ML Anthology

Capturing 3D Stretchable Surfaces from Single Images in Closed Form

Francesc Moreno-Noguer, Mathieu Salzmann, Vincent Lepetit, Pascal Fua
CVPR 2009 pp. 1842-1849
doi:10.1109/CVPR.2009.5206758 /cvpr/2009/morenonoguer2009cvpr-capturing/

Abstract

We present a closed-form solution to the problem of re- covering the 3D shape of a non-rigid potentially stretchable surface from 3D-to-2D correspondences. In other words, we can reconstruct a surface from a single image without a priori knowledge of its deformations in that image. State-of-the-art solutions to non-rigid 3D shape recovery rely on the fact that distances between neighboring surface points must be preserved and are therefore limited to in- elastic surfaces. Here, we show that replacing the inextensibility constraints by shading ones removes this limitation while still allowing 3D reconstruction in closed-form. We demonstrate our method and compare it to an earlier one using both synthetic and real data.

PDF CVPR Semantic Scholar

Cite

Text

Moreno-Noguer et al. "Capturing 3D Stretchable Surfaces from Single Images in Closed Form." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009. doi:10.1109/CVPR.2009.5206758

Markdown

[Moreno-Noguer et al. "Capturing 3D Stretchable Surfaces from Single Images in Closed Form." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009.](https://mlanthology.org/cvpr/2009/morenonoguer2009cvpr-capturing/) doi:10.1109/CVPR.2009.5206758

BibTeX

@inproceedings{morenonoguer2009cvpr-capturing,
  title     = {{Capturing 3D Stretchable Surfaces from Single Images in Closed Form}},
  author    = {Moreno-Noguer, Francesc and Salzmann, Mathieu and Lepetit, Vincent and Fua, Pascal},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2009},
  pages     = {1842-1849},
  doi       = {10.1109/CVPR.2009.5206758},
  url       = {https://mlanthology.org/cvpr/2009/morenonoguer2009cvpr-capturing/}
}