Sparsity-based Color Image Super Resolution via Exploiting Cross Channel Constraints

TL;DR

This paper introduces a sparsity-based super-resolution method that incorporates cross-channel constraints and edge similarities among RGB channels, improving color image super-resolution by exploiting inter-channel correlations.

Contribution

It extends sparse super-resolution to color images by modeling cross-channel interactions and proposes a new dictionary learning approach for better color representation.

Findings

Outperforms state-of-the-art methods visually and quantitatively.

Effectively captures inter-channel correlations through edge similarity constraints.

Provides an efficient solution to a complex optimization problem.

Abstract

Sparsity constrained single image super-resolution (SR) has been of much recent interest. A typical approach involves sparsely representing patches in a low-resolution (LR) input image via a dictionary of example LR patches, and then using the coefficients of this representation to generate the high-resolution (HR) output via an analogous HR dictionary. However, most existing sparse representation methods for super resolution focus on the luminance channel information and do not capture interactions between color channels. In this work, we extend sparsity based super-resolution to multiple color channels by taking color information into account. Edge similarities amongst RGB color bands are exploited as cross channel correlation constraints. These additional constraints lead to a new optimization problem which is not easily solvable; however, a tractable solution is proposed to solve it efficiently. Moreover, to fully exploit the complementary information among color channels, a dictionary learning method is also proposed specifically to learn color dictionaries that encourage edge similarities. Merits of the proposed method over state of the art are demonstrated both visually and quantitatively using image quality metrics.