Learning local shape descriptors for computing non-rigid dense correspondence

被引:0
|
作者
Jianwei Guo [1 ]
Hanyu Wang [2 ]
Zhanglin Cheng [3 ]
Xiaopeng Zhang [1 ]
Dong-Ming Yan [1 ]
机构
[1] National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
[2] University of Maryland-College Park
[3] Shenzhen Visu CA Key Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
基金
中国国家自然科学基金; 国家重点研发计划; 北京市自然科学基金;
关键词
local feature descriptor; triplet CNN; dense correspondence; geometry image; non-rigid shape;
D O I
暂无
中图分类号
TP391.41 []; TP18 [人工智能理论];
学科分类号
080203 ; 081104 ; 0812 ; 0835 ; 1405 ;
摘要
A discriminative local shape descriptor plays an important role in various applications. In this paper, we present a novel deep learning framework that derives discriminative local descriptors for deformable 3D shapes. We use local "geometry images" to encode the multi-scale local features of a point, via an intrinsic parameterization method based on geodesic polar coordinates. This new parameterization provides robust geometry images even for badly-shaped triangular meshes. Then a triplet network with shared architecture and parameters is used to perform deep metric learning;its aim is to distinguish between similar and dissimilar pairs of points. Additionally, a newly designed triplet loss function is minimized for improved, accurate training of the triplet network. To solve the dense correspondence problem, an efficient sampling approach is utilized to achieve a good compromise between training performance and descriptor quality. During testing,given a geometry image of a point of interest, our network outputs a discriminative local descriptor for it.Extensive testing of non-rigid dense shape matching on a variety of benchmarks demonstrates the superiority of the proposed descriptors over the state-of-the-art alternatives.
引用
收藏
页码:95 / 112
页数:18
相关论文
共 50 条
  • [41] Non-rigid 3D shapes retrieval using a hybrid algorithm based on local descriptors
    Keshavarzi, Vahid
    Hajati, Farshid
    2017 10TH IRANIAN CONFERENCE ON MACHINE VISION AND IMAGE PROCESSING (MVIP), 2017, : 128 - 133
  • [42] A Robust Local Spectral Descriptor for Matching Non-Rigid Shapes with Incompatible Shape Structures
    Wang, Yiqun
    Guo, Jianwei
    Yan, Dong-Ming
    Wang, Kai
    Zhang, Xiaopeng
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 6224 - 6233
  • [43] LRA: Local Rigid Averaging of Stretchable Non-rigid Shapes
    Raviv, Dan
    Bayro-Corrochano, Eduardo
    Raskar, Ramesh
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2017, 124 (02) : 132 - 144
  • [44] LRA: Local Rigid Averaging of Stretchable Non-rigid Shapes
    Dan Raviv
    Eduardo Bayro-Corrochano
    Ramesh Raskar
    International Journal of Computer Vision, 2017, 124 : 132 - 144
  • [45] 3-D Shape Matching and Non-Rigid Correspondence for Hippocampi Based on Markov Random Fields
    Xiao, Pengdong
    Barnes, Nick
    Caetano, Tiberio
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (03) : 1271 - 1281
  • [46] Product Manifold Filter: Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Space
    Vestner, Matthias
    Litman, Roee
    Rodola, Emanuele
    Bronstein, Alex
    Cremers, Daniel
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 6681 - 6690
  • [47] A probabilistic model for object recognition, segmentation, and non-rigid correspondence
    Simon, Ian
    Seitz, Steven M.
    2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8, 2007, : 346 - +
  • [48] Global correspondence optimization for non-rigid registration of depth scans
    Li, Hao
    Sumner, Robert W.
    Pauly, Mark
    COMPUTER GRAPHICS FORUM, 2008, 27 (05) : 1421 - 1430
  • [49] Some new results on non-rigid correspondence and classification of curves
    Zheng, XQ
    Chen, YM
    Groisser, D
    Wilson, D
    ENERGY MINIMIZATION METHODS IN COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 2005, 3757 : 473 - 489
  • [50] On Two Methods for Computing the Non-Rigid Group of Molecules
    Iranmanesh, Ali
    Ashrafi, Ali Reza
    IRANIAN JOURNAL OF MATHEMATICAL SCIENCES AND INFORMATICS, 2008, 3 (02): : 21 - 28