ML Anthology

Laplacian Meshes for Monocular 3D Shape Recovery

Jonas Östlund, Aydin Varol, Dat Tien Ngo, Pascal Fua
ECCV 2012 pp. 412-425
doi:10.1007/978-3-642-33712-3_30 /eccv/2012/ostlund2012eccv-laplacian/

Abstract

We show that by extending the Laplacian formalism, which was first introduced in the Graphics community to regularize 3D meshes, we can turn the monocular 3D shape reconstruction of a deformable surface given correspondences with a reference image into a well-posed problem. Furthermore, this does not require any training data and eliminates the need to pre-align the reference shape with the one to be reconstructed, as was done in earlier methods.

PDF ECCV Semantic Scholar

Cite

Text

Östlund et al. "Laplacian Meshes for Monocular 3D Shape Recovery." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33712-3_30

Markdown

[Östlund et al. "Laplacian Meshes for Monocular 3D Shape Recovery." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/ostlund2012eccv-laplacian/) doi:10.1007/978-3-642-33712-3_30

BibTeX

@inproceedings{ostlund2012eccv-laplacian,
  title     = {{Laplacian Meshes for Monocular 3D Shape Recovery}},
  author    = {Östlund, Jonas and Varol, Aydin and Ngo, Dat Tien and Fua, Pascal},
  booktitle = {European Conference on Computer Vision},
  year      = {2012},
  pages     = {412-425},
  doi       = {10.1007/978-3-642-33712-3_30},
  url       = {https://mlanthology.org/eccv/2012/ostlund2012eccv-laplacian/}
}