Hyperspectral Image Fusion with Spectral-Band and Fusion-Scale Agnosticism

TL;DR

This paper introduces SSA, a universal hyperspectral image fusion framework that is agnostic to spectral bands and spatial scales, enabling better generalization across sensors and resolutions.

Contribution

The paper presents Matryoshka Kernel and an INR backbone to create a single, adaptable MS/HS fusion model with broad transferability.

Findings

Achieves state-of-the-art fusion performance.

Generalizes effectively to unseen sensors.

Handles arbitrary spatial resolutions.

Abstract

Current deep learning models for Multispectral and Hyperspectral Image Fusion (MS/HS fusion) are typically designed for fixed spectral bands and spatial scales, which limits their transferability across diverse sensors. To address this, we propose SSA, a universal framework for MS/HS fusion with spectral-band and fusion-scale agnosticism. Specifically, we introduce Matryoshka Kernel (MK), a novel operator that enables a single model to adapt to arbitrary numbers of spectral channels. Meanwhile, we build SSA upon an Implicit Neural Representation (INR) backbone that models the HS signal as a continuous function, enabling reconstruction at arbitrary spatial resolutions. Together, these two forms of agnosticism enable a single MS/HS fusion model that generalizes effectively to unseen sensors and spatial scales. Extensive experiments demonstrate that our single model achieves state-of-the-art performance while generalizing well to unseen sensors and scales, paving the way toward future HS foundation models.