欢迎访问《图学学报》 分享到：
图学学报

图学学报 ›› 2022, Vol. 43 ›› Issue (1): 36-43.DOI: 10.11996/JG.j.2095-302X.2022010036

• 图像处理与计算机视觉 • 上一篇    下一篇

基于自适应多类中心和半异构网络的 三维模型草图检索 

  

  1. 1. 北方民族大学计算机科学与工程学院，宁夏 银川 750021；  2. 国家民委图像图形智能处理实验室，宁夏 银川 750021
  • 出版日期:2022-02-28 发布日期:2022-02-16
  • 基金资助:
    国家自然科学基金项目(61762003，62162001)；中国科学院“西部之光”人才培养引进计划(JF2012c016-2)；宁夏优秀人才支持计划；北 方民族大学“计算机视觉和虚拟现实”创新团队

Adaptive multi-class centers and semi-heterogeneous network for sketch-based 3D model retrieval 

  1. 1. School of Computer Science and Engineering, North Minzu University, Yinchuan Ningxia 750021, China;  2. The Key Laboratory of Images & Graphics Intelligent Processing of State Ethnic Affairs Commission, Yinchuan Ningxia 750021, China
  • Online:2022-02-28 Published:2022-02-16
  • Supported by:
    National Natural Science Foundation of China (61762003, 62162001); The “Light of the West” Talent Training and Introduction Plan of Chinese Academy of Sciences (JF2012c016-2); Ningxia Excellent Talents Support Program; “Computer Vision and Virtual Reality” Innovation Team of North University for Nationalities 

PDF (PC)

153

摘要： 草图具有易于构建且不受语言、专业、年龄限制等优势，基于手绘草图的三维模型检索受到越 来越多的关注。然而在三维模型草图检索任务中，三维模型具有复杂性，草图具有类内多样性，同时三维模型 与草图之间又具有巨大的域间差异性，这些特点的相互作用严重影响检索的准确性。针对以上问题，提出了一 种基于自适应多类中心和半异构网络的三维模型草图检索方法。首先，通过异构网络分别提取草图和三维模型 的初始特征：设计了基于自适应多类中心的草图特征嵌入子网络以捕捉草图数据的类内多样性，采用了基于多 视图特征融合的三维模型特征嵌入子网络适应三维模型的复杂性。然后，以包含丰富语义信息的语义标签为指 引，构建同构网络实现草图-三维模型的跨域共享特征嵌入，缩小域间的差异性。在大型公开数据集 SHREC2013 和 SHREC2014 上的对比实验表明，该算法获得了和当前最好算法一致的检索性能。

关键词: 基于草图的检索, 三维模型检索, 自适应多类中心, 半异构, 语义嵌入

Abstract: Sketches are advantageous in being easy to construct and unrestricted by language, discipline, age, and so forth, and the 3D model retrieval based on hand-drawn sketches has attracted increasing attention. However, due to the complexity of 3D models, intra-class diversity of 2D sketches, and the inter-domain differences between 3D models and 2D sketches, the sketch-based 3D model retrieval remains highly challenging currently. To address these issues, we proposed a 3D model retrieval for sketch based on adaptive multi-class centers and semi-heterogeneous network. First, the initial features of the sketches and the 3D models were extracted separately through two heterogeneous networks: a sketch feature embedding sub-network based on adaptive multi-class centers was designed to capture the intra-class diversity of sketches, and a 3D model feature embedding sub-network based on multi-view feature fusion was adopted to adapt to the complexity of 3D models. Then, using the label vectors with rich semantic information as guides, a homogeneous network was designed to realize the cross-domain shared feature embedding of the sketches and 3D models, so as to reduce the inter-domain differences. Comparative experiments on the large public data sets SHREC2013 and SHREC2014 demonstrate that the proposed algorithm is on par with or better than the state-of-the-art methods. 

Key words: sketch-based retrieval, 3D model retrieval, adaptive multi-class center, semi-heterogeneous network, semantic embedding

中图分类号: