RGB-D Object-to-CAD Retrieval

dc.contributor.authorPham, Quang-Hieuen_US
dc.contributor.authorTran, Minh-Khoien_US
dc.contributor.authorLi, Wenhuien_US
dc.contributor.authorXiang, Shuen_US
dc.contributor.authorZhou, Heyuen_US
dc.contributor.authorNie, Weizhien_US
dc.contributor.authorLiu, Ananen_US
dc.contributor.authorSu, Yutingen_US
dc.contributor.authorTran, Minh-Trieten_US
dc.contributor.authorBui, Ngoc-Minhen_US
dc.contributor.authorDo, Trong-Leen_US
dc.contributor.authorNinh, Tu V.en_US
dc.contributor.authorLe, Tu-Khiemen_US
dc.contributor.authorDao, Anh-Vuen_US
dc.contributor.authorNguyen, Vinh-Tiepen_US
dc.contributor.authorDo, Minh N.en_US
dc.contributor.authorDuong, Anh-Ducen_US
dc.contributor.authorHua, Binh-Sonen_US
dc.contributor.authorYu, Lap-Faien_US
dc.contributor.authorNguyen, Duc Thanhen_US
dc.contributor.authorYeung, Sai-Kiten_US
dc.contributor.editorTelea, Alex and Theoharis, Theoharis and Veltkamp, Remcoen_US
dc.date.accessioned2018-04-14T18:28:40Z
dc.date.available2018-04-14T18:28:40Z
dc.date.issued2018
dc.description.abstractRecent advances in consumer-grade depth sensors have enable the collection of massive real-world 3D objects. Together with the rise of deep learning, it brings great potential for large-scale 3D object retrieval. In this challenge, we aim to study and evaluate the performance of 3D object retrieval algorithms with RGB-D data. To support the study, we expanded the previous ObjectNN dataset [HTT 17] to include RGB-D objects from both SceneNN [HPN 16] and ScanNet [DCS 17], with the CAD models from ShapeNetSem [CFG 15]. Evaluation results show that while the RGB-D to CAD retrieval problem is indeed challenging due to incomplete RGB-D reconstructions, it can be addressed to a certain extent using deep learning techniques trained on multi-view 2D images or 3D point clouds. The best method in this track has a 82% retrieval accuracy.en_US
dc.description.sectionheadersSHREC Tracks
dc.description.seriesinformationEurographics Workshop on 3D Object Retrieval
dc.identifier.doi10.2312/3dor.20181052
dc.identifier.isbn978-3-03868-053-6
dc.identifier.issn1997-0471
dc.identifier.pages45-52
dc.identifier.urihttps://doi.org/10.2312/3dor.20181052
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/3dor20181052
dc.publisherThe Eurographics Associationen_US
dc.titleRGB-D Object-to-CAD Retrievalen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
045-052.pdf
Size:
1.84 MB
Format:
Adobe Portable Document Format
Collections