SSSGAN: Satellite Style and Structure Generative Adversarial Networks

This work presents Satellite Style and Structure Generative Adversarial Network (SSGAN), a generative model of high resolution satellite imagery to support image segmentation. Based on spatially adaptive denormalization modules (SPADE) that modulate the activations with respect to segmentation map s...

ver descrição completa

Detalhes bibliográficos
Autores: Marín Tur, Javier, Escalera Guerrero, Sergio
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:España
Recursos:Universidad de Barcelona
Repositorio:Dipòsit Digital de la UB
OAI Identifier:oai:diposit.ub.edu:2445/181116
Acesso em linha:https://hdl.handle.net/2445/181116
Access Level:acceso abierto
Palavra-chave:Imatges satel·litàries
Visió per ordinador
Aprenentatge automàtic
Remote-sensing images
Computer vision
Machine learning
id ES_4519ff1fa8ba4e0e3ac6e60fec5ce63d
oai_identifier_str oai:diposit.ub.edu:2445/181116
network_acronym_str ES
network_name_str España
repository_id_str
spelling SSSGAN: Satellite Style and Structure Generative Adversarial NetworksMarín Tur, JavierEscalera Guerrero, SergioImatges satel·litàriesVisió per ordinadorAprenentatge automàticRemote-sensing imagesComputer visionMachine learningThis work presents Satellite Style and Structure Generative Adversarial Network (SSGAN), a generative model of high resolution satellite imagery to support image segmentation. Based on spatially adaptive denormalization modules (SPADE) that modulate the activations with respect to segmentation map structure, in addition to global descriptor vectors that capture the semantic information in a vector with respect to Open Street Maps (OSM) classes, this model is able to produce consistent aerial imagery. By decoupling the generation of aerial images into a structure map and a carefully defined style vector, we were able to improve the realism and geodiversity of the synthesis with respect to the state-of-the-art baseline. Therefore, the proposed model allows us to control the generation not only with respect to the desired structure, but also with respect to a geographic area.MDPI2021info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://hdl.handle.net/2445/181116Articles publicats en revistes (Matemàtiques i Informàtica)reponame:Dipòsit Digital de la UBinstname:Universidad de BarcelonaInglésReproducció del document publicat a: https://doi.org/10.3390/rs13193984Remote Sensing, 2021, vol. 13, num. 19https://doi.org/10.3390/rs13193984cc-by (c) Marín, Javier et al., 2021https://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:diposit.ub.edu:2445/1811162026-05-27T06:46:51Z
dc.title.none.fl_str_mv SSSGAN: Satellite Style and Structure Generative Adversarial Networks
title SSSGAN: Satellite Style and Structure Generative Adversarial Networks
spellingShingle SSSGAN: Satellite Style and Structure Generative Adversarial Networks
Marín Tur, Javier
Imatges satel·litàries
Visió per ordinador
Aprenentatge automàtic
Remote-sensing images
Computer vision
Machine learning
title_short SSSGAN: Satellite Style and Structure Generative Adversarial Networks
title_full SSSGAN: Satellite Style and Structure Generative Adversarial Networks
title_fullStr SSSGAN: Satellite Style and Structure Generative Adversarial Networks
title_full_unstemmed SSSGAN: Satellite Style and Structure Generative Adversarial Networks
title_sort SSSGAN: Satellite Style and Structure Generative Adversarial Networks
dc.creator.none.fl_str_mv Marín Tur, Javier
Escalera Guerrero, Sergio
author Marín Tur, Javier
author_facet Marín Tur, Javier
Escalera Guerrero, Sergio
author_role author
author2 Escalera Guerrero, Sergio
author2_role author
dc.subject.none.fl_str_mv Imatges satel·litàries
Visió per ordinador
Aprenentatge automàtic
Remote-sensing images
Computer vision
Machine learning
topic Imatges satel·litàries
Visió per ordinador
Aprenentatge automàtic
Remote-sensing images
Computer vision
Machine learning
description This work presents Satellite Style and Structure Generative Adversarial Network (SSGAN), a generative model of high resolution satellite imagery to support image segmentation. Based on spatially adaptive denormalization modules (SPADE) that modulate the activations with respect to segmentation map structure, in addition to global descriptor vectors that capture the semantic information in a vector with respect to Open Street Maps (OSM) classes, this model is able to produce consistent aerial imagery. By decoupling the generation of aerial images into a structure map and a carefully defined style vector, we were able to improve the realism and geodiversity of the synthesis with respect to the state-of-the-art baseline. Therefore, the proposed model allows us to control the generation not only with respect to the desired structure, but also with respect to a geographic area.
publishDate 2021
dc.date.none.fl_str_mv 2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/2445/181116
url https://hdl.handle.net/2445/181116
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Reproducció del document publicat a: https://doi.org/10.3390/rs13193984
Remote Sensing, 2021, vol. 13, num. 19
https://doi.org/10.3390/rs13193984
dc.rights.none.fl_str_mv cc-by (c) Marín, Javier et al., 2021
https://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv cc-by (c) Marín, Javier et al., 2021
https://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv Articles publicats en revistes (Matemàtiques i Informàtica)
reponame:Dipòsit Digital de la UB
instname:Universidad de Barcelona
instname_str Universidad de Barcelona
reponame_str Dipòsit Digital de la UB
collection Dipòsit Digital de la UB
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407139084107776
score 15.300719

Registos relacionados