Gradient-based adaptive interpolation in super-resolution image restoration

TL;DR

This paper introduces a super-resolution technique that uses gradient-based adaptive interpolation to enhance image quality, especially edges, and employs Wiener filtering for deblurring, demonstrating robustness and low computational cost.

Contribution

It proposes a novel gradient-aware interpolation method for super-resolution that improves image quality and robustness over existing techniques.

Findings

Significant improvement in subjective and objective image quality.

Enhanced edge preservation in super-resolved images.

Robustness to registration errors and low computational complexity.

Abstract

This paper presents a super-resolution method based on gradient-based adaptive interpolation. In this method, in addition to considering the distance between the interpolated pixel and the neighboring valid pixel, the interpolation coefficients take the local gradient of the original image into account. The smaller the local gradient of a pixel is, the more influence it should have on the interpolated pixel. And the interpolated high resolution image is finally deblurred by the application of wiener filter. Experimental results show that our proposed method not only substantially improves the subjective and objective quality of restored images, especially enhances edges, but also is robust to the registration error and has low computational complexity.