Publication : Deep learning-enabled framework for automatic lens design starting point generation
ali.license-ref | https://creativecommons.org/licenses/by/4.0 | fr |
ali.license-ref.start-date | 2021-01-25 | fr |
bul.description.provenance | noadg autorité-manquante : Côté spbar | fr |
bul.rights.dateAccepPubl | 2021-01-25 | fr |
bul.rights.periodeEmbargo | P0M | fr |
bul.rights.typeDate | datePublication | fr |
dc.contributor.author | Côté, Geoffroi | |
dc.contributor.author | Thibault, Simon | |
dc.contributor.author | Lalonde, Jean-François | |
dc.date.accessioned | 2021-02-18T13:03:30Z | |
dc.date.available | 2021-02-18T13:03:30Z | |
dc.date.issued | 2021-01-25 | |
dc.description.abstract | We 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.doi | 10.1364/OE.401590 | fr |
dc.identifier.issn | 1094-4087 | fr |
dc.identifier.uri | http://hdl.handle.net/20.500.11794/68199 | |
dc.language | eng | fr |
dc.publisher | Optical Society of America | fr |
dc.rights | http://purl.org/coar/access_right/c_abf2 | |
dc.subject.rvm | Apprentissage profond | fr |
dc.subject.rvm | Réseaux neuronaux (Informatique) | fr |
dc.subject.rvm | Lentilles (Optique) -- Conception et construction | fr |
dc.title | Deep learning-enabled framework for automatic lens design starting point generation | fr |
dc.type | article de recherche | |
dc.type.legacy | COAR1_1::Texte::Périodique::Revue::Contribution à un journal::Article::Article de recherche | fr |
dcterms.bibliographicCitation | Optics express, Vol. 29 (3), 3841-3854 (2021) | fr |
dspace.accessstatus.time | 2023-01-26 18:03:06 | |
dspace.entity.type | Publication | |
relation.isAuthorOfPublication | 266c268b-4959-4af9-820d-623fed91c98c | |
relation.isAuthorOfPublication | d4a21b62-cb04-44db-9fee-8b00022d11ca | |
relation.isAuthorOfPublication.latestForDiscovery | 266c268b-4959-4af9-820d-623fed91c98c | |
relation.isResourceTypeOfPublication | 4c433ef5-3937-4530-8252-cca17d715747 | |
relation.isResourceTypeOfPublication.latestForDiscovery | 4c433ef5-3937-4530-8252-cca17d715747 | |
rioxxterms.project.funder-name | Natural Sciences and Engineering Research Council of Canada | fr |
rioxxterms.project.funder-name | Canada First Research Excellence Fund | fr |
rioxxterms.version | VoR | fr |
rioxxterms.version-of-record | https://doi.org/10.1364/OE.401590 | fr |
Fichiers
Bundle original
1 - 1 sur 1
En cours de chargement...
- Nom :
- oe-29-3-3841.pdf
- Taille :
- 2.05 MB
- Format :
- Adobe Portable Document Format
- Description :