Learning Canonical View Representation for 3D Shape Recognition with Arbitrary Views

被引:10
作者
Wei, Xin [1 ]
Gong, Yifei [2 ]
Wang, Fudong [2 ]
Sun, Xing [2 ]
Sun, Jian [1 ]
机构
[1] Xi An Jiao Tong Univ, Xian, Peoples R China
[2] Tencent Youtu Lab, Shanghai, Peoples R China
来源
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) | 2021年
关键词
D O I
10.1109/ICCV48922.2021.00046
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we focus on recognizing 3D shapes from arbitrary views, i.e., arbitrary numbers and positions of viewpoints. It is a challenging and realistic setting for view-based 3D shape recognition. We propose a canonical view representation to tackle this challenge. We first transform the original features of arbitrary views to a fixed number of view features, dubbed canonical view representation, by aligning the arbitrary view features to a set of learnable reference view features using optimal transport. In this way, each 3D shape with arbitrary views is represented by a fixed number of canonical view features, which are further aggregated to generate a rich and robust 3D shape representation for shape recognition. We also propose a canonical view feature separation constraint to enforce that the view features in canonical view representation can be embedded into scattered points in a Euclidean space. Experiments on the ModelNet40, ScanObjectNN, and RGBD datasets show that our method achieves competitive results under the fixed viewpoint settings, and significantly outperforms the applicable methods under the arbitrary view setting.
引用
收藏
页码:397 / 406
页数:10
相关论文
共 44 条
[1]  
[Anonymous], 2006, Eurographics Symposium on Geometry Processing
[2]  
[Anonymous], 2016, J. Mach. Learn. Res.
[3]   A Multi-Modal, Discriminative and Spatially Invariant CNN for RGB-D Object Labeling [J].
Asif, Umar ;
Bennamoun, Mohammed ;
Sohel, Ferdous A. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (09) :2051-2065
[4]   ITERATIVE BREGMAN PROJECTIONS FOR REGULARIZED TRANSPORTATION PROBLEMS [J].
Benamou, Jean-David ;
Carlier, Guillaume ;
Cuturi, Marco ;
Nenna, Luca ;
Peyre, Gabriel .
SIAM JOURNAL ON SCIENTIFIC COMPUTING, 2015, 37 (02) :A1111-A1138
[5]  
Brown TB, 2020, ADV NEUR IN, V33
[6]   End-to-End Object Detection with Transformers [J].
Carion, Nicolas ;
Massa, Francisco ;
Synnaeve, Gabriel ;
Usunier, Nicolas ;
Kirillov, Alexander ;
Zagoruyko, Sergey .
COMPUTER VISION - ECCV 2020, PT I, 2020, 12346 :213-229
[7]  
Chen Huigang, 2020, CAUSALML PYTHON PACK
[8]  
Chen Jiaxin, 2020, ECCV
[9]   Convolutional Fisher Kernels for RGB-D Object Recognition [J].
Cheng, Yanhua ;
Cai, Rui ;
Zhao, Xin ;
Huang, Kaiqi .
2015 INTERNATIONAL CONFERENCE ON 3D VISION, 2015, :135-143
[10]  
ChuWang Marcello Pelillo, 2017, BMVC