9Bt9EjWvNKyB-KGKlXUvBO7u5qUzFMsX5QUXXuZ5VhluGcPH56VsLrsdDidPjyPb59G91HTHiF69XrLysOJJpWao7I8eBuN4FagxSIbSleIpBAOBSptTULKDBMnUmtNppyR2itRMd-HznwxpwNglGlZZNYDaHSK0mktHZKQTnlW7tceQi-gMPusK2DMGgCO_p4-hu0Acx1QdQKd1XJNp7Blv1Zv5fKsOrZve9aXVQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED6VggRTgRbxxgMjoUkcx_bIq7SiRBEqqFvl2BeBBC1qWn4_dhIVBhY2nyVL1mf77nxPgHM_tz80xn1PYai9SFP0hGTaowZDP1fUCFM1m-BJIsZjmTbgYpULg4hl8BleumHpyzczvXSmsq6w1ytifA3WWRSFQZWttbKohLGgovaROZrav00sRV3PJ_Bl9-YlfXLRXC58krrqpL8aqpTypNf63062ofOTmEfSlcjZgQZOd6FVa5KkfqdFG9gtlspo9o7k_iopiKVIOivQu7ZSy5DSdE8GH5aZkKrwtDufDjz37kY3fa9ukOC9Ws1lYQHlWSQU5VJT52_MGNWMa57HgTA5C3NmOONS6SxEmQWhYZHWWSxNJpRVo3y6B83pbIr7QDBWIo-1BTBTERdGKWE4MmGkZeZ27QG0HQqTz6oGxqQG4PDv6TPY7I8eh5PhIHk4gi0HeRVedQzNxXyJJ7ChvxZvxfy0PMJvju-anA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2018+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.atitle=Deformable+GANs+for+Pose-Based+Human+Image+Generation&rft.au=Siarohin%2C+Aliaksandr&rft.au=Sangineto%2C+Enver&rft.au=Lathuiliere%2C+Stephane&rft.au=Sebe%2C+Nicu&rft.date=2018-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=3408&rft.epage=3416&rft_id=info:doi/10.1109%2FCVPR.2018.00359&rft.externalDocID=8578457