ML Anthology

3D Shape from Anisotropic Diffusion

Paolo Favaro, Stanley J. Osher, Stefano Soatto, Luminita A. Vese
CVPR 2003 pp. 179-186
doi:10.1109/CVPR.2003.1211352 /cvpr/2003/favaro2003cvpr-d/

Abstract

We cast the problem of inferring the 3D shape of a scene from a collection of defocused images in the framework of anisotropic diffusion. We propose an algorithm that can estimate the shape of a scene by inferring the diffusion coefficient of a heat equation. The method is optimal, as we pose it as the minimization of a certain cost functional based on the input images, and fast. Furthermore, we also extend our algorithm to the case of multiple images, and derive a 3D scene segmentation algorithm that can work in the presence of pictorial camouflage.

CVPR Semantic Scholar

Cite

Text

Favaro et al. "3D Shape from Anisotropic Diffusion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211352

Markdown

[Favaro et al. "3D Shape from Anisotropic Diffusion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/favaro2003cvpr-d/) doi:10.1109/CVPR.2003.1211352

BibTeX

@inproceedings{favaro2003cvpr-d,
  title     = {{3D Shape from Anisotropic Diffusion}},
  author    = {Favaro, Paolo and Osher, Stanley J. and Soatto, Stefano and Vese, Luminita A.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {179-186},
  doi       = {10.1109/CVPR.2003.1211352},
  url       = {https://mlanthology.org/cvpr/2003/favaro2003cvpr-d/}
}