DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Seong-heum | ko |
dc.contributor.author | Hwang, Youngbae | ko |
dc.contributor.author | Kweon, In So | ko |
dc.date.accessioned | 2020-05-12T07:20:05Z | - |
dc.date.available | 2020-05-12T07:20:05Z | - |
dc.date.created | 2020-05-11 | - |
dc.date.created | 2020-05-11 | - |
dc.date.issued | 2020-04 | - |
dc.identifier.citation | IMAGE AND VISION COMPUTING, v.96 | - |
dc.identifier.issn | 0262-8856 | - |
dc.identifier.uri | http://hdl.handle.net/10203/274168 | - |
dc.description.abstract | In this paper, we address a problem of correcting upright orientation of a reconstructed object to search. We first reconstruct an input object appearing in an image sequence, and generate a query shape using multi-view object co-segmentation. In the next phase, we utilize the Convolutional Neural Network (CNN) architecture to determine category-specific upright orientation of the queried shape for 3D model classification and retrieval. As a practical application of our system, a shape style and a pose from an inferred category and up-vector are obtained by comparing 3D shape similarity with candidate 3D models and aligning its projections with a set of 2D co-segmentation masks. We quantitatively and qualitatively evaluate the presented system with more than 720 upfront-aligned 3D models and five sets of multi-view image sequences. | - |
dc.language | English | - |
dc.publisher | ELSEVIER | - |
dc.title | Category-specific upright orientation estimation for 3D model classification and retrieval | - |
dc.type | Article | - |
dc.identifier.wosid | 000527905200003 | - |
dc.identifier.scopusid | 2-s2.0-85082863511 | - |
dc.type.rims | ART | - |
dc.citation.volume | 96 | - |
dc.citation.publicationname | IMAGE AND VISION COMPUTING | - |
dc.identifier.doi | 10.1016/j.imavis.2020.103900 | - |
dc.contributor.localauthor | Kweon, In So | - |
dc.contributor.nonIdAuthor | Kim, Seong-heum | - |
dc.contributor.nonIdAuthor | Hwang, Youngbae | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Model-based 3D reconstruction | - |
dc.subject.keywordAuthor | Multi-view object co-segmentation | - |
dc.subject.keywordAuthor | Convolutional neural networks | - |
dc.subject.keywordAuthor | Upright orientation estimation | - |
dc.subject.keywordAuthor | 3D model classification | - |
dc.subject.keywordAuthor | 3D model classification retrieval | - |
dc.subject.keywordPlus | NETWORKS | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.