Hyperspectral Image Super-Resolution in Arbitrary Input-Output Band Settings

TL;DR

This paper introduces a meta-learning-based model for hyperspectral image super-resolution that can adapt to arbitrary input and output band settings, overcoming limitations of existing methods tied to specific camera configurations.

Contribution

A novel single MLSR model capable of handling diverse input-output band settings for hyperspectral images, unlike prior models limited to fixed configurations.

Findings

Successfully super-resolves HSIs at arbitrary band settings

Performs better or comparably to models trained on specific settings

Validated on NTIRE2020 and ICVL datasets

Abstract

Hyperspectral image (HSI) with narrow spectral bands can capture rich spectral information, but it sacrifices its spatial resolution in the process. Many machine-learning-based HSI super-resolution (SR) algorithms have been proposed recently. However, one of the fundamental limitations of these approaches is that they are highly dependent on image and camera settings and can only learn to map an input HSI with one specific setting to an output HSI with another. However, different cameras capture images with different spectral response functions and bands numbers due to the diversity of HSI cameras. Consequently, the existing machine-learning-based approaches fail to learn to super-resolve HSIs for a wide variety of input-output band settings. We propose a single Meta-Learning-Based Super-Resolution (MLSR) model, which can take in HSI images at an arbitrary number of input bands' peak wavelengths and generate SR HSIs with an arbitrary number of output bands' peak wavelengths. We leverage NTIRE2020 and ICVL datasets to train and validate the performance of the MLSR model. The results show that the single proposed model can successfully generate super-resolved HSI bands at arbitrary input-output band settings. The results are better or at least comparable to baselines that are separately trained on a specific input-output band setting.