当前位置: X-MOL 学术Comput. Graph. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
SHREC 2021: Retrieval of cultural heritage objects
Computers & Graphics ( IF 2.5 ) Pub Date : 2021-07-15 , DOI: 10.1016/j.cag.2021.07.010
Ivan Sipiran 1 , Patrick Lazo 2 , Cristian Lopez 3 , Milagritos Jimenez 4 , Nihar Bagewadi 5 , Benjamin Bustos 1 , Hieu Dao 6 , Shankar Gangisetty 5 , Martin Hanik 7 , Ngoc-Phuong Ho-Thi 6 , Mike Holenderski 8 , Dmitri Jarnikov 8, 9 , Arniel Labrada 1 , Stefan Lengauer 10 , Roxane Licandro 11, 12 , Dinh-Huan Nguyen 6 , Thang-Long Nguyen-Ho 6 , Luis A. Perez Rey 8, 9 , Bang-Dang Pham 6 , Minh-Khoi Pham 6
Affiliation  

This paper presents the methods and results of the SHREC’21 track on a dataset of cultural heritage (CH) objects. We present a dataset of 938 scanned models that have varied geometry and artistic styles. For the competition, we propose two challenges: the retrieval-by-shape challenge and the retrieval-by-culture challenge. The former aims at evaluating the ability of retrieval methods to discriminate cultural heritage objects by overall shape. The latter focuses on assessing the effectiveness of retrieving objects from the same culture. Both challenges constitute a suitable scenario to evaluate modern shape retrieval methods in a CH domain. Ten groups participated in the challenges: thirty runs were submitted for the retrieval-by-shape task, and twenty-six runs were submitted for the retrieval-by-culture task. The results show a predominance of learning methods on image-based multi-view representations to characterize 3D objects. Nevertheless, the problem presented in our challenges is far from being solved. We also identify the potential paths for further improvements and give insights into the future directions of research.



中文翻译:

SHREC 2021:文化遗产对象的检索

本文介绍了 SHREC'21 跟踪对文化遗产 (CH) 对象数据集的方法和结果。我们提供了一个包含 938 个扫描模型的数据集,这些模型具有不同的几何形状和艺术风格。对于比赛,我们提出了两个挑战:按形状检索挑战和按文化检索挑战。前者旨在评估检索方法通过整体形状区分文化遗产对象的能力。后者侧重于评估从同一文化中检索对象的有效性。这两个挑战构成了评估 CH 域中现代形状检索方法的合适场景。十个小组参加了挑战:为形状检索任务提交了 30 次运行,为按文化检索任务提交了 26 次运行。结果显示了基于图像的多视图表示的学习方法的优势,以表征 3D 对象。然而,我们挑战中提出的问题远未得到解决。我们还确定了进一步改进的潜在途径,并对未来的研究方向提供了见解。

更新日期:2021-08-03
down
wechat
bug