ML Anthology

Image Super-Resolution Using Gradient Profile Prior

Jian Sun, Zongben Xu, Heung-Yeung Shum
CVPR 2008
doi:10.1109/CVPR.2008.4587659 /cvpr/2008/sun2008cvpr-image/

Abstract

In this paper, we propose an image super-resolution approach using a novel generic image prior - gradient profile prior, which is a parametric prior describing the shape and the sharpness of the image gradients. Using the gradient profile prior learned from a large number of natural images, we can provide a constraint on image gradients when we estimate a hi-resolution image from a low-resolution image. With this simple but very effective prior, we are able to produce state-of-the-art results. The reconstructed hi-resolution image is sharp while has rare ringing or jaggy artifacts.

CVPR Semantic Scholar

Cite

Text

Sun et al. "Image Super-Resolution Using Gradient Profile Prior." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587659

Markdown

[Sun et al. "Image Super-Resolution Using Gradient Profile Prior." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/sun2008cvpr-image/) doi:10.1109/CVPR.2008.4587659

BibTeX

@inproceedings{sun2008cvpr-image,
  title     = {{Image Super-Resolution Using Gradient Profile Prior}},
  author    = {Sun, Jian and Xu, Zongben and Shum, Heung-Yeung},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2008},
  doi       = {10.1109/CVPR.2008.4587659},
  url       = {https://mlanthology.org/cvpr/2008/sun2008cvpr-image/}
}