A polygon-based interpolation operator for super-resolution imaging
Computer Vision and Pattern Recognition
2012-10-17 v2
Abstract
We outline the super-resolution reconstruction problem posed as a maximization of probability. We then introduce an interpolation method based on polygonal pixel overlap, express it as a linear operator, and use it to improve reconstruction. Polygon interpolation outperforms the simpler bilinear interpolation operator and, unlike Gaussian modeling of pixels, requires no parameter estimation. A free software implementation that reproduces the results shown is provided.
Keywords
Cite
@article{arxiv.1210.3404,
title = {A polygon-based interpolation operator for super-resolution imaging},
author = {Stéfan J. van der Walt and B. M. Herbst},
journal= {arXiv preprint arXiv:1210.3404},
year = {2012}
}
Comments
10 pages; update typo in abstract