# Unregistered Spectral Image Fusion: Unmixing, Adversarial Learning, and Recoverability

arXiv: https://arxiv.org/abs/2603.21510 · HTML: https://mlsanity.com/paper/2603.21510/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 57 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification](https://mlsanity.com/paper/1608.05167/) (2016)
- [Nonnegative Matrix Factorization for Signal and Data Analytics: Identifiability, Algorithms, and Applications](https://mlsanity.com/paper/1803.01257/) (2018)
- [A convex formulation for hyperspectral image superresolution via subspace-based regularization](https://mlsanity.com/paper/1411.4005/) (2014)
- [Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective](https://mlsanity.com/paper/2106.07115/) (2021)
- [Hyperspectral Super-Resolution: A Coupled Tensor Factorization Approach](https://mlsanity.com/paper/1804.05307/) (2018)
- [Spectrum Cartography via Coupled Block-Term Tensor Decomposition](https://mlsanity.com/paper/1911.12468/) (2019)
- [Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations](https://mlsanity.com/paper/2311.08815/) (2023)
- [Unsupervised and Unregistered Hyperspectral Image Super-Resolution with Mutual Dirichlet-Net](https://mlsanity.com/paper/1904.12175/) (2019)
- [Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment](https://mlsanity.com/paper/2406.13371/) (2024)
- [Self-Dictionary Sparse Regression for Hyperspectral Unmixing: Greedy Pursuit and Pure Pixel Search are Related](https://mlsanity.com/paper/1409.4320/) (2014)
- [Hyperspectral Super-Resolution via Interpretable Block-Term Tensor Modeling](https://mlsanity.com/paper/2006.10248/) (2020)
- [Hyperspectral Super-Resolution with Coupled Tucker Approximation: Recoverability and SVD-based algorithms](https://mlsanity.com/paper/1811.11091/) (2018)
- [Advances and Challenges in Multimodal Remote Sensing Image Registration](https://mlsanity.com/paper/2302.00912/) (2023)
- [Normalized Total Gradient: A New Measure for Multispectral Image Registration](https://mlsanity.com/paper/1702.04562/) (2017)
- [Fast and Structured Block-Term Tensor Decomposition For Hyperspectral Unmixing](https://mlsanity.com/paper/2205.03798/) (2022)
- [Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach](https://mlsanity.com/paper/2401.09671/) (2024)
- [Is There Any Recovery Guarantee with Coupled Structured Matrix Factorization for Hyperspectral Super-Resolution?](https://mlsanity.com/paper/1907.12728/) (2019)
- [Rethinking Coupled Tensor Analysis for Hyperspectral Super-Resolution: Recoverable Modeling Under Endmember Variability](https://mlsanity.com/paper/2512.19489/) (2025)

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

- [Registration-Free Hyperspectral Reconstruction from RGB via a Permutation-Invariant Gram-Matrix Principle](https://mlsanity.com/paper/2608.14994/) (2026)

## Abstract (arXiv)

This paper addresses the fusion of a pair of spatially unregistered hyperspectral image (HSI) and multispectral image (MSI) covering roughly overlapping regions. HSIs offer high spectral but low spatial resolution, while MSIs provide the opposite. The goal is to integrate their complementary information to enhance both HSI spatial resolution and MSI spectral resolution. While hyperspectral-multispectral fusion (HMF) has been widely studied, the unregistered setting remains challenging. Many existing methods focus solely on MSI super-resolution, leaving HSI unchanged. Supervised deep learning approaches were proposed for HSI super-resolution, but rely on accurate training data, which is often unavailable. Moreover, theoretical analyses largely address the co-registered case, leaving unregistered HMF poorly understood. In this work, an unsupervised framework is proposed to simultaneously super-resolve both MSI and HSI. The method integrates coupled spectral unmixing for MSI super-resolution with latent-space adversarial learning for HSI super-resolution. Theoretical guarantees on the recoverability of the super-resolution MSI and HSI are established under reasonable generative models -- providing, to our best knowledge, the first such insights for unregistered HMF. The approach is validated on semi-real and real HSI-MSI pairs across diverse conditions.