Superresolution of Noisy Remotely Sensed Images Through Directional Representations

TL;DR

This paper introduces a superresolution algorithm for noisy remote sensing images using shearlet transforms, which effectively captures directional features and improves image quality compared to existing methods.

Contribution

It presents a novel superresolution method combining shearlet transforms with sparse mixing estimators, specifically tailored for remotely sensed data.

Findings

Competitive PSNR and SSIM performance

Effective directional feature extraction

Outperforms wavelet-based superresolution methods

Abstract

We develop an algorithm for single-image superresolution of remotely sensed data, based on the discrete shearlet transform. The shearlet transform extracts directional features of signals, and is known to provide near-optimally sparse representations for a broad class of images. This often leads to superior performance in edge detection and image representation when compared to isotropic frames. We justify the use of shearlets mathematically, before presenting a denoising single-image superresolution algorithm that combines the shearlet transform with sparse mixing estimators (SME). Our algorithm is compared with a variety of single-image superresolution methods, including wavelet SME superresolution. Our numerical results demonstrate competitive performance in terms of PSNR and SSIM.