Learning Centre

Noise2Noise

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.author Lehtinen, Jaakko
dc.contributor.author Munkberg, Jacob
dc.contributor.author Hasselgren, Jon
dc.contributor.author Laine, Samuli
dc.contributor.author Karras, Tero
dc.contributor.author Aittala, Miika
dc.contributor.author Aila, Timo
dc.contributor.editor Dy, Jennifer
dc.contributor.editor Krause, Andreas
dc.date.accessioned 2020-02-03T09:00:40Z
dc.date.available 2020-02-03T09:00:40Z
dc.date.issued 2018-01-01
dc.identifier.citation Lehtinen , J , Munkberg , J , Hasselgren , J , Laine , S , Karras , T , Aittala , M & Aila , T 2018 , Noise2Noise : Learning image restoration without clean data . in J Dy & A Krause (eds) , 35th International Conference on Machine Learning, ICML 2018 . vol. 7 , Proceedings of Machine Learning Research , no. 80 , International Machine Learning Society (IMLS) , pp. 4620-4631 , International Conference on Machine Learning , Stockholm , Sweden , 10/07/2018 . en
dc.identifier.isbn 9781510867963
dc.identifier.issn 1938-7228
dc.identifier.other PURE UUID: 68e78264-82b3-461a-9bb8-f230ddba1175
dc.identifier.other PURE ITEMURL: https://research.aalto.fi/en/publications/68e78264-82b3-461a-9bb8-f230ddba1175
dc.identifier.other PURE LINK: http://www.scopus.com/inward/record.url?scp=85057221611&partnerID=8YFLogxK
dc.identifier.other PURE FILEURL: https://research.aalto.fi/files/40605293/lehtinen18a.pdf
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/42912
dc.description.abstract We apply basic statistical reasoning to signal reconstruction by machine learning - learning to map corrupted observations to clean signals - with a simple and powerful conclusion: It is possible to learn to restore images by only looking at corrupted examples, at performance at and some-times exceeding training using clean data, without explicit image priors or likelihood models of the corruption. In practice, we show that a single model learns photographic noise removal, denois- ing synthetic Monte Carlo images, and reconstruction of undersampled MRI scans - all corrupted by different processes - based on noisy data only. en
dc.format.extent 12
dc.format.extent 4620-4631
dc.format.mimetype application/pdf
dc.language.iso en en
dc.publisher PMLR
dc.relation.ispartof International Conference on Machine Learning en
dc.relation.ispartofseries 35th International Conference on Machine Learning, ICML 2018 en
dc.relation.ispartofseries Volume 7 en
dc.relation.ispartofseries Proceedings of Machine Learning Research en
dc.relation.ispartofseries issue 80 en
dc.rights openAccess en
dc.title Noise2Noise en
dc.type A4 Artikkeli konferenssijulkaisussa fi
dc.description.version Peer reviewed en
dc.contributor.department Professorship Lehtinen Jaakko
dc.contributor.department Nvidia
dc.contributor.department Massachusetts Institute of Technology
dc.contributor.department Department of Computer Science en
dc.identifier.urn URN:NBN:fi:aalto-202002031992
dc.type.version publishedVersion


Files in this item

Files Size Format View

There are no open access files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search archive


Advanced Search

article-iconSubmit a publication

Browse

Statistics