# Robust Hyperspectral Image Fusion with Simultaneous Guide Image Denoising via Constrained Convex Optimization

arXiv: https://arxiv.org/abs/2209.11979 · HTML: https://mlsanity.com/paper/2209.11979/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 54 references that are in the map.
- First posted on arXiv 24 Sep 2022.

## Builds on (most cited first, 8 of 8)

- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Hyperspectral pansharpening: a review](https://mlsanity.com/paper/1504.04531/) (2015)
- [A convex formulation for hyperspectral image superresolution via subspace-based regularization](https://mlsanity.com/paper/1411.4005/) (2014)
- [Unsupervised and Unregistered Hyperspectral Image Super-Resolution with Mutual Dirichlet-Net](https://mlsanity.com/paper/1904.12175/) (2019)
- [Hyperspectral Super-Resolution via Coupled Tensor Ring Factorization](https://mlsanity.com/paper/2001.01547/) (2020)
- [Multi-Band Image Fusion Based on Spectral Unmixing](https://mlsanity.com/paper/1603.08720/) (2016)
- [Efficient Constrained Signal Reconstruction by Randomized Epigraphical Projection](https://mlsanity.com/paper/1810.12249/) (2018)
- [A Constrained Convex Optimization Approach to Hyperspectral Image Restoration with Hybrid Spatio-Spectral Regularization](https://mlsanity.com/paper/1907.13357/) (2019)

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

- [CORE: Learning Consistent Ordinal REpresentations for Image Ordinal Estimation](https://mlsanity.com/paper/2301.06122/) (2023)

## Abstract (arXiv)

The paper proposes a new high spatial resolution hyperspectral (HR-HS) image estimation method based on convex optimization. The method assumes a low spatial resolution HS (LR-HS) image and a guide image as observations, where both observations are contaminated by noise. Our method simultaneously estimates an HR-HS image and a noiseless guide image, so the method can utilize spatial information in a guide image even if it is contaminated by heavy noise. The proposed estimation problem adopts hybrid spatio-spectral total variation as regularization and evaluates the edge similarity between HR-HS and guide images to effectively use apriori knowledge on an HR-HS image and spatial detail information in a guide image. To efficiently solve the problem, we apply a primal-dual splitting method. Experiments demonstrate the performance of our method and the advantage over several existing methods.