Show simple item record

dc.contributor.authorAhmad, Bilal
dc.contributor.authorFloor, Pål Anders
dc.contributor.authorFarup, Ivar
dc.contributor.authorKresović, Milan
dc.date.accessioned2023-02-28T07:17:15Z
dc.date.available2023-02-28T07:17:15Z
dc.date.created2022-11-28T15:26:13Z
dc.date.issued2022
dc.identifier.citationCEUR Workshop Proceedings. 2022, 3271 .en_US
dc.identifier.issn1613-0073
dc.identifier.urihttps://hdl.handle.net/11250/3054433
dc.description.abstract3D shape reconstruction from images is one of the problem under investigation in the field of computer vision. Shape-from-shading (SfS) is an important approach which requires the reflectance properties of surface and light source position to infer the 3D shape. SfS is usually tested in medical applications without the availability of the ground truth data which makes the conclusion dubious. In this article SfS is applied on synthetic gastrointestinal regions and precise comparison is done between recovered shape and ground truth data by measuring the depth error and correlation between them. Results shows that SfS can recover the shapes quite well if penalized correctly.en_US
dc.language.isoengen_US
dc.publisherCEUR Workshop Proceedingsen_US
dc.relation.urihttps://ceur-ws.org/Vol-3271/Paper3_CVCS2022.pdf
dc.rightsNavngivelse 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/deed.no*
dc.title3D Reconstruction of GI Regions from Single Imagesen_US
dc.title.alternative3D Reconstruction of GI Regions from Single Imagesen_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionpublishedVersionen_US
dc.source.pagenumber10en_US
dc.source.volume3271en_US
dc.source.journalCEUR Workshop Proceedingsen_US
dc.identifier.cristin2082971
dc.relation.projectNorges forskningsråd: 300031en_US
cristin.ispublishedtrue
cristin.qualitycode1


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Navngivelse 4.0 Internasjonal
Except where otherwise noted, this item's license is described as Navngivelse 4.0 Internasjonal