ML Anthology

On Reconstruction of Non-Rigid Shapes with Intrinsic Regularization

Yohai S. Devir, Guy Rosman, Alexander M. Bronstein, Michael M. Bronstein, Ron Kimmel
ICCVW 2009 pp. 272-279
doi:10.1109/ICCVW.2009.5457688 /iccvw/2009/devir2009iccvw-reconstruction/

Abstract

Shape-from-X is a generic type of inverse problems in computer vision, in which a shape is reconstructed from some measurements. A specially challenging setting of this problem is the case in which the reconstructed shapes are non-rigid. In this paper, we propose a framework for intrinsic regularization of such problems. The assumption is that we have the geometric structure of a shape which is intrinsically (up to bending) similar to the one we would like to reconstruct. For that goal, we formulate a variation with respect to vertex coordinates of a triangulated mesh approximating the continuous shape. The numerical core of the proposed method is based on differentiating the fast marching update step for geodesic distance computation.

ICCVW Semantic Scholar

Cite

Text

Devir et al. "On Reconstruction of Non-Rigid Shapes with Intrinsic Regularization." IEEE/CVF International Conference on Computer Vision Workshops, 2009. doi:10.1109/ICCVW.2009.5457688

Markdown

[Devir et al. "On Reconstruction of Non-Rigid Shapes with Intrinsic Regularization." IEEE/CVF International Conference on Computer Vision Workshops, 2009.](https://mlanthology.org/iccvw/2009/devir2009iccvw-reconstruction/) doi:10.1109/ICCVW.2009.5457688

BibTeX

@inproceedings{devir2009iccvw-reconstruction,
  title     = {{On Reconstruction of Non-Rigid Shapes with Intrinsic Regularization}},
  author    = {Devir, Yohai S. and Rosman, Guy and Bronstein, Alexander M. and Bronstein, Michael M. and Kimmel, Ron},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2009},
  pages     = {272-279},
  doi       = {10.1109/ICCVW.2009.5457688},
  url       = {https://mlanthology.org/iccvw/2009/devir2009iccvw-reconstruction/}
}