SpectraLift: Physics-Guided Spectral-Inversion Network for Self-Supervised Hyperspectral Image Super-Resolution

TL;DR

SpectraLift is a self-supervised spectral-inversion network that fuses low-resolution hyperspectral images with high-resolution multispectral images using only spectral response functions, achieving superior super-resolution results.

Contribution

It introduces a novel self-supervised framework that does not require PSF calibration or ground truth high-resolution hyperspectral images for fusion.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Converges in minutes and is agnostic to spatial blur and resolution.

Uses only spectral response functions for training.

Abstract

High-spatial-resolution hyperspectral images (HSI) are essential for applications such as remote sensing and medical imaging, yet HSI sensors inherently trade spatial detail for spectral richness. Fusing high-spatial-resolution multispectral images (HR-MSI) with low-spatial-resolution hyperspectral images (LR-HSI) is a promising route to recover fine spatial structures without sacrificing spectral fidelity. Most state-of-the-art methods for HSI-MSI fusion demand point spread function (PSF) calibration or ground truth high resolution HSI (HR-HSI), both of which are impractical to obtain in real world settings. We present SpectraLift, a fully self-supervised framework that fuses LR-HSI and HR-MSI inputs using only the MSI's Spectral Response Function (SRF). SpectraLift trains a lightweight per-pixel multi-layer perceptron (MLP) network using ($i$)~a synthetic low-spatial-resolution multispectral image (LR-MSI) obtained by applying the SRF to the LR-HSI as input, ($ii$)~the LR-HSI as the output, and ($iii$)~an $\ell_1$ spectral reconstruction loss between the estimated and true LR-HSI as the optimization objective. At inference, SpectraLift uses the trained network to map the HR-MSI pixel-wise into a HR-HSI estimate. SpectraLift converges in minutes, is agnostic to spatial blur and resolution, and outperforms state-of-the-art methods on PSNR, SAM, SSIM, and RMSE benchmarks.