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
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
  • [21] 3D reconstruction using silhouettes from unordered viewpoints
    Liang, Chen
    Wong, Kwan-Yee K.
    IMAGE AND VISION COMPUTING, 2010, 28 (04) : 579 - 589
  • [22] Neural Contours: Learning to Draw Lines from 3D Shapes
    Liu, Difan
    Nabail, Mohamed
    Hertzmann, Aaron
    Kalogerakis, Evangelos
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 5427 - 5435
  • [23] Learning to Rank 3D Features
    Tuzel, Oncel
    Liu, Ming-Yu
    Taguchi, Yuichi
    Raghunathan, Arvind
    COMPUTER VISION - ECCV 2014, PT I, 2014, 8689 : 520 - 535
  • [24] ShapeCaptioner: Generative Caption Network for 3D Shapes by Learning a Mapping from Parts Detected in Multiple Views to Sentences
    Han, Zhizhong
    Chen, Chao
    Liu, Yu-Shen
    Zwicker, Matthias
    MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, : 1018 - 1027
  • [25] Unsupervised Learning of 3D Object Models from Partial Views
    Ruhnke, Michael
    Steder, Bastian
    Grisetti, Giorgio
    Burgard, Wolfram
    ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7, 2009, : 2173 - 2178
  • [26] Web-image driven best views of 3D shapes
    Liu, Hong
    Zhang, Lei
    Huang, Hua
    VISUAL COMPUTER, 2012, 28 (03): : 279 - 287
  • [27] Web-image driven best views of 3D shapes
    Hong Liu
    Lei Zhang
    Hua Huang
    The Visual Computer, 2012, 28 : 279 - 287
  • [28] Point rotation invariant features and attention fusion network for point cloud registration of 3D shapes
    Zeyang Liu
    Zhiguo Lu
    Yancong Shan
    Scientific Reports, 15 (1)
  • [29] A 3D Point Cloud Classification Method Based on Adaptive Graph Convolution and Global Attention
    Yue, Yaowei
    Li, Xiaonan
    Peng, Yun
    SENSORS, 2024, 24 (02)
  • [30] Continuous Geodesic Convolutions for Learning on 3D Shapes
    Yang, Zhangsihao
    Litany, Or
    Birdal, Tolga
    Sridhar, Srinath
    Guibas, Leonidas
    2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021), 2021, : 134 - 144