Single Frame Image super Resolution using Learned Directionlets

TL;DR

This paper introduces a novel super resolution method using directionally adaptive Directionlets, which effectively capture edge information and outperform standard techniques in visual quality and mean squared error, even with aliased images.

Contribution

It presents a new learning-based super resolution approach using Directionlets for better edge and directional feature capture, outperforming existing methods.

Findings

Outperforms cubic spline interpolation visually and in mse

Effective with aliased images

Captures directional features better

Abstract

In this paper, a new directionally adaptive, learning based, single image super resolution method using multiple direction wavelet transform, called Directionlets is presented. This method uses directionlets to effectively capture directional features and to extract edge information along different directions of a set of available high resolution images .This information is used as the training set for super resolving a low resolution input image and the Directionlet coefficients at finer scales of its high-resolution image are learned locally from this training set and the inverse Directionlet transform recovers the super-resolved high resolution image. The simulation results showed that the proposed approach outperforms standard interpolation techniques like Cubic spline interpolation as well as standard Wavelet-based learning, both visually and in terms of the mean squared error (mse) values. This method gives good result with aliased images also.