Interpretable Deep Multimodal Image Super-Resolution

TL;DR

This paper introduces an interpretable deep multimodal image super-resolution model that effectively fuses information from different modalities using coupled sparse priors, leading to superior reconstruction performance.

Contribution

It presents a novel network design inspired by coupled convolutional sparse coding, integrating domain knowledge for improved multimodal super-resolution.

Findings

Outperforms state-of-the-art methods in near-infrared super-resolution

Incorporates domain knowledge through coupled sparse priors

Provides an interpretable deep network architecture

Abstract

Multimodal image super-resolution (SR) is the reconstruction of a high resolution image given a low-resolution observation with the aid of another image modality. While existing deep multimodal models do not incorporate domain knowledge about image SR, we present a multimodal deep network design that integrates coupled sparse priors and allows the effective fusion of information from another modality into the reconstruction process. Our method is inspired by a novel iterative algorithm for coupled convolutional sparse coding, resulting in an interpretable network by design. We apply our model to the super-resolution of near-infrared image guided by RGB images. Experimental results show that our model outperforms state-of-the-art methods.