Lightweight single image dehazing utilizing relative depth information

Show simple item record
dc.contributor.authorFrasiolas, Panagiotis
dc.contributor.authorReppas, Asterios
dc.contributor.authorKonstantoudakis, Konstantinos
dc.contributor.authorZarpalos, Dimitrios
dc.contributor.editorSkala, Václav
dc.date.accessioned2024-07-31T18:52:02Z
dc.date.available2024-07-31T18:52:02Z
dc.date.issued2024
dc.description.abstract-translatedConsidering the need for lightweight and fast implementations, this paper presents an architecture based on a Mo bileVit encoder for efficiency and speed, introducing a fully convolutional lightweight decoder with skip connec tions for feature extraction. The main purpose of this network is to address the problem of single image dehazing. Recognizing the critical role of depth information in assisting the above task, the merging of these two tasks into a single network was performed in a supervised manner. Taking into account that there is a shortage of datasets that provide both dehazing and relative depth estimation ground truths, Depth Anything was utilized to extract the relative depth values of the images, which is the SOTA network in this tasken
dc.description.sponsorshipThis research has been supported by the European Commission funded program RESCUER, under H2020 Grant Agreement 101021836.en
dc.format10 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationWSCG 2024: full papers proceedings: 32. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 349-358.en
dc.identifier.doihttps://doi.org/10.24132/CSRN.3401.38
dc.identifier.issn2464–4625 (online)
dc.identifier.issn2464–4617 (print)
dc.identifier.urihttp://hdl.handle.net/11025/57409
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencyen
dc.rights© Václav Skala - UNION Agencyen
dc.rights.accessopenAccessen
dc.subjectlehká váhacs
dc.subjecttransformátory viděnícs
dc.subjectrelativní hloubkacs
dc.subjectdehazovánícs
dc.subject.translatedlightweighten
dc.subject.translatedvision transformersen
dc.subject.translatedrelative depthen
dc.subject.translateddehazingen
dc.titleLightweight single image dehazing utilizing relative depth informationen
dc.typekonferenční příspěvekcs
dc.typeconferenceObjecten
dc.type.statusPeer revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
D31-2024.pdf
Size:
7.99 MB
Format:
Adobe Portable Document Format
Description:
Plný text
Download
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:
Download

Collections

WSCG 2024: Full Papers Proceedings