摘要
近年来,细粒度三维模型分类在计算机图形学和计算机视觉领域受到越来越多的关注。如何有效检索细粒度类级三维模型引起了学者的关注。构建了一个基于草图的细粒度类级三维模型检索数据集,并命名为FGCL-SBSR,以支持草图到元类别下特定子类三维模型的检索。该数据集中三维模型取自FG3D数据集,而草图则是通过招募志愿者绘制的方式完成收集。在草图收集完成后,对其进行了筛选,并据此对数据集进行了合理的划分。具体来说,FGCL-SBSR中Airplane子数据集包含12个类,其中三维模型1388个,草图1286张;Chair子数据集包含25个类,其中三维模型2321个,草图2102张。该数据集在子类别上建立了草图与三维模型之间的对应关系,并且保持了草图的抽象性、稀疏性、多样性和代表性。最后,通过不同训练集训练模型以及不同方法在该数据集中的实验结果证明了该数据集可以很好地适用于基于草图的细粒度类级三维模型检索任务,充分体现了其必要性、一致性和有效性。
Recently,fine-grained 3D shape classification has received growing attention in the community of computer graphics and computer vision.The paper constructs a sketch-based fine-grained class-level 3D shape retrieval dataset,named FGCL-SBSR,to support the use of sketches to retrieve 3D shapes of specific subclasses under a metaclass.The 3D shapes in this dataset are sourced from the FG3D dataset,while the sketches are collected through recruiting volunteers to draw them.After the sketches are collected,they are filtered and the dataset is accordingly divided rationally.Specifically,the Airplane sub-dataset in FGCL-SBSR contains 12 classes,including 13883D shapes and 1286 sketches,and the Chair sub-dataset contains 25 classes,including 23213D shapes and 2102 sketches.The dataset establishes a correspondence between sketches and 3D shapes in terms of subcategories and maintains the abstraction,sparseness,diversity and repre-sentativeness of the sketches.Finally,the experimental results of training models with different training sets and different methods on this paper’s dataset prove that this paper’s dataset can be well suited for the task of sketch-based fine-grained class-level 3D shape retrieval,fully demonstrating its necessity,consistency and effectiveness.
作者
郑虎
白静
晏浩
苏雅雯
ZHENG Hu;BAI Jing;YAN Hao;SU Yawen(School of Computer Science and Engineering,North Minzu University,Yinchuan 750021,China;The Key Laboratory of Images&Graphics Intelligent Processing of State Ethnic Affairs Commission,North Minzu University,Yinchuan 750021,China)
出处
《计算机工程与应用》
北大核心
2025年第19期226-236,共11页
Computer Engineering and Applications
基金
国家自然科学基金(62162001)
宁夏自然科学基金(2022AAC02041)
宁夏优秀人才支持计划。
