Photo-realistic photo synthesis using improved conditional generative adversarial networks

There are a wide range of potential uses for both the forward (generating face drawings from actual images) and backward (generating photos from synthetic face sketches). However, photo/sketch synthesis is still a difficult problem to solve because of the distinct differences between photos and sket...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IAES international journal of artificial intelligence Ročník 13; číslo 1; s. 516
Hlavní autori: Mandara Kirimanjeshwara, Raghavendra Shetty, Prasad, Sarappadi Narasimha
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: 01.03.2024
ISSN:2089-4872, 2252-8938
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract There are a wide range of potential uses for both the forward (generating face drawings from actual images) and backward (generating photos from synthetic face sketches). However, photo/sketch synthesis is still a difficult problem to solve because of the distinct differences between photos and sketches. Existing frameworks often struggle to acquire a strong mapping among the geometry of drawing and its corresponding photo-realistic pictures because of the little amount of paired sketch-photo training data available. In this study, we adopt the perspective that this is an image-to-image translation issue and investigate the usage of the well-known enhanced pix2pix generative adversarial networks (GANs) to generate high-quality photo-realistic pictures from drawings; we make use of three distinct datasets. While recent GAN-based approaches have shown promise in image translation, they still struggle to produce high-resolution, photorealistic pictures. This technique uses supervised learning to train the generator's hidden layers to produce low-resolution pictures initially, then uses the network's implicit refinement to produce high-resolution images. Extensive tests on three sketch-photo datasets (two publicly accessible and one we produced) are used to evaluate. Our solution outperforms existing image translation techniques by producing more photorealistic visuals with a peak signal-to-noise ratio of 59.85% and pixel accuracy of 82.7%. 
AbstractList There are a wide range of potential uses for both the forward (generating face drawings from actual images) and backward (generating photos from synthetic face sketches). However, photo/sketch synthesis is still a difficult problem to solve because of the distinct differences between photos and sketches. Existing frameworks often struggle to acquire a strong mapping among the geometry of drawing and its corresponding photo-realistic pictures because of the little amount of paired sketch-photo training data available. In this study, we adopt the perspective that this is an image-to-image translation issue and investigate the usage of the well-known enhanced pix2pix generative adversarial networks (GANs) to generate high-quality photo-realistic pictures from drawings; we make use of three distinct datasets. While recent GAN-based approaches have shown promise in image translation, they still struggle to produce high-resolution, photorealistic pictures. This technique uses supervised learning to train the generator's hidden layers to produce low-resolution pictures initially, then uses the network's implicit refinement to produce high-resolution images. Extensive tests on three sketch-photo datasets (two publicly accessible and one we produced) are used to evaluate. Our solution outperforms existing image translation techniques by producing more photorealistic visuals with a peak signal-to-noise ratio of 59.85% and pixel accuracy of 82.7%. 
Author Mandara Kirimanjeshwara, Raghavendra Shetty
Prasad, Sarappadi Narasimha
Author_xml – sequence: 1
  givenname: Raghavendra Shetty
  orcidid: 0000-0001-9489-4348
  surname: Mandara Kirimanjeshwara
  fullname: Mandara Kirimanjeshwara, Raghavendra Shetty
– sequence: 2
  givenname: Sarappadi Narasimha
  orcidid: 0000-0002-8304-8506
  surname: Prasad
  fullname: Prasad, Sarappadi Narasimha
BookMark eNot0E1OwzAQBWALFYlSegWUCyRk7Dq2l6jiT6oEC9iwsdxk3A60dmSHoN6eUljNm7d4i--STUIMyNg11BWANHBDH46qEURFUPW9hKaUXJyxKeeSl9oIPTnmWptyoRW_YPOcaV0DGK6lUVP2_rKNQywTuh3lgdqi__2LfAjDFjPl4itT2BS071McsSvaGDoaKAa3KzYYMLmBRixcN2LKLtGxDjh8x_SZr9i5d7uM8_87Y2_3d6_Lx3L1_PC0vF2VLTRSlEpqA1J3dYvdgmsHBoWSoLzxTiq-dq1UncJ64ZXgiN41IBrRNop7L1CCmLHmb7dNMeeE3vaJ9i4dLNT2hGR_kewRyRLYE5I9Iokf7eNh6w
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.11591/ijai.v13.i1.pp516-523
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2252-8938
ExternalDocumentID 10_11591_ijai_v13_i1_pp516_523
GroupedDBID 8FE
8FG
AAKDD
AAYXX
ABUWG
AFFHD
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ARAPS
AZQEC
BENPR
BGLVJ
BPHCQ
BVBZV
CCPQU
CITATION
DWQXO
GNUQQ
HCIFZ
K6V
K7-
P62
PHGZM
PHGZT
PQGLB
PQQKQ
PROAC
RNS
ID FETCH-LOGICAL-c1653-7589158d0ced428a19e37517f9fa572bac57d7e04f732eefa61363c672ff3e513
ISSN 2089-4872
IngestDate Sat Nov 29 05:33:40 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License http://creativecommons.org/licenses/by-sa/4.0
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c1653-7589158d0ced428a19e37517f9fa572bac57d7e04f732eefa61363c672ff3e513
ORCID 0000-0002-8304-8506
0000-0001-9489-4348
OpenAccessLink https://ijai.iaescore.com/index.php/IJAI/article/download/23094/13853
ParticipantIDs crossref_primary_10_11591_ijai_v13_i1_pp516_523
PublicationCentury 2000
PublicationDate 2024-03-01
PublicationDateYYYYMMDD 2024-03-01
PublicationDate_xml – month: 03
  year: 2024
  text: 2024-03-01
  day: 01
PublicationDecade 2020
PublicationTitle IAES international journal of artificial intelligence
PublicationYear 2024
SSID ssib011928597
ssib033899589
ssj0001341662
ssib044738854
Score 2.2482884
Snippet There are a wide range of potential uses for both the forward (generating face drawings from actual images) and backward (generating photos from synthetic face...
SourceID crossref
SourceType Index Database
StartPage 516
Title Photo-realistic photo synthesis using improved conditional generative adversarial networks
Volume 13
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2252-8938
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib044738854
  issn: 2089-4872
  databaseCode: M~E
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 2252-8938
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001341662
  issn: 2089-4872
  databaseCode: P5Z
  dateStart: 20170101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 2252-8938
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001341662
  issn: 2089-4872
  databaseCode: K7-
  dateStart: 20170101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: East & South Asia Database (ProQuest)
  customDbUrl:
  eissn: 2252-8938
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001341662
  issn: 2089-4872
  databaseCode: BVBZV
  dateStart: 20170101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/eastsouthasia
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2252-8938
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001341662
  issn: 2089-4872
  databaseCode: BENPR
  dateStart: 20170101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1La9wwEBbbtIde-i59o0NvwYktWZZ0DCWlpSUsJC2hF6PYUqyQeM3a2eaP9f91JPlFUkpzKCxmV96d3fV8nhmNRt8g9B48Lti4mEdlmpIoVRJuKXXCIm1EkphEG-aXC75_5QcH4vhYLheLX8NemM05r2txdSWb_6pqGANlu62zt1D3KBQG4DkoHY6gdjj-k-KX1apbRRALnnsO5u3GvXbMBBDqOfaRS58dsD6ZoN2eNrdoHRKCp56D2hcTKdeouVW-p0cdSsXbeSD7eW__0HNNTOnEGQmF-1k9NYWdcX5O6W-XvlDbX6zjuqjPdFv9VOsQxqrTynW4L-H0YaW7bkz5L9eqVWMWu2lUacE3wKC9qNQ8eUHSqXor2DgSCxnBnCkYZB3GCAMjLQPpy2ik6Q0wBovLwlbNm56ASecK7JmyO5uE7lhwSQ282c28J983rPdfc4ljoaKfIoGk3MnJQU5uk9zLyUHOHXSXcDjragF4NJixBIJmwabFWeooDNlE6p-mnArRR3E-FQiRROZb346Xo9_L7r56949_YRZGzeKho0foQT-RwXsBgI_RQtdP0MOhSQjufcZT9OMaHrHHIx7xiD0e8YBHPMMjnvCIZ3jEAx6foW8f948-fIr6hh5RkWSMRty1sGSijAtdwrRXJVJTzhJupFGMkxNVMF5yHaeGU6K1URBrZrTIODGGapbQ52irXtX6BcLC9eIojBasJKkxpZCKFMbAI5aCZeIl2h2uT94E3pb878p8detPvEb3J0y_QVvd-lK_RfeKTWfb9TuPid_4Vpgf
linkProvider ProQuest
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%3Ajournal&rft.genre=article&rft.atitle=Photo-realistic+photo+synthesis+using+improved+conditional+generative+adversarial+networks&rft.jtitle=IAES+international+journal+of+artificial+intelligence&rft.au=Mandara+Kirimanjeshwara%2C+Raghavendra+Shetty&rft.au=Prasad%2C+Sarappadi+Narasimha&rft.date=2024-03-01&rft.issn=2089-4872&rft.eissn=2252-8938&rft.volume=13&rft.issue=1&rft.spage=516&rft_id=info:doi/10.11591%2Fijai.v13.i1.pp516-523&rft.externalDBID=n%2Fa&rft.externalDocID=10_11591_ijai_v13_i1_pp516_523
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2089-4872&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2089-4872&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2089-4872&client=summon