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
  • [41] Sparse approximation of 3D shapes via spectral graph wavelets
    Zhong, Ming
    Qin, Hong
    VISUAL COMPUTER, 2014, 30 (6-8): : 751 - 761
  • [42] Sparse approximation of 3D shapes via spectral graph wavelets
    Ming Zhong
    Hong Qin
    The Visual Computer, 2014, 30 : 751 - 761
  • [43] Learning Line Features in 3D Geometry
    Sunkel, M.
    Jansen, S.
    Wand, M.
    Eisemann, E.
    Seidel, H. -P.
    COMPUTER GRAPHICS FORUM, 2011, 30 (02) : 267 - 276
  • [44] Learning to Predict 3D Surfaces of Sculptures from Single and Multiple Views
    Olivia Wiles
    Andrew Zisserman
    International Journal of Computer Vision, 2019, 127 : 1780 - 1800
  • [45] Learning Barycentric Representations of 3D Shapes for Sketch-based 3D Shape Retrieval
    Xie, Jin
    Dai, Guoxian
    Zhu, Fan
    Fang, Yi
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 3615 - 3623
  • [46] Learning to Predict 3D Surfaces of Sculptures from Single and Multiple Views
    Wiles, Olivia
    Zisserman, Andrew
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2019, 127 (11-12) : 1780 - 1800
  • [47] Discuss 3D cognitive graph and meaningful learning
    Hong, CF
    Chen, YM
    Liu, YC
    Wu, TH
    ADVANCED RESEARCH IN COMPUTERS AND COMMUNICATIONS IN EDUCATION, VOL 1: NEW HUMAN ABILITIES FOR THE NETWORKED SOCIETY, 1999, 55 : 240 - 243
  • [48] Subequivariant Graph Reinforcement Learning in 3D Environments
    Chen, Runfa
    Han, Jiaqi
    Sun, Fuchun
    Huang, Wenbing
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 202, 2023, 202
  • [49] Automatic extraction of facial features from frontal and profile views and their 3D computations
    Ansari, AN
    Abdel-Mottaleb, M
    PROCEEDINGS OF THE SIXTH IASTED INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING, 2004, : 128 - 133
  • [50] DiscoNet: Shapes Learning on Disconnected Manifolds for 3D Editing
    Mehr, Eloi
    Jourdan, Ariane
    Thome, Nicolas
    Cord, Matthieu
    Guitteny, Vincent
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 3473 - 3482