# Leveraging pretrained RGB denoisers for hyperspectral image restoration

arXiv: https://arxiv.org/abs/2605.24769 · HTML: https://mlsanity.com/paper/2605.24769/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 23 May 2026.

## Builds on (most cited first, 12 of 12)

- [Plug-and-Play Image Restoration with Deep Denoiser Prior](https://mlsanity.com/paper/2008.13751/) (2020)
- [Denoising Diffusion Models for Plug-and-Play Image Restoration](https://mlsanity.com/paper/2305.08995/) (2023)
- [Plug-and-Play Methods Provably Converge with Properly Trained Denoisers](https://mlsanity.com/paper/1905.05406/) (2019)
- [HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models](https://mlsanity.com/paper/2402.15865/) (2024)
- [FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration](https://mlsanity.com/paper/2412.01427/) (2024)
- [Deep Hyperspectral Prior: Denoising, Inpainting, Super-Resolution](https://mlsanity.com/paper/1902.00301/) (2019)
- [Spatial-Spectral Transformer for Hyperspectral Image Denoising](https://mlsanity.com/paper/2211.14090/) (2022)
- [A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration](https://mlsanity.com/paper/2111.09708/) (2021)
- [Deep Plug-and-Play Prior for Hyperspectral Image Restoration](https://mlsanity.com/paper/2209.08240/) (2022)
- [Hyperspectral recovery from RGB images using Gaussian Processes](https://mlsanity.com/paper/1801.04654/) (2018)
- [MP-HSIR: A Multi-Prompt Framework for Universal Hyperspectral Image Restoration](https://mlsanity.com/paper/2503.09131/) (2025)
- [GRU-Net: Gaussian Attention Aided Dense Skip Connection Based MultiResUNet for Breast Histopathology Image Segmentation](https://mlsanity.com/paper/2406.08604/) (2024)

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

- [Lightweight Interpretable RGB-Guided Hyperspectral Super-Resolution under Real Cross-resolution Misalignment](https://mlsanity.com/paper/2609.01060/) (2026)

## Abstract (arXiv)

Hyperspectral image restoration faces several challenges, including limited training data, strong sensor specificity, and high spectral dimensionality. These limitations hinder the learning of robust hyperspectral priors, motivating the reuse of priors learned from large-scale RGB data. In this work, we propose a minimally trained, lightweight adapter that repurposes frozen pretrained RGB denoisers for hyperspectral restoration through a projection mapping. The method denoises low-dimensional spectral projections and reconstructs the hyperspectral cube through constrained linear aggregation, while preserving plug-and-play compatibility and the stability properties of the underlying RGB denoiser. Experiments on denoising, deblurring, and super-resolution across multiple datasets demonstrate consistent improvements over hyperspectral-specific baselines, showing the strong transferability of large-scale RGB priors.