ML Anthology

Non-Linear Operators in Image Restoration

Pierre Kornprobst, Rachid Deriche, Gilles Aubert
CVPR 1997 pp. 325-330
doi:10.1109/CVPR.1997.609344 /cvpr/1997/kornprobst1997cvpr-non/

Abstract

We present a variational approach such that during image restoration, edges detected in the original image are being preserved. We compare the mathematical foundation of this method with respect to some of the well known methods recently proposed in the literature within the class of PDE based algorithms (anisotropic diffusion, mean curvature motion, min/max flow technique). The performance of our approach is carefully examined and compared to the classical methods. Experimental results on synthetic and real images illustrate the capabilities of all the studied approaches.

CVPR Semantic Scholar

Cite

Text

Kornprobst et al. "Non-Linear Operators in Image Restoration." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609344

Markdown

[Kornprobst et al. "Non-Linear Operators in Image Restoration." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/kornprobst1997cvpr-non/) doi:10.1109/CVPR.1997.609344

BibTeX

@inproceedings{kornprobst1997cvpr-non,
  title     = {{Non-Linear Operators in Image Restoration}},
  author    = {Kornprobst, Pierre and Deriche, Rachid and Aubert, Gilles},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {325-330},
  doi       = {10.1109/CVPR.1997.609344},
  url       = {https://mlanthology.org/cvpr/1997/kornprobst1997cvpr-non/}
}