A Sampled Texture Prior for Image Super-Resolution
Abstract
Super-resolution aims to produce a high-resolution image from a set of one or more low-resolution images by recovering or inventing plausible high-frequency image content. Typical approaches try to reconstruct a high-resolution image using the sub-pixel displacements of several low- resolution images, usually regularized by a generic smoothness prior over the high-resolution image space. Other methods use training data to learn low-to-high-resolution matches, and have been highly successful even in the single-input-image case. Here we present a domain-specific im- age prior in the form of a p.d.f. based upon sampled images, and show that for certain types of super-resolution problems, this sample-based prior gives a significant improvement over other common multiple-image super-resolution techniques.
Cite
Text
Pickup et al. "A Sampled Texture Prior for Image Super-Resolution." Neural Information Processing Systems, 2003.Markdown
[Pickup et al. "A Sampled Texture Prior for Image Super-Resolution." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/pickup2003neurips-sampled/)BibTeX
@inproceedings{pickup2003neurips-sampled,
title = {{A Sampled Texture Prior for Image Super-Resolution}},
author = {Pickup, Lyndsey C. and Roberts, Stephen J. and Zisserman, Andrew},
booktitle = {Neural Information Processing Systems},
year = {2003},
pages = {1587-1594},
url = {https://mlanthology.org/neurips/2003/pickup2003neurips-sampled/}
}