Unsupervised SIFT features-to-Image Translation using CycleGAN

dc.contributor.authorMackowiak, Sławomir
dc.contributor.authorBrudz, Patryk
dc.contributor.authorCiesielski, Mikołaj
dc.contributor.authorWawrzyniak, Maciej
dc.contributor.editorSkala, Václav
dc.date.accessioned2021-09-01T06:01:16Z
dc.date.available2021-09-01T06:01:16Z
dc.date.issued2021
dc.description.abstract-translatedThe generation of video content from a small set of data representing the features of objects has very promising application prospects. This is particularly important in the context of the work of the MPEG Video Coding for Machine group, where various efforts are being undertaken related to efficient image coding for machines and humans. The representation of feature points well understood by machines in a video form, which is easy to understand by humans, is an important current challenge. This paper presents results on the ability to generate images from a set of SIFT feature points without descriptors using the generative adversarial network CycleGAN. The impact of the SIFT keypoint representation method on the learning quality of the network is presented. The results and a subjective evaluation of the generated images are presented.en
dc.format10 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationWSCG 2021: full papers proceedings: 29. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 217-226.en
dc.identifier.doihttps://doi.org/10.24132/CSRN.2021.3101.24
dc.identifier.isbn978-80-86943-34-3
dc.identifier.issn2464-4617
dc.identifier.issn2464–4625(CD/DVD)
dc.identifier.urihttp://hdl.handle.net/11025/45027
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencycs
dc.rights© Václav Skala - UNION Agencycs
dc.rights.accessopenAccessen
dc.subjectSIFTcs
dc.subjectfunkcecs
dc.subjectklíčové bodycs
dc.subjectCycleGANcs
dc.subject.translatedSIFTen
dc.subject.translatedfeaturesen
dc.subject.translatedkeypointsen
dc.subject.translatedCycleGANen
dc.titleUnsupervised SIFT features-to-Image Translation using CycleGANen
dc.typeconferenceObjecten
dc.typekonferenční příspěvekcs
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
J05.pdf
Size:
1.5 MB
Format:
Adobe Portable Document Format
Description:
Plný text
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
OPEN License Selector