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

arXiv: https://arxiv.org/abs/2602.01681 · HTML: https://mlsanity.com/paper/2602.01681/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 44 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [Matryoshka Representation Learning](https://mlsanity.com/paper/2205.13147/) (2022)
- [Fusformer: A Transformer-based Fusion Approach for Hyperspectral Image Super-resolution](https://mlsanity.com/paper/2109.02079/) (2021)
- [MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection](https://mlsanity.com/paper/2410.14731/) (2024)
- [Implicit Neural Representation Learning for Hyperspectral Image Super-Resolution](https://mlsanity.com/paper/2112.10541/) (2021)
- [Spectral-wise Implicit Neural Representation for Hyperspectral Image Reconstruction](https://mlsanity.com/paper/2312.01061/) (2023)
- [Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image Fusion](https://mlsanity.com/paper/2404.15174/) (2024)
- [Train Once, Deploy Anywhere: Matryoshka Representation Learning for Multimodal Recommendation](https://mlsanity.com/paper/2409.16627/) (2024)
- [Hyperspectral and multispectral image fusion with arbitrary resolution through self-supervised representations](https://mlsanity.com/paper/2405.17818/) (2024)
- [Unsupervised Cycle-consistent Generative Adversarial Networks for Pan-sharpening](https://mlsanity.com/paper/2109.09395/) (2021)
- [Multispectral to Hyperspectral using Pretrained Foundational model](https://mlsanity.com/paper/2502.19451/) (2025)

## Built on by (most cited first, 1 of 1)

- [Super-Resolving Unseen Hyperspectral Sensors at Any Scale via Spatial Operators](https://mlsanity.com/paper/2609.39926/) (2026)

## Abstract (arXiv)

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.