Boosting Image Super-Resolution Via Fusion of Complementary Information Captured by Multi-Modal Sensors

TL;DR

This paper introduces a multispectral fusion network that leverages complementary visible and depth information to enhance thermal image super-resolution, significantly improving accuracy and efficiency over existing methods.

Contribution

It presents a novel multispectral fusion residual network and a method for generating aligned multi-modal images for improved thermal super-resolution.

Findings

Outperforms state-of-the-art SR methods in accuracy.

Reduces parameters needed for high-quality SR.

Effectively utilizes low-cost spectral information.

Abstract

Image Super-Resolution (SR) provides a promising technique to enhance the image quality of low-resolution optical sensors, facilitating better-performing target detection and autonomous navigation in a wide range of robotics applications. It is noted that the state-of-the-art SR methods are typically trained and tested using single-channel inputs, neglecting the fact that the cost of capturing high-resolution images in different spectral domains varies significantly. In this paper, we attempt to leverage complementary information from a low-cost channel (visible/depth) to boost image quality of an expensive channel (thermal) using fewer parameters. To this end, we first present an effective method to virtually generate pixel-wise aligned visible and thermal images based on real-time 3D reconstruction of multi-modal data captured at various viewpoints. Then, we design a feature-level multispectral fusion residual network model to perform high-accuracy SR of thermal images by adaptively integrating co-occurrence features presented in multispectral images. Experimental results demonstrate that this new approach can effectively alleviate the ill-posed inverse problem of image SR by taking into account complementary information from an additional low-cost channel, significantly outperforming state-of-the-art SR approaches in terms of both accuracy and efficiency.