SHREC 2020 Track: Extended Monocular Image Based 3D Model Retrieval

dc.contributor.authorLi, Wenhuien_US
dc.contributor.authorSong, Danen_US
dc.contributor.authorLiu, Ananen_US
dc.contributor.authorNie, Weizhien_US
dc.contributor.authorZhang, Tingen_US
dc.contributor.authorZhao, Xiaoqianen_US
dc.contributor.authorMa, Mingshengen_US
dc.contributor.authorLi, Yuqianen_US
dc.contributor.authorZhou, Heyuen_US
dc.contributor.authorZhang, Beibeien_US
dc.contributor.authorLe, Shengjieen_US
dc.contributor.authorWang, Dandanen_US
dc.contributor.authorRen, Tongweien_US
dc.contributor.authorWu, Gangshanen_US
dc.contributor.authorVu-Le, The-Anhen_US
dc.contributor.authorHoang, Xuan-Nhaten_US
dc.contributor.authorNguyen, E-Roen_US
dc.contributor.authorNguyen-Ho, Thang-Longen_US
dc.contributor.authorNguyen, Hai-Dangen_US
dc.contributor.authorDo, Trong-Leen_US
dc.contributor.authorTran, Minh-Trieten_US
dc.contributor.editorSchreck, Tobias and Theoharis, Theoharis and Pratikakis, Ioannis and Spagnuolo, Michela and Veltkamp, Remco C.en_US
dc.date.accessioned2020-09-03T09:50:27Z
dc.date.available2020-09-03T09:50:27Z
dc.date.issued2020
dc.description.abstractMonocular image based 3D object retrieval has attracted more and more attentions in the field of 3D object retrieval. However, the research of 3D object retrieval based on 2D image is still challenging, mainly because of the gap between data from different modalities. To further support this research, we extend the previous track SHREC19'MI3DOR to organize this track, and we construct the expanded monocular image based 3D object retrieval benchmark. Compared with SHREC19'MI3DOR, this benchmark adds 19 categories for both 2D images and 3D models to the original 21 categories, taking into account the lack of categories for practical applications. Two groups participated, proposed three kinds of supervised methods and submitted 20 runs in total, and 7 commonly-used criteria are used to evaluate the retrieval performance. The results show that supervised methods still achieve satisfying retrieval results (Best NN is 96.7% for 40 categories), which are comparable to the results of SHREC19'MI3DOR. In the future, unsupervised methods are encouraged to discover in monocular image based 3D model retrieval.en_US
dc.description.sectionheadersSHREC Short Papers
dc.description.seriesinformationEurographics Workshop on 3D Object Retrieval
dc.identifier.doi10.2312/3dor.20201163
dc.identifier.isbn978-3-03868-126-7
dc.identifier.issn1997-0471
dc.identifier.pages37-44
dc.identifier.urihttps://doi.org/10.2312/3dor.20201163
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/3dor20201163
dc.publisherThe Eurographics Associationen_US
dc.subjectH.3.3 [Computer Graphics]
dc.subjectInformation Systems
dc.subjectInformation Search and Retrieval
dc.titleSHREC 2020 Track: Extended Monocular Image Based 3D Model Retrievalen_US
Files