Publication :
Deep learning-enabled framework for automatic lens design starting point generation

ali.license-refhttps://creativecommons.org/licenses/by/4.0fr
ali.license-ref.start-date2021-01-25fr
bul.description.provenancenoadg autorité-manquante : Côté spbarfr
bul.rights.dateAccepPubl2021-01-25fr
bul.rights.periodeEmbargoP0Mfr
bul.rights.typeDatedatePublicationfr
dc.contributor.authorCôté, Geoffroi
dc.contributor.authorThibault, Simon
dc.contributor.authorLalonde, Jean-François
dc.date.accessioned2021-02-18T13:03:30Z
dc.date.available2021-02-18T13:03:30Z
dc.date.issued2021-01-25
dc.description.abstractWe present a simple, highly modular deep neural network (DNN) framework to address the problem of automatically inferring lens design starting points tailored to the desired specifications. In contrast to previous work, our model can handle various and complex lens structures suitable for real-world problems such as Cooke Triplets or Double Gauss lenses. Our successfully trained dynamic model can infer lens designs with realistic glass materials whose optical performance compares favorably to reference designs from the literature on 80 different lens structures. Using our trained model as a backbone, we make available to the community a web application that outputs a selection of varied, high-quality starting points directly from the desired specifications, which we believe will complement any lens designer's toolbox.fr
dc.identifier.doi10.1364/OE.401590fr
dc.identifier.issn1094-4087fr
dc.identifier.urihttp://hdl.handle.net/20.500.11794/68199
dc.languageengfr
dc.publisherOptical Society of Americafr
dc.rightshttp://purl.org/coar/access_right/c_abf2
dc.subject.rvmApprentissage profondfr
dc.subject.rvmRéseaux neuronaux (Informatique)fr
dc.subject.rvmLentilles (Optique) -- Conception et constructionfr
dc.titleDeep learning-enabled framework for automatic lens design starting point generationfr
dc.typearticle de recherche
dc.type.legacyCOAR1_1::Texte::Périodique::Revue::Contribution à un journal::Article::Article de recherchefr
dcterms.bibliographicCitationOptics express, Vol. 29 (3), 3841-3854 (2021)fr
dspace.accessstatus.time2023-01-26 18:03:06
dspace.entity.typePublication
relation.isAuthorOfPublication266c268b-4959-4af9-820d-623fed91c98c
relation.isAuthorOfPublicationd4a21b62-cb04-44db-9fee-8b00022d11ca
relation.isAuthorOfPublication.latestForDiscovery266c268b-4959-4af9-820d-623fed91c98c
relation.isResourceTypeOfPublication4c433ef5-3937-4530-8252-cca17d715747
relation.isResourceTypeOfPublication.latestForDiscovery4c433ef5-3937-4530-8252-cca17d715747
rioxxterms.project.funder-nameNatural Sciences and Engineering Research Council of Canadafr
rioxxterms.project.funder-nameCanada First Research Excellence Fundfr
rioxxterms.versionVoRfr
rioxxterms.version-of-recordhttps://doi.org/10.1364/OE.401590fr
Fichiers
Bundle original
Voici les éléments 1 - 1 sur 1
En cours de chargement...
Vignette d'image
Nom :
oe-29-3-3841.pdf
Taille :
2.05 MB
Format :
Adobe Portable Document Format
Description :