Super-resolution from a single image (ac.il)

This post has been automatically generated. I use this blog to collect links that I have bookmarked. All activity is automated.

Super Resolution From a Single Image

Daniel Glasner, Shai Bagon, Michal Irani

This webpage presents the paper “Super-Resolution form a Single Image” (ICCV 2009).
Paper [PDF] [bibtex]

Abstract

Methods for super-resolution (SR) can be broadly classified into two families of methods: (i) The classical multi-image super-resolution (combining images obtained at subpixel misalignments), and (ii) Example-Based super-resolution (learning correspondence between low and high resolution image patches from a database). In this paper we propose a unified framework for combining these two families of methods. We further show how this combined approach can be applied to obtain super resolution from as little as a single image (with no database or prior examples). Our approach is based on the observation that patches in a natural image tend to redundantly recur many times inside the image, both within the same scale, as well as across different scales. Recurrence of patches within the same image scale (at subpixel misalignments) gives rise to the classical super-resolution, whereas recurrence of patches across different scales of the same image gives rise to example-based super-resolution. Our approach attempts to recover at each pixel its best possible resolution increase based on its patch redundancy within and across scales.

To switch between images please use the colored buttons on the right.
Please note that the magnified images are initialized to Nearest-neighbor interpolation.
In order to see our SR results you must click the blue button.
To see magnification using bi-cubic interpolation, please click the orange button.

We compare our super-resolution (SR) method to results from the example based methods of [Freeman et al.] and [Kim et al.], as well as to the method of [Fattal]. Note that our results are comparable, even though we do not use any external database of low-res/high-res pairs of patches [Freeman et al., Kim et al.], nor a parametric learned edge model [Fattal]. The images we compare on and the results of the other methods [Freeman et al., Kim et al., Fattal] were taken from their papers.

[Freeman et all.]W. T. Freeman, T. R. Jones, and E. C. Pasztor. Example-based super-resolution. IEEE Computer Graphics and Applications, 22(2):56-65, 2002.
[Kim et al.]K. I. Kim and Y. Kwon. Example-based learning for single-image super-resolution and JPEG artifact removal. Technical Report 173, 08 2008.
[Fattal]R. Fattal. Image upsampling via imposed edge statistics. ACM Trans. Graphics (Proc. SIGGRAPH 2007), 26(3):95-102, 2007.