Li, WenhuiSong, DanLiu, AnanNie, WeizhiZhang, TingZhao, XiaoqianMa, MingshengLi, YuqianZhou, HeyuZhang, BeibeiLe, ShengjieWang, DandanRen, TongweiWu, GangshanVu-Le, The-AnhHoang, Xuan-NhatNguyen, E-RoNguyen-Ho, Thang-LongNguyen, Hai-DangDo, Trong-LeTran, Minh-TrietSchreck, Tobias and Theoharis, Theoharis and Pratikakis, Ioannis and Spagnuolo, Michela and Veltkamp, Remco C.2020-09-032020-09-032020978-3-03868-126-71997-0471https://doi.org/10.2312/3dor.20201163https://diglib.eg.org:443/handle/10.2312/3dor20201163Monocular 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.H.3.3 [Computer Graphics]Information SystemsInformation Search and Retrieval10.2312/3dor.2020116337-44