Joint Dictionary Learning for Example-based Image Super-resolution

TL;DR

This paper introduces a joint dictionary learning approach for example-based image super-resolution that leverages sparse representations to improve the quality of high-resolution image reconstruction.

Contribution

The paper presents a novel joint dictionary learning method that ensures consistent sparse representations between low- and high-resolution patches for enhanced super-resolution.

Findings

Outperforms state-of-the-art SR algorithms in simulations

Effective in reconstructing high-resolution images from low-resolution inputs

Ensures sparse representation consistency between LR and HR patches

Abstract

In this paper, we propose a new joint dictionary learning method for example-based image super-resolution (SR), using sparse representation. The low-resolution (LR) dictionary is trained from a set of LR sample image patches. Using the sparse representation coefficients of these LR patches over the LR dictionary, the high-resolution (HR) dictionary is trained by minimizing the reconstruction error of HR sample patches. The error criterion used here is the mean square error. In this way we guarantee that the HR patches have the same sparse representation over HR dictionary as the LR patches over the LR dictionary, and at the same time, these sparse representations can well reconstruct the HR patches. Simulation results show the effectiveness of our method compared to the state-of-art SR algorithms.