A short analysis of BigColor for image colorization.

García, Rosana - Randall, Gregory - Raad, Lara

Resumen:

This work analyzes the BigColor method, a fully automatic colorization approach that aims to meet the challenge of providing realistic and vivid colorization for complex and diverse images in real-world scenarios. The method is a BigGAN-inspired encoder-generator network, using a spatial feature map, enabling single forward-pass colorization, supporting arbitrary input resolutions, and producing multimodal colorization results. We provide a short analysis of the method’s results and highlight some limitations alongside its achievements.


Detalles Bibliográficos
2024
Colorization
Generative color prior
BigGAN
Inglés
Universidad de la República
COLIBRI
https://www.ipol.im/pub/art/2024/542/
https://hdl.handle.net/20.500.12008/43955
Acceso abierto
Licencia Creative Commons Atribución - No Comercial - Compartir Igual (CC - By-NC-SA 4.0)
_version_ 1807522942634950656
author García, Rosana
author2 Randall, Gregory
Raad, Lara
author2_role author
author
author_facet García, Rosana
Randall, Gregory
Raad, Lara
author_role author
bitstream.checksum.fl_str_mv 6429389a7df7277b72b7924fdc7d47a9
a9ac1bac94fe38dbe560422d834a993f
1f211367f76b79f4a1d61a3586a52e65
27d85011139cdc22b845da52c980f01f
55c41d1cc53f239b62d8cc197330d9df
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
MD5
bitstream.url.fl_str_mv http://localhost:8080/xmlui/bitstream/20.500.12008/43955/5/license.txt
http://localhost:8080/xmlui/bitstream/20.500.12008/43955/2/license_url
http://localhost:8080/xmlui/bitstream/20.500.12008/43955/3/license_text
http://localhost:8080/xmlui/bitstream/20.500.12008/43955/4/license_rdf
http://localhost:8080/xmlui/bitstream/20.500.12008/43955/1/GRR24a.pdf
collection COLIBRI
dc.contributor.filiacion.none.fl_str_mv García Rosana, Universidad de la República (Uruguay). Facultad de Ingeniería.
Randall Gregory, Universidad de la República (Uruguay). Facultad de Ingeniería.
Raad Lara, Université Gustave Eiffel, France
dc.creator.none.fl_str_mv García, Rosana
Randall, Gregory
Raad, Lara
dc.date.accessioned.none.fl_str_mv 2024-05-31T13:58:54Z
dc.date.available.none.fl_str_mv 2024-05-31T13:58:54Z
dc.date.issued.none.fl_str_mv 2024
dc.description.abstract.none.fl_txt_mv This work analyzes the BigColor method, a fully automatic colorization approach that aims to meet the challenge of providing realistic and vivid colorization for complex and diverse images in real-world scenarios. The method is a BigGAN-inspired encoder-generator network, using a spatial feature map, enabling single forward-pass colorization, supporting arbitrary input resolutions, and producing multimodal colorization results. We provide a short analysis of the method’s results and highlight some limitations alongside its achievements.
dc.format.extent.es.fl_str_mv 15 p.
dc.format.mimetype.es.fl_str_mv application/pdf
dc.identifier.citation.es.fl_str_mv García, R., Randall, G. y Raad, L. "A short analysis of BigColor for image colorization". IPOL. Journal Image Processing On Line. [en línea]. 2024, no. 14, pp. 144-158. DOI: 10.5201/ipol.2024.542.
dc.identifier.doi.none.fl_str_mv 10.5201/ipol.2024.542
dc.identifier.issn.none.fl_str_mv 2105–1232
dc.identifier.uri.none.fl_str_mv https://www.ipol.im/pub/art/2024/542/
https://hdl.handle.net/20.500.12008/43955
dc.language.iso.none.fl_str_mv en
eng
dc.publisher.es.fl_str_mv Centre Borelli, ENS Paris-Saclay; DMI, Universitat de les Illes Balears; Fing, Universidad de la República.
dc.relation.ispartof.es.fl_str_mv IPOL. Journal Image Processing On Line, no. 14, May. 2024, pp. 144-158.
dc.rights.license.none.fl_str_mv Licencia Creative Commons Atribución - No Comercial - Compartir Igual (CC - By-NC-SA 4.0)
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
dc.source.none.fl_str_mv reponame:COLIBRI
instname:Universidad de la República
instacron:Universidad de la República
dc.subject.es.fl_str_mv Colorization
Generative color prior
BigGAN
dc.title.none.fl_str_mv A short analysis of BigColor for image colorization.
dc.type.es.fl_str_mv Artículo
dc.type.none.fl_str_mv info:eu-repo/semantics/article
dc.type.version.none.fl_str_mv info:eu-repo/semantics/publishedVersion
description This work analyzes the BigColor method, a fully automatic colorization approach that aims to meet the challenge of providing realistic and vivid colorization for complex and diverse images in real-world scenarios. The method is a BigGAN-inspired encoder-generator network, using a spatial feature map, enabling single forward-pass colorization, supporting arbitrary input resolutions, and producing multimodal colorization results. We provide a short analysis of the method’s results and highlight some limitations alongside its achievements.
eu_rights_str_mv openAccess
format article
id COLIBRI_2b24174d25ef949f6814e628ba6c1118
identifier_str_mv García, R., Randall, G. y Raad, L. "A short analysis of BigColor for image colorization". IPOL. Journal Image Processing On Line. [en línea]. 2024, no. 14, pp. 144-158. DOI: 10.5201/ipol.2024.542.
2105–1232
10.5201/ipol.2024.542
instacron_str Universidad de la República
institution Universidad de la República
instname_str Universidad de la República
language eng
language_invalid_str_mv en
network_acronym_str COLIBRI
network_name_str COLIBRI
oai_identifier_str oai:colibri.udelar.edu.uy:20.500.12008/43955
publishDate 2024
reponame_str COLIBRI
repository.mail.fl_str_mv mabel.seroubian@seciu.edu.uy
repository.name.fl_str_mv COLIBRI - Universidad de la República
repository_id_str 4771
rights_invalid_str_mv Licencia Creative Commons Atribución - No Comercial - Compartir Igual (CC - By-NC-SA 4.0)
spelling García Rosana, Universidad de la República (Uruguay). Facultad de Ingeniería.Randall Gregory, Universidad de la República (Uruguay). Facultad de Ingeniería.Raad Lara, Université Gustave Eiffel, France2024-05-31T13:58:54Z2024-05-31T13:58:54Z2024García, R., Randall, G. y Raad, L. "A short analysis of BigColor for image colorization". IPOL. Journal Image Processing On Line. [en línea]. 2024, no. 14, pp. 144-158. DOI: 10.5201/ipol.2024.542.2105–1232https://www.ipol.im/pub/art/2024/542/https://hdl.handle.net/20.500.12008/4395510.5201/ipol.2024.542This work analyzes the BigColor method, a fully automatic colorization approach that aims to meet the challenge of providing realistic and vivid colorization for complex and diverse images in real-world scenarios. The method is a BigGAN-inspired encoder-generator network, using a spatial feature map, enabling single forward-pass colorization, supporting arbitrary input resolutions, and producing multimodal colorization results. We provide a short analysis of the method’s results and highlight some limitations alongside its achievements.Submitted by Ribeiro Jorge (jribeiro@fing.edu.uy) on 2024-05-26T03:53:31Z No. of bitstreams: 2 license_rdf: 26308 bytes, checksum: 27d85011139cdc22b845da52c980f01f (MD5) GRR24a.pdf: 19661511 bytes, checksum: 55c41d1cc53f239b62d8cc197330d9df (MD5)Approved for entry into archive by Machado Jimena (jmachado@fing.edu.uy) on 2024-05-30T14:37:36Z (GMT) No. of bitstreams: 2 license_rdf: 26308 bytes, checksum: 27d85011139cdc22b845da52c980f01f (MD5) GRR24a.pdf: 19661511 bytes, checksum: 55c41d1cc53f239b62d8cc197330d9df (MD5)Made available in DSpace by Luna Fabiana (fabiana.luna@seciu.edu.uy) on 2024-05-31T13:58:54Z (GMT). No. of bitstreams: 2 license_rdf: 26308 bytes, checksum: 27d85011139cdc22b845da52c980f01f (MD5) GRR24a.pdf: 19661511 bytes, checksum: 55c41d1cc53f239b62d8cc197330d9df (MD5) Previous issue date: 202415 p.application/pdfenengCentre Borelli, ENS Paris-Saclay; DMI, Universitat de les Illes Balears; Fing, Universidad de la República.IPOL. Journal Image Processing On Line, no. 14, May. 2024, pp. 144-158.Las obras depositadas en el Repositorio se rigen por la Ordenanza de los Derechos de la Propiedad Intelectual de la Universidad de la República.(Res. Nº 91 de C.D.C. de 8/III/1994 – D.O. 7/IV/1994) y por la Ordenanza del Repositorio Abierto de la Universidad de la República (Res. Nº 16 de C.D.C. de 07/10/2014)info:eu-repo/semantics/openAccessLicencia Creative Commons Atribución - No Comercial - Compartir Igual (CC - By-NC-SA 4.0)ColorizationGenerative color priorBigGANA short analysis of BigColor for image colorization.Artículoinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionreponame:COLIBRIinstname:Universidad de la Repúblicainstacron:Universidad de la RepúblicaGarcía, RosanaRandall, GregoryRaad, LaraLICENSElicense.txtlicense.txttext/plain; charset=utf-84267http://localhost:8080/xmlui/bitstream/20.500.12008/43955/5/license.txt6429389a7df7277b72b7924fdc7d47a9MD55CC-LICENSElicense_urllicense_urltext/plain; charset=utf-850http://localhost:8080/xmlui/bitstream/20.500.12008/43955/2/license_urla9ac1bac94fe38dbe560422d834a993fMD52license_textlicense_texttext/html; charset=utf-822698http://localhost:8080/xmlui/bitstream/20.500.12008/43955/3/license_text1f211367f76b79f4a1d61a3586a52e65MD53license_rdflicense_rdfapplication/rdf+xml; charset=utf-826308http://localhost:8080/xmlui/bitstream/20.500.12008/43955/4/license_rdf27d85011139cdc22b845da52c980f01fMD54ORIGINALGRR24a.pdfGRR24a.pdfapplication/pdf19661511http://localhost:8080/xmlui/bitstream/20.500.12008/43955/1/GRR24a.pdf55c41d1cc53f239b62d8cc197330d9dfMD5120.500.12008/439552024-05-31 10:58:54.871oai:colibri.udelar.edu.uy:20.500.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Universidadhttps://udelar.edu.uy/https://www.colibri.udelar.edu.uy/oai/requestmabel.seroubian@seciu.edu.uyUruguayopendoar:47712024-07-25T14:33:52.597820COLIBRI - Universidad de la Repúblicafalse
spellingShingle A short analysis of BigColor for image colorization.
García, Rosana
Colorization
Generative color prior
BigGAN
status_str publishedVersion
title A short analysis of BigColor for image colorization.
title_full A short analysis of BigColor for image colorization.
title_fullStr A short analysis of BigColor for image colorization.
title_full_unstemmed A short analysis of BigColor for image colorization.
title_short A short analysis of BigColor for image colorization.
title_sort A short analysis of BigColor for image colorization.
topic Colorization
Generative color prior
BigGAN
url https://www.ipol.im/pub/art/2024/542/
https://hdl.handle.net/20.500.12008/43955

Resultados similares