3DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention

被引:0
|
作者
Han, Zhizhong [1 ,3 ]
Wang, Xiyang [1 ,2 ]
Chi-Man Vong [4 ]
Liu, Yu-Shen [1 ,2 ]
Zwicker, Matthias [3 ]
Chen, C. L. Philip [5 ]
机构
[1] Tsinghua Univ, Sch Software, Beijing, Peoples R China
[2] Beijing Natl Res Ctr Informat Sci & Technol BNRis, Beijing, Peoples R China
[3] Univ Maryland, Dept Comp Sci, College Pk, MD 20742 USA
[4] Univ Macau, Dept Comp & Informat Sci, Macau, Peoples R China
[5] Univ Macau, Fac Sci & Technol, Macau, Peoples R China
来源
PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE | 2019年
基金
国家重点研发计划;
关键词
NETWORK;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Learning global features by aggregating information over multiple views has been shown to be effective for 3D shape analysis. For view aggregation in deep learning models, pooling has been applied extensively. However, pooling leads to a loss of the content within views, and the spatial relationship among views, which limits the discriminability of learned features. We propose 3DViewGraph to resolve this issue, which learns 3D global features by more effectively aggregating unordered views with attention. Specifically, unordered views taken around a shape are regarded as view nodes on a view graph. 3DViewGraph first learns a novel latent semantic mapping to project low-level view features into meaningful latent semantic embeddings in a lower dimensional space, which is spanned by latent semantic patterns. Then, the content and spatial information of each pair of view nodes are encoded by a novel spatial pattern correlation, where the correlation is computed among latent semantic patterns. Finally, all spatial pattern correlations are integrated with attention weights learned by a novel attention mechanism. This further increases the discriminability of learned features by highlighting the unordered view nodes with distinctive characteristics and depressing the ones with appearance ambiguity. We show that 3DViewGraph outperforms state-of-the-art methods under three large-scale benchmarks.
引用
收藏
页码:758 / 765
页数:8
相关论文
共 50 条
  • [31] EdgeNet: Deep metric learning for 3D shapes
    Chen, Mingjia
    Zou, Qianfang
    Wang, Changbo
    Liu, Ligang
    COMPUTER AIDED GEOMETRIC DESIGN, 2019, 72 : 19 - 33
  • [32] Global Localization by Soft Object Recognition from 3D Partial Views
    Ribeiro, Fernando
    Brandao, Susana
    Costeira, Joao P.
    Veloso, Manuela
    2015 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2015, : 3709 - 3714
  • [33] A Method of 3D Reconstruction from Multiple Views Based on Graph Theoretic Segmentation
    Li, Yi
    Hong, Hanyu
    Zhang, Xiuhua
    Bai, Haoyu
    MIPPR 2013: PATTERN RECOGNITION AND COMPUTER VISION, 2013, 8919
  • [34] Interactive 3D Architectural Modeling from Unordered Photo Collections
    Sinha, Sudipta N.
    Steedly, Drew
    Szeliski, Richard
    Agrawala, Maneesh
    Pollefeys, Marc
    ACM TRANSACTIONS ON GRAPHICS, 2008, 27 (05):
  • [35] Learning Representative Features by Deep Attention Network for 3D Point Cloud Registration
    Xia, Xiaokai
    Fan, Zhiqiang
    Xiao, Gang
    Chen, Fangyue
    Liu, Yu
    Hu, Yiheng
    SENSORS, 2023, 23 (08)
  • [36] 3D Object Detection Method Combining on Graph Sampling and Graph Attention
    Li, Wenju
    Chu, Wanghui
    Cui, Liu
    Su, Pan
    Zhang, Gan
    Computer Engineering and Applications, 2023, 59 (09) : 237 - 244
  • [37] Global-to-Local Generative Model for 3D Shapes
    Wang, Hao
    Schor, Nadav
    Hu, Ruizhen
    Huang, Haibin
    Cohen-Or, Daniel
    Huang, Hui
    ACM TRANSACTIONS ON GRAPHICS, 2018, 37 (06):
  • [38] Global-to-Local Generative Model for 3D Shapes
    Wang, Hao
    Schor, Nadav
    Hu, Ruizhen
    Huang, Haibin
    Cohen-Or, Daniel
    Huang, Hui
    SIGGRAPH ASIA'18: SIGGRAPH ASIA 2018 TECHNICAL PAPERS, 2018,
  • [39] Local and global properties in 3D braided structural shapes
    Wang, ASD
    Kumar, A
    PROCEEDINGS OF THE EIGHTH JAPAN-U.S. CONFERENCE ON COMPOSITE MATERIALS, 1999, : 157 - 166
  • [40] PointGAT: Graph attention networks for 3D object detection
    Zhou H.
    Wang W.
    Liu G.
    Zhou Q.
    Intelligent and Converged Networks, 2022, 3 (02): : 204 - 216