ML Anthology

Efficient Filter Flow for Space-Variant Multiframe Blind Deconvolution

Michael Hirsch, Suvrit Sra, Bernhard Schölkopf, Stefan Harmeling
CVPR 2010 pp. 607-614
doi:10.1109/CVPR.2010.5540158 /cvpr/2010/hirsch2010cvpr-efficient/

Abstract

Ultimately being motivated by facilitating space-variant blind deconvolution, we present a class of linear transformations, that are expressive enough for space-variant filters, but at the same time especially designed for efficient matrix-vector-multiplications. Successful results on astronomical imaging through atmospheric turbulences and on noisy magnetic resonance images of constantly moving objects demonstrate the practical significance of our approach.

PDF CVPR Semantic Scholar

Cite

Text

Hirsch et al. "Efficient Filter Flow for Space-Variant Multiframe Blind Deconvolution." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5540158

Markdown

[Hirsch et al. "Efficient Filter Flow for Space-Variant Multiframe Blind Deconvolution." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/hirsch2010cvpr-efficient/) doi:10.1109/CVPR.2010.5540158

BibTeX

@inproceedings{hirsch2010cvpr-efficient,
  title     = {{Efficient Filter Flow for Space-Variant Multiframe Blind Deconvolution}},
  author    = {Hirsch, Michael and Sra, Suvrit and Schölkopf, Bernhard and Harmeling, Stefan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2010},
  pages     = {607-614},
  doi       = {10.1109/CVPR.2010.5540158},
  url       = {https://mlanthology.org/cvpr/2010/hirsch2010cvpr-efficient/}
}