Large Scale Comprehensive 3D Shape Retrieval
Large Scale Comprehensive 3D Shape Retrieval
复制标题
DOI：
10.2312/3dor.20141059
复制
发表时间：
2014-04
期刊：
影响因子：
--
通讯作者：
Bo Li;Yijuan Lu;C. Li;A. Godil;Tobias Schreck;Masaki Aono;Qiang Chen;N. K. Chowdhury;Bin Fang;T. Furuya;H. Johan;Ryuichi Kosaka;Hitoshi Koyanagi;Ryutarou Ohbuchi;A. Tatsuma
中科院分区：
文献类型：
--
作者：
Bo Li;Yijuan Lu;C. Li;A. Godil;Tobias Schreck;Masaki Aono;Qiang Chen;N. K. Chowdhury;Bin Fang;T. Furuya;H. Johan;Ryuichi Kosaka;Hitoshi Koyanagi;Ryutarou Ohbuchi;A. Tatsuma
该跟踪的目标是评估3D形状检索方法在大规模销售的综合3D形状数据库上的性能，该数据库包含不同类型的模型，例如通用模型、铰接模型、CAD模型和建筑模型。该轨迹基于新的全面3D形状基准，该基准包含8,987个三角形网格，分为171个类别。该基准被汇编为现有基准的超集，并对检索方法提出了新的挑战，因为它包括通用模型以及特定领域的模型类型。在这条赛道上，5个小组提交了14个跑动，并使用7个常用的性能指标评估了它们的检索准确性。
The objective of this track is to evaluate the performance of 3D shape retrieval approaches on a large-sale comprehensive 3D shape database that contains different types of models, such as generic, articulated, CAD and architecture models. The track is based on a new comprehensive 3D shape benchmark, which contains 8,987 triangle meshes that are classified into 171 categories. The benchmark was compiled as a superset of existing benchmarks and presents a new challenge to retrieval methods as it comprises generic models as well as domain-specific model types. In this track, 14 runs have been submitted by 5 groups and their retrieval accuracies were evaluated using 7 commonly used performance metrics.