Ground-based image deconvolution with Swin Transformer UNet

Aims. As ground-based all-sky astronomical surveys will gather millions of images in the coming years, a critical requirement emerges for the development of fast deconvolution algorithms capable of efficiently improving the spatial resolution of these images. By successfully recovering clean and hig...

Descripción completa

Detalles Bibliográficos
Autores: Akhaury, Utsav, Jablonka, Pascale, Starck, J.-L., Courbin, Frédéric
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:2445/221096
Acceso en línea:https://hdl.handle.net/2445/221096
http://hdl.handle.net/2445/221096
Access Level:acceso abierto
Palabra clave:Processament de dades
Processament d'imatges
Data processing
Image processing
id ES_bbe57178fda99c4ecef2a1cb1b86d4a0
oai_identifier_str oai:recercat.cat:2445/221096
network_acronym_str ES
network_name_str España
repository_id_str
spelling Ground-based image deconvolution with Swin Transformer UNetAkhaury, UtsavJablonka, PascaleStarck, J.-L.Courbin, FrédéricProcessament de dadesProcessament d'imatgesData processingImage processingAims. As ground-based all-sky astronomical surveys will gather millions of images in the coming years, a critical requirement emerges for the development of fast deconvolution algorithms capable of efficiently improving the spatial resolution of these images. By successfully recovering clean and high-resolution images from these surveys, the objective is to deepen the understanding of galaxy formation and evolution through accurate photometric measurements. Methods. We introduce a two-step deconvolution framework using a Swin Transformer architecture. Our study reveals that the deep learning-based solution introduces a bias, constraining the scope of scientific analysis. To address this limitation, we propose a novel third step relying on the active coefficients in the sparsity wavelet framework. Results. We conducted a performance comparison between our deep learning-based method and Firedec, a classical deconvolution algorithm, based on an analysis of a subset of the EDisCS cluster samples. We demonstrate the advantage of our method in terms of resolution recovery, generalisation to different noise properties, and computational efficiency. The analysis of this cluster sample not only allowed us to assess the efficiency of our method, but it also enabled us to quantify the number of clumps within these galaxies in relation to their disc colour. This robust technique that we propose holds promise for identifying structures in the distant universe through ground-based images. EDP Sciences2025202520242025info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersion10 p.application/pdfhttps://hdl.handle.net/2445/221096http://hdl.handle.net/2445/221096Articles publicats en revistes (Institut de Ciències del Cosmos (ICCUB))reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)InglésReproducció del document publicat a: https://doi.org/10.1051/0004-6361/202449495Astronomy & Astrophysics, 2024, vol. 688https://doi.org/10.1051/0004-6361/202449495cc-by (c) Akhaury, Utsav et al., 2024http://creativecommons.org/licenses/by/3.0/es/info:eu-repo/semantics/openAccessoai:recercat.cat:2445/2210962026-05-29T05:05:01Z
dc.title.none.fl_str_mv Ground-based image deconvolution with Swin Transformer UNet
title Ground-based image deconvolution with Swin Transformer UNet
spellingShingle Ground-based image deconvolution with Swin Transformer UNet
Akhaury, Utsav
Processament de dades
Processament d'imatges
Data processing
Image processing
title_short Ground-based image deconvolution with Swin Transformer UNet
title_full Ground-based image deconvolution with Swin Transformer UNet
title_fullStr Ground-based image deconvolution with Swin Transformer UNet
title_full_unstemmed Ground-based image deconvolution with Swin Transformer UNet
title_sort Ground-based image deconvolution with Swin Transformer UNet
dc.creator.none.fl_str_mv Akhaury, Utsav
Jablonka, Pascale
Starck, J.-L.
Courbin, Frédéric
author Akhaury, Utsav
author_facet Akhaury, Utsav
Jablonka, Pascale
Starck, J.-L.
Courbin, Frédéric
author_role author
author2 Jablonka, Pascale
Starck, J.-L.
Courbin, Frédéric
author2_role author
author
author
dc.subject.none.fl_str_mv Processament de dades
Processament d'imatges
Data processing
Image processing
topic Processament de dades
Processament d'imatges
Data processing
Image processing
description Aims. As ground-based all-sky astronomical surveys will gather millions of images in the coming years, a critical requirement emerges for the development of fast deconvolution algorithms capable of efficiently improving the spatial resolution of these images. By successfully recovering clean and high-resolution images from these surveys, the objective is to deepen the understanding of galaxy formation and evolution through accurate photometric measurements. Methods. We introduce a two-step deconvolution framework using a Swin Transformer architecture. Our study reveals that the deep learning-based solution introduces a bias, constraining the scope of scientific analysis. To address this limitation, we propose a novel third step relying on the active coefficients in the sparsity wavelet framework. Results. We conducted a performance comparison between our deep learning-based method and Firedec, a classical deconvolution algorithm, based on an analysis of a subset of the EDisCS cluster samples. We demonstrate the advantage of our method in terms of resolution recovery, generalisation to different noise properties, and computational efficiency. The analysis of this cluster sample not only allowed us to assess the efficiency of our method, but it also enabled us to quantify the number of clumps within these galaxies in relation to their disc colour. This robust technique that we propose holds promise for identifying structures in the distant universe through ground-based images. 
publishDate 2024
dc.date.none.fl_str_mv 2024
2025
2025
2025
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/2445/221096
http://hdl.handle.net/2445/221096
url https://hdl.handle.net/2445/221096
http://hdl.handle.net/2445/221096
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/10.1051/0004-6361/202449495
Astronomy & Astrophysics, 2024, vol. 688
https://doi.org/10.1051/0004-6361/202449495
dc.rights.none.fl_str_mv cc-by (c) Akhaury, Utsav et al., 2024
http://creativecommons.org/licenses/by/3.0/es/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv cc-by (c) Akhaury, Utsav et al., 2024
http://creativecommons.org/licenses/by/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 10 p.
application/pdf
dc.publisher.none.fl_str_mv EDP Sciences
publisher.none.fl_str_mv EDP Sciences
dc.source.none.fl_str_mv Articles publicats en revistes (Institut de Ciències del Cosmos (ICCUB))
reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869418066076499968
score 15,811543

Similares en LA Referencia