ML Anthology

On the Fundamental Limits of Reconstruction-Based Super-Resolution Algorithms

Zhouchen Lin, Heung-Yeung Shum
CVPR 2001 pp. I:1171-1176
doi:10.1109/CVPR.2001.990663 /cvpr/2001/lin2001cvpr-fundamental/

Abstract

Super-resolution is a technique that produces higher resolution images from low resolution images (LRIs). In practice, people have found that the improvement in resolution is limited. The aim of this paper is to address the problem "do fundamental limits exist for super-resolution?". Specifically this paper provides explicit limits for a major class of super-resolution algorithms, called the reconstruction-based algorithms, under both real and synthetic conditions. Our analysis is based on perturbation theory of linear systems. We also show that a sufficient number of LRIs can be determined to reach the limit. Both real and synthetic experiments are carried out to verify our analysis.

CVPR Semantic Scholar

Cite

Text

Lin and Shum. "On the Fundamental Limits of Reconstruction-Based Super-Resolution Algorithms." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.990663

Markdown

[Lin and Shum. "On the Fundamental Limits of Reconstruction-Based Super-Resolution Algorithms." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/lin2001cvpr-fundamental/) doi:10.1109/CVPR.2001.990663

BibTeX

@inproceedings{lin2001cvpr-fundamental,
  title     = {{On the Fundamental Limits of Reconstruction-Based Super-Resolution Algorithms}},
  author    = {Lin, Zhouchen and Shum, Heung-Yeung},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {I:1171-1176},
  doi       = {10.1109/CVPR.2001.990663},
  url       = {https://mlanthology.org/cvpr/2001/lin2001cvpr-fundamental/}
}