Author(s): Shwetambari Shinde | Meeta Dewangan
Journal: International Journal of Computer Science and Engineering Survey
ISSN 0976-3252
Volume: 3;
Issue: 2;
Start page: 47;
Date: 2012;
VIEW PDF
DOWNLOAD PDF 
Original page
Keywords: Classicalmultiimage | Example-based | low resolution | patch redundancy | Super-resolution.
ABSTRACT
Methods for super-resolution can be broadly classified into two families of methods: (i) The classicalmulti-image super-resolution (combining images obtained at subpixel misalignments), and (ii) ExampleBased 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 sub pixel 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.
Journal: International Journal of Computer Science and Engineering Survey
ISSN 0976-3252
Volume: 3;
Issue: 2;
Start page: 47;
Date: 2012;
VIEW PDF
DOWNLOAD PDF Original pageKeywords: Classicalmultiimage | Example-based | low resolution | patch redundancy | Super-resolution.
ABSTRACT
Methods for super-resolution can be broadly classified into two families of methods: (i) The classicalmulti-image super-resolution (combining images obtained at subpixel misalignments), and (ii) ExampleBased 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 sub pixel 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.
