SHREC'22 track: Open-Set 3D Object Retrieval

作     者：Feng, Yifan Gao, Yue Zhao, Xibin Guo, Yandong Bagewadi, Nihar Bui, Nhat-Tan Dao, Hieu Gangisetty, Shankar Guan, Ripeng Han, Xie Hua, Cong Hunakunti, Chidambar Jiang, Yu Jiao, Shichao Ke, Yuqi Kuang, Liqun Liu, Anan Nguyen, Dinh-Huan Nguyen, Hai-Dang Nie, Weizhi Pham, Bang-Dang Raikar, Karthik Tang, Qingmei Tran, Minh-Triet Wan, Jialong Yan, Chenggang You, Haoxuan Zhu, Difei 

作者机构：Tsinghua Univ Sch Software Beijing Peoples R China Tsinghua Univ BNRist THUIBCS KLISSBLBCI Beijing Peoples R China OPPO Res Inst Beijing Peoples R China Univ Sci Ho Chi Minh City Vietnam John Neumann Inst Ho Chi Minh City Vietnam Vietnam Natl Univ Ho Chi Minh City Vietnam KLE Technol Univ Hubballi India North Univ China Sch Data Sci & Technol Taiyuan Peoples R China Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China Zhejiang Univ Sch Management Hangzhou Zhejiang Peoples R China Shandong Univ Sch Mech Elect Informat Engn Jinan Peoples R China Jilin Univ Coll Comp Sci & Technol Changchun Peoples R China Columbia Univ New York NY 10025 USA 

出 版 物：《COMPUTERS & GRAPHICS-UK》 (计算机与图形学)

年 卷 期：2022年第107卷

页      面：231-240页

核心收录：

学科分类：08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Funds of China [62088102, 62021002, 61671267] National Key R&D Program of China [2018YFB1703404] Beijing Natural Science Foundation 

主　　题：SHREC?22 3D Object Retrieval Open-Set Multi-Modal 

摘      要：This paper reports the results of the SHREC 22 track: Open-Set 3D Object Retrieval, the goal of which is to evaluate the performance of different retrieval algorithms under the Open-Set setting and modality-missing setting, respectively. Since objects from unseen categories are very common in real-world applications, we design the open-set 3D object retrieval to expand the application of traditional 3D object retrieval. In this track, we generate open-set 3D object retrieval datasets OS-MN40 and OS-MN40-Miss based on the ModelNet40 dataset, which are collected for the open-set setting and both open-set setting and modality-missing setting, respectively. Both the two datasets include the training set (2822 objects from 8 categories) and the retrieval set (960 query objects and 8527 target objects from the other 32 categories). The categories of retrieval (query/target) sets are not seen in the training set. For each object in the OS-MN40, four types of modalities, including mesh, point cloud, multi-view, and voxel, are provided. Each object in the OS-MN40-Miss is represented with incomplete modality information, which is collected to simulate the retrieval task in the real world. This track attracted eight participants from four countries and 191 runs of all submissions. The evaluation results show a promising scenario about open-set retrieval on 3D objects with multi -modal and multi-resolution representation and reveal interesting insights in dealing with retrieving 3D objects in unknown-category objects.(c) 2022 Elsevier Ltd. All rights reserved.