Equiareal Shape-from-Template

被引:5
|
作者
Casillas-Perez, David [1 ]
Pizarro, Daniel [1 ,2 ]
Fuentes-Jimenez, David [1 ]
Mazo, Manuel [1 ]
Bartoli, Adrien [2 ]
机构
[1] Univ Alcala, GEINTRA, Alcala De Henares, Spain
[2] Univ Auvergne, CNRS, ISIT, Clermont Ferrand, France
关键词
Shape; Deformable models; Deformable reconstruction; Image reconstruction; Equiareal deformations; Three-dimensional displays; Measurement; PDE; Cameras; Manifolds; Partial Differential Equations; Shape recognition; Equiareal surfaces; Monge's theory; First-order methods; RECONSTRUCTION; MOTION; SURFACES;
D O I
10.1007/s10851-018-0862-5
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper studies the 3D reconstruction of a deformable surface from a single image and a reference surface, known as the template. This problem is known as Shape-from-Template and has been recently shown to be well-posed for isometric deformations, for which the surface bends without altering geodesics. This paper studies the case of equiareal deformations. They are elastic deformations where the local area is preserved and thus include isometry as a special case. Elastic deformations have been studied before in Shape-from-Template, yet no theoretical results were given on the existence or uniqueness of solutions. The equiareal model is much more widely applicable than isometry. This paper brings Monge's theory, widely used for studying the solutions of nonlinear first-order PDEs, to the field of 3D reconstruction. It uses this theory to establish a theoretical framework for equiareal Shape-from-Template and answers the important question of whether it is possible to reconstruct a surface exactly with a much weaker prior than isometry. We prove that equiareal Shape-from-Template has a maximum of two local solutions sufficiently near an initial curve that lies on the surface. In addition, we propose an analytical reconstruction algorithm that can recover the multiple solutions. Our algorithm uses standard numerical tools for ODEs. We use the perspective camera model and give reconstruction results with both synthetic and real examples.
引用
收藏
页码:607 / 626
页数:20
相关论文
共 50 条
  • [1] Equiareal Shape-from-Template
    David Casillas-Perez
    Daniel Pizarro
    David Fuentes-Jimenez
    Manuel Mazo
    Adrien Bartoli
    Journal of Mathematical Imaging and Vision, 2019, 61 : 607 - 626
  • [2] Shape-from-Template
    Bartoli, Adrien
    Gerard, Yan
    Chadebecq, Francois
    Collins, Toby
    Pizarro, Daniel
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2015, 37 (10) : 2099 - 2118
  • [3] Shape-From-Template with Curves
    Gallardo, Mathias
    Pizarro, Daniel
    Collins, Toby
    Bartoli, Adrien
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2020, 128 (01) : 121 - 165
  • [4] Shape-from-Template in Flatland
    Gallardo, Mathias
    Pizarro, Daniel
    Bartoli, Adrien
    Collins, Toby
    2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2015, : 2847 - 2854
  • [5] Shape-From-Template with Curves
    Mathias Gallardo
    Daniel Pizarro
    Toby Collins
    Adrien Bartoli
    International Journal of Computer Vision, 2020, 128 : 121 - 165
  • [6] Realtime Shape-from-Template: System and Applications
    Collins, Toby
    Bartoli, Adrien
    2015 IEEE INTERNATIONAL SYMPOSIUM ON MIXED AND AUGMENTED REALITY, 2015, : 116 - 119
  • [7] Weakly-Supervised Deep Shape-From-Template
    Luengo-Sanchez, Sara
    Fuentes-Jimenez, David
    Losada-Gutierrez, Cristina
    Pizarro, Daniel
    Bartoli, Adrien
    IEEE ACCESS, 2025, 13 : 22868 - 22892
  • [8] Texture-Generic Deep Shape-From-Template
    Fuentes-Jimenez, David
    Pizarro, Daniel
    Casillas-Perez, David
    Collins, Toby
    Bartoli, Adrien
    IEEE ACCESS, 2021, 9 : 75211 - 75230
  • [9] A Perspective on Non-Isometric Shape-from-Template
    Bartoli, Adrien
    Ozgur, Erol
    ADJUNCT PROCEEDINGS OF THE 2016 IEEE INTERNATIONAL SYMPOSIUM ON MIXED AND AUGMENTED REALITY (ISMAR-ADJUNCT), 2016, : 5 - 10
  • [10] As-Rigid-As-Possible Volumetric Shape-from-Template
    Parashar, Shaifali
    Pizarro, Daniel
    Bartoli, Adrien
    Collins, Toby
    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 891 - 899