Full metadata record
DC poleHodnotaJazyk
dc.contributor.authorBorkowski, Dariusz
dc.contributor.authorJanczak-Borkowska, Katarzyna
dc.contributor.editorSkala, Václav
dc.date.accessioned2021-08-31T05:22:02Z
dc.date.available2021-08-31T05:22:02Z
dc.date.issued2021
dc.identifier.citationWSCG 2021: full papers proceedings: 29. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 1-10.en
dc.identifier.isbn978-80-86943-34-3
dc.identifier.issn2464-4617
dc.identifier.issn2464–4625(CD/DVD)
dc.identifier.urihttp://hdl.handle.net/11025/45004
dc.format10 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencycs
dc.rights© Václav Skala - UNION Agencycs
dc.subjectrekonstrukce obrazucs
dc.subjectartefakty JPEGcs
dc.subjectstochastické diferenciální rovnicecs
dc.subjectnelokální prostředkycs
dc.titleReduction of JPEG Artifacts using BSDEsen
dc.typeconferenceObjecten
dc.typekonferenční příspěvekcs
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedIn this paper we propose a novel approach for reduction of JPEG artifacts using advanced techniques of stochasticcalculus. In order to solve this problem we use backward stochastic differential equations (in short BSDEs) andthe non local means method. In our algorithm we consider two processes. One of them has values in the imagedomain and determines pixels that will be involved in the reconstruction, the second one has values in the imagecodomain and gives weight to values of pixels. To calculate the weights, we use the idea of the patches similarityused in the non local means. Our experiments show that the new approach gives very good results and comparesfavourably with other methods.en
dc.subject.translatedimage reconstructionen
dc.subject.translatedJPEG artifactsen
dc.subject.translatedstochastic differential equationsen
dc.subject.translatednon local meansen
dc.identifier.doihttps://doi.org/10.24132/CSRN.2021.3101.1
dc.type.statusPeer-revieweden
Vyskytuje se v kolekcích:WSCG 2021: Full Papers Proceedings

Soubory připojené k záznamu:
Soubor Popis VelikostFormát 
H43.pdfPlný text3,36 MBAdobe PDFZobrazit/otevřít


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/45004

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.