Vis enkel innførsel

dc.contributor.authorSfikas, Konstantinos
dc.contributor.authorPratikakis, Ioannis
dc.contributor.authorTheoharis, Theoharis
dc.date.accessioned2019-04-25T12:17:06Z
dc.date.available2019-04-25T12:17:06Z
dc.date.created2018-09-28T16:05:39Z
dc.date.issued2018
dc.identifier.citationComputers & graphics. 2018, 71 208-218.nb_NO
dc.identifier.issn0097-8493
dc.identifier.urihttp://hdl.handle.net/11250/2595507
dc.description.abstractA novel method for the classification and retrieval of 3D models is proposed; it exploits the 2D panoramic view representation of 3D models as input to an ensemble of convolutional neural networks which automatically compute the features. The first step of the proposed pipeline, pose normalization is performed using the SYMPAN method, which is also computed on the panoramic view representation. In the training phase, three panoramic views corresponding to the major axes, are used for the training of an ensemble of convolutional neural networks. the panoramic views consist of 3-channel images, containing the Spatial Distribution Map, the Normals’ Deviation Map and the magnitude of the Normals’ Devation Map Gradient Image. The proposed method aims at capturing feature continuity of 3D models, while simultaneously minimizing data preprocessing via the construction of an augmented image representation. It is extensively tested in terms of classification and retrieval accuracy on two standard large scale datasets: ModelNet and ShapeNet.nb_NO
dc.language.isoengnb_NO
dc.publisherElseviernb_NO
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/deed.no*
dc.titleEnsemble of PANORAMA-based convolutional neural networks for 3D model classification and retrievalnb_NO
dc.typeJournal articlenb_NO
dc.typePeer reviewednb_NO
dc.description.versionacceptedVersionnb_NO
dc.source.pagenumber208-218nb_NO
dc.source.volume71nb_NO
dc.source.journalComputers & graphicsnb_NO
dc.identifier.doi10.1016/j.cag.2017.12.001
dc.identifier.cristin1615920
dc.description.localcode© 2018. This is the authors’ accepted and refereed manuscript to the article. Locked until 13.12.2019 due to copyright restrictions. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/nb_NO
cristin.unitcode194,63,10,0
cristin.unitnameInstitutt for datateknologi og informatikk
cristin.ispublishedtrue
cristin.fulltextpostprint
cristin.qualitycode2


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel

Attribution-NonCommercial-NoDerivatives 4.0 Internasjonal
Med mindre annet er angitt, så er denne innførselen lisensiert som Attribution-NonCommercial-NoDerivatives 4.0 Internasjonal