Bending invariant representations for surfaces

被引:0
|
作者
Elad, A [1 ]
Kimmel, R [1 ]
机构
[1] Technion Israel Inst Technol, Dept Comp Sci, IL-32000 Haifa, Israel
关键词
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
Isometric surfaces share the same geometric structure also known as the 'first fundamental form'. For example, all possible bending of a given surface, that include all length preserving deformations without. tearing or stretching the surface, are considered to be isometric. We present a method to construct a bending invariant canonical form for such surfaces. This invariant representation is an embedding of the intrinsic geodesic structure of the surface in a finite dimensional Euclidean space, in which geodesic distances are approximated by Euclidean ones. The canonical representation is constructed by first measuring the inter geodesic distances between points on the surfaces. Next, multi-dimensional scaling (MDS) techniques are applied to extract a finite dimensional flat space in which geodesic distances are represented as Euclidean ones. The geodesic distances are measured by the efficient fast marching on triangulated domains' numerical algorithm. Applying this transform to various objects with similar geodesic structures (similar first fundamental form) maps isometric objects into similar canonical forms. We show a simple surface classification method based on the bending invariant canonical form.
引用
收藏
页码:168 / 174
页数:7
相关论文
共 50 条
  • [31] Are face representations depth cue invariant?
    Dehmoobadsharifabadi, Armita
    Farivar, Reza
    JOURNAL OF VISION, 2016, 16 (08):
  • [32] On Learning Invariant Representations for Domain Adaptation
    Zhao, Han
    des Combes, Remi Tachet
    Zhang, Kun
    Gordon, Geoffrey J.
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
  • [33] INVARIANT ALGEBRAS AND COMPLETELY REDUCIBLE REPRESENTATIONS
    Kraft, H.
    Small, L. W.
    MATHEMATICAL RESEARCH LETTERS, 1994, 1 (03) : 297 - 307
  • [34] INTEGRAL-REPRESENTATIONS OF INVARIANT MEASURES
    MAITRA, A
    TRANSACTIONS OF THE AMERICAN MATHEMATICAL SOCIETY, 1977, 229 (MAY) : 209 - 225
  • [35] Invariant Representations through Adversarial Forgetting
    Jaiswal, Ayush
    Moyer, Daniel
    Ver Steeg, Greg
    AbdAlmageed, Wael
    Natarajan, Premkumar
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 4272 - 4279
  • [36] Invariant convex sets in polar representations
    Biliotti, Leonardo
    Ghigi, Alessandro
    Heinzner, Peter
    ISRAEL JOURNAL OF MATHEMATICS, 2016, 213 (01) : 423 - 441
  • [37] Expression-invariant representations of faces
    Bronstein, Alexander M.
    Bronstein, Michael M.
    Kimmel, Ron
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2007, 16 (01) : 188 - 197
  • [38] Invariant Representations Learning with Future Dynamics
    Hu, Wenning
    He, Ming
    Chen, Xirui
    Wang, Nianbin
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 128
  • [39] Copula Representations for Invariant Dependence Functions
    Pinto, Jayme
    Kolev, Nikolai
    INNOVATIONS IN QUANTITATIVE RISK MANAGEMENT, 2015, 99 : 411 - 421
  • [40] ON GROUP REPRESENTATIONS AND INVARIANT STOCHASTIC PROCESSES
    MCLAREN, AD
    PROCEEDINGS OF THE CAMBRIDGE PHILOSOPHICAL SOCIETY, 1963, 59 (02): : 431 - &