Sökning: onr:"swepub:oai:lup.lub.lu.se:9852dc4e-c152-4a04-8ecd-dc8cf4b751f3" >
Semantic Room Wiref...
-
Gillsjö, DavidLund University,Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,LTH profilområde: AI och digitalisering,LTH profilområden,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH,LTH Profile Area: AI and Digitalization,LTH Profile areas,Faculty of Engineering, LTH
(författare)
Semantic Room Wireframe Detection from a Single View
- Artikel/kapitelEngelska2022
Förlag, utgivningsår, omfång ...
Nummerbeteckningar
-
LIBRIS-ID:oai:lup.lub.lu.se:9852dc4e-c152-4a04-8ecd-dc8cf4b751f3
-
https://lup.lub.lu.se/record/9852dc4e-c152-4a04-8ecd-dc8cf4b751f3URI
-
https://doi.org/10.1109/ICPR56361.2022.9956252DOI
Kompletterande språkuppgifter
-
Språk:engelska
-
Sammanfattning på:engelska
Ingår i deldatabas
Klassifikation
-
Ämneskategori:kon swepub-publicationtype
-
Ämneskategori:ref swepub-contenttype
Anmärkningar
-
Reconstruction of indoor surfaces with limited texture information or with repeated textures, a situation common in walls and ceilings, may be difficult with a monocular Structure from Motion system. We propose a Semantic Room Wireframe Detection task to predict a Semantic Wireframe from a single perspective image. Such predictions may be used with shape priors to estimate the Room Layout and aid reconstruction. To train and test the proposed algorithm we create a new set of annotations from the simulated Structured3D dataset. We show qualitatively that the SRW-Net handles complex room geometries better than previous Room Layout Estimation algorithms while quantitatively out-performing the baseline in non-semantic Wireframe Detection.
Ämnesord och genrebeteckningar
Biuppslag (personer, institutioner, konferenser, titlar ...)
-
Flood, GabrielleLund University,Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,LTH profilområde: AI och digitalisering,LTH profilområden,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH,LTH Profile Area: AI and Digitalization,LTH Profile areas,Faculty of Engineering, LTH(Swepub:lu)ga4756fl
(författare)
-
Åström, KalleLund University,Lunds universitet,Mathematical Imaging Group,Forskargrupper vid Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Stroke Imaging Research group,LTH profilområde: AI och digitalisering,LTH profilområden,LTH profilområde: Teknik för hälsa,Lund University Research Groups,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH,LTH Profile Area: AI and Digitalization,LTH Profile areas,Faculty of Engineering, LTH,LTH Profile Area: Engineering Health,Faculty of Engineering, LTH(Swepub:lu)math-kas
(författare)
-
Matematik LTHMatematikcentrum
(creator_code:org_t)
Sammanhörande titlar
-
Ingår i:26th International Conference on Pattern Recognition, 2022, s. 1886-189397816654906279781665490634
Internetlänk
Hitta via bibliotek
Till lärosätets databas