Multimodal Image Super-resolution via Deep Unfolding with Side Information

TL;DR

This paper introduces a deep unfolding approach for multimodal image super-resolution that leverages side information and sparse priors, outperforming existing methods in reconstructing high-resolution images from low-resolution inputs.

Contribution

It presents a novel deep learning architecture based on iterative algorithm unfolding, effectively integrating side information and sparse priors for multimodal super-resolution.

Findings

Proposed models outperform state-of-the-art methods in super-resolving near-infrared images.

Deep unfolding architecture effectively incorporates domain knowledge into neural networks.

Experimental results show significant improvements over unimodal and multimodal baselines.

Abstract

Deep learning methods have been successfully applied to various computer vision tasks. However, existing neural network architectures do not per se incorporate domain knowledge about the addressed problem, thus, understanding what the model has learned is an open research topic. In this paper, we rely on the unfolding of an iterative algorithm for sparse approximation with side information, and design a deep learning architecture for multimodal image super-resolution that incorporates sparse priors and effectively utilizes information from another image modality. We develop two deep models performing reconstruction of a high-resolution image of a target image modality from its low-resolution variant with the aid of a high-resolution image from a second modality. We apply the proposed models to super-resolve near-infrared images using as side information high-resolution RGB\ images. Experimental results demonstrate the superior performance of the proposed models against state-of-the-art methods including unimodal and multimodal approaches.