ML Anthology

Limits on Super-Resolution and How to Break Them

Simon Baker, Takeo Kanade
CVPR 2000 pp. 2372-2379
doi:10.1109/CVPR.2000.854852 /cvpr/2000/baker2000cvpr-limits/

Abstract

We analyze the super-resolution reconstruction constraints. In particular we derive a sequence of results which all show that the constraints provide far less useful information as the magnification factor increases. It is well established that the use of a smoothness prior may help somewhat, however for large enough magnification factors any smoothness prior leads to overly smooth results. We therefore propose an algorithm that learns recognition-based priors for specific classes of scenes, the use of which gives far better super-resolution results for both faces and text.

PDF CVPR Semantic Scholar

Cite

Text

Baker and Kanade. "Limits on Super-Resolution and How to Break Them." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.854852

Markdown

[Baker and Kanade. "Limits on Super-Resolution and How to Break Them." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/baker2000cvpr-limits/) doi:10.1109/CVPR.2000.854852

BibTeX

@inproceedings{baker2000cvpr-limits,
  title     = {{Limits on Super-Resolution and How to Break Them}},
  author    = {Baker, Simon and Kanade, Takeo},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2000},
  pages     = {2372-2379},
  doi       = {10.1109/CVPR.2000.854852},
  url       = {https://mlanthology.org/cvpr/2000/baker2000cvpr-limits/}
}