Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/90067
Full metadata record
DC FieldValueLanguage
dc.contributor.authorZhang, Xingzien_US
dc.contributor.authorLippoldt, Franziskaen_US
dc.contributor.authorChen, Kanen_US
dc.contributor.authorJohan, Henryen_US
dc.contributor.authorErdt, Mariusen_US
dc.date.accessioned2019-09-03T01:25:22Zen
dc.date.accessioned2019-12-06T17:39:56Z-
dc.date.available2019-09-03T01:25:22Zen
dc.date.available2019-12-06T17:39:56Z-
dc.date.issued2019-
dc.identifier.citationZhang, X., Lippoldt, F., Chen, K., Johan, H., & Erdt, M. (2019). A data-driven approach for adding facade details to textured LoD2 CityGML models. GRAPP 2019 : 14th International Conference on Computer Graphics Theory and Applications. doi:10.5220/0007507802940301en_US
dc.identifier.urihttps://hdl.handle.net/10356/90067-
dc.description.abstractLoD3 CityGML models (with facade elements, e.g., windows and doors) have many applications, however, they are not easy to acquire, while LoD2 models (only roofs and walls) are currently largely available. In this paper, we propose to generate LoD3 models by adding facade details to textured LoD2 models using a data-driven approach. The existing reconstruction-based methods usually require high costs to obtain plausible LoD3 models. Instead, our proposed data-driven method is based on automatically detecting the facade elements from the texture images and interactively selecting matched models from a 3D facade element model database, then deforming and stitching them with the input LoD2 model to generate a LoD3 model. In this manner, our method is free from reconstruction errors, such as non-symmetrical artifacts and noise, and it is practically useful for its simplicity and effectiveness.en_US
dc.format.extent8 p.en
dc.language.isoenen_US
dc.rights© 2019 SCITEPRESS. All rights reserved. This paper was published in GRAPP 2019 : 14th International Conference on Computer Graphics Theory and Applications and is made available with permission of SCITEPRESS.en_US
dc.subjectData-drivenen_US
dc.subjectFacade Details Additionen_US
dc.subjectEngineering::Computer science and engineeringen_US
dc.titleA data-driven approach for adding facade details to textured LoD2 CityGML modelsen_US
dc.typeConference Paperen
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.contributor.conferenceGRAPP 2019 : 14th International Conference on Computer Graphics Theory and Applicationsen_US
dc.contributor.researchCentre for Advanced Media Technologyen_US
dc.identifier.doi10.5220/0007507802940301-
dc.description.versionPublished versionen_US
dc.description.acknowledgementThis research is supported by the National Research Foundation, Prime Ministers Office, Singapore under the Virtual Singapore Programme. Berlin’s CityGML model source can be downloaded from the following link: https://www.businesslocationcenter. de/en/downloadportal.en_US
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:Fraunhofer Singapore Conference Papers
Files in This Item:
File Description SizeFormat 
Example.pdf13.33 MBAdobe PDFThumbnail
View/Open

SCOPUSTM   
Citations

2
checked on Jul 24, 2020

Page view(s)

170
checked on Oct 25, 2020

Download(s)

54
checked on Oct 25, 2020

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.