Template-based Monocular 3D Recovery of Elastic Shapes using Lagrangian Multipliers - Archive ouverte HAL Access content directly
Conference Papers Year :

Template-based Monocular 3D Recovery of Elastic Shapes using Lagrangian Multipliers

(1) , (1)
1

Abstract

We present in this paper an efficient template-based method for 3D recovery of elastic shapes from a fixed monocular camera. By exploiting the object's elasticity, in contrast to isometric methods that use inextensibility constraints , a large range of deformations can be handled. Our method is expressed as a saddle point problem using La-grangian multipliers resulting in a linear system which unifies both mechanical and optical constraints and integrates Dirichlet boundary conditions, whether they are fixed or free. We experimentally show that no prior knowledge on material properties is needed, which exhibit the generic usability of our method with elastic and inelastic objects with different kinds of materials. Comparisons with existing techniques are conducted on synthetic and real elastic objects with strains ranging from 25% to 130% resulting to low errors.
Fichier principal
Vignette du fichier
CVPR 2017 - Template-based Monocular 3D Recovery of Elastic Shapes using Lagrangian Multipliers.pdf (19.48 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01524609 , version 1 (18-05-2017)

Identifiers

  • HAL Id : hal-01524609 , version 1

Cite

Nazim Haouchine, Stéphane Cotin. Template-based Monocular 3D Recovery of Elastic Shapes using Lagrangian Multipliers. Computer Vision and Pattern Recognition (CVPR), Jul 2017, Honolulu, Hawai, United States. ⟨hal-01524609⟩
391 View
281 Download

Share

Gmail Facebook Twitter LinkedIn More