ML Anthology

Vector-Valued Image Regularization with PDE's : A Common Framework for Different Applications

David Tschumperlé, Rachid Deriche
CVPR 2003 pp. 651-656
doi:10.1109/CVPR.2003.1211415 /cvpr/2003/tschumperle2003cvpr-vector/

Abstract

We address the problem of vector-valued image regularization with variational methods and PDEs. From the study of existing formalisms, we propose a unifying framework based on a very local interpretation of the regularization processes. The resulting equations are then specialized into new regularization PDEs and corresponding numerical schemes that respect the local geometry of vector-valued images. They are finally applied on a wide variety of image processing problems, including color image restoration, in-painting, magnification and flow visualization.

PDF CVPR Semantic Scholar

Cite

Text

Tschumperlé and Deriche. "Vector-Valued Image Regularization with PDE's : A Common Framework for Different Applications." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211415

Markdown

[Tschumperlé and Deriche. "Vector-Valued Image Regularization with PDE's : A Common Framework for Different Applications." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/tschumperle2003cvpr-vector/) doi:10.1109/CVPR.2003.1211415

BibTeX

@inproceedings{tschumperle2003cvpr-vector,
  title     = {{Vector-Valued Image Regularization with PDE's : A Common Framework for Different Applications}},
  author    = {Tschumperlé, David and Deriche, Rachid},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {651-656},
  doi       = {10.1109/CVPR.2003.1211415},
  url       = {https://mlanthology.org/cvpr/2003/tschumperle2003cvpr-vector/}
}