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
  • [21] Functional Maps and Its Application in Non-Rigid 3D Shape Correspondence
    Wang, Ning
    Zhang, Dan
    Xu, Chenhao
    Song, Meihua
    Zhang, Jianpeng
    Peng, Quanhong
    Computer Engineering and Applications, 2024, 60 (24) : 20 - 43
  • [22] Non-Rigid Shape From Water
    Kuo, Meng-Yu Jennifer
    Kawahara, Ryo
    Nobuhara, Shohei
    Nishino, Ko
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (07) : 2220 - 2232
  • [23] Dense Non-Rigid Structure From Motion
    Russell, Chris
    Fayad, Joao
    Agapito, Lourdes
    SECOND JOINT 3DIM/3DPVT CONFERENCE: 3D IMAGING, MODELING, PROCESSING, VISUALIZATION & TRANSMISSION (3DIMPVT 2012), 2012, : 509 - 516
  • [24] Bag of shape descriptor using unsupervised deep learning for non-rigid shape recognition
    Yang, Linjie
    Wang, Luping
    Su, Yijing
    Gao, Yin
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2021, 96
  • [25] Learning Spectral Descriptors for Deformable Shape Correspondence
    Litman, R.
    Bronstein, A. M.
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2014, 36 (01) : 171 - 180
  • [26] Unsupervised Learning of Dense Shape Correspondence
    Halimi, Oshri
    Litany, Or
    Rodola, Emanuele
    Bronstein, Alex
    Kimmel, Ron
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 4365 - 4374
  • [27] Fast Sinkhorn Filters: Using Matrix Scaling for Non-Rigid Shape Correspondence with Functional Maps
    Pai, Gautam
    Ren, Jing
    Melzi, Simone
    Wonka, Peter
    Ovsjanikov, Maks
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 384 - 393
  • [28] Correspondence Estimation from Non-Rigid Motion Information
    Wulff, Jonas
    Lotz, Thomas
    Stehle, Thomas
    Aach, Til
    Chase, J. Geoffrey
    MEDICAL IMAGING 2011: IMAGE PROCESSING, 2011, 7962
  • [29] Spherical matching for temporal correspondence of non-rigid surfaces
    Starck, J
    Hilton, A
    TENTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS 1 AND 2, PROCEEDINGS, 2005, : 1387 - 1394
  • [30] Enforcing a shape correspondence between two views of a 3D non-rigid object
    Dias, MB
    Buxton, BF
    PROGRESS IN PATTERN RECOGNITION, SPEECH AND IMAGE ANALYSIS, 2003, 2905 : 163 - 170