# Enhancing Hyperspectral Images via Diffusion Model and Group-Autoencoder Super-resolution Network

arXiv: https://arxiv.org/abs/2402.17285 · HTML: https://mlsanity.com/paper/2402.17285/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 11 of 11)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [Implicit Diffusion Models for Continuous Super-Resolution](https://mlsanity.com/paper/2303.16491/) (2023)
- [Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery](https://mlsanity.com/paper/2005.08752/) (2020)
- [DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-Resolution](https://mlsanity.com/paper/2303.13933/) (2023)
- [Exploring Multi-Timestep Multi-Stage Diffusion Features for Hyperspectral Image Classification](https://mlsanity.com/paper/2306.08964/) (2023)

## Built on by (most cited first, 11 of 11)

- [HSIGene: A Foundation Model For Hyperspectral Image Generation](https://mlsanity.com/paper/2409.12470/) (2024)
- [Towards Lightweight Hyperspectral Image Super-Resolution with Depthwise Separable Dilated Convolutional Network](https://mlsanity.com/paper/2505.00374/) (2025)
- [Hipandas: Hyperspectral Image Joint Denoising and Super-Resolution by Image Fusion with the Panchromatic Image](https://mlsanity.com/paper/2412.04201/) (2024)
- [A Fusion-Guided Inception Network for Hyperspectral Image Super-Resolution](https://mlsanity.com/paper/2505.03431/) (2025)
- [DACN: Dual-Attention Convolutional Network for Hyperspectral Image Super-Resolution](https://mlsanity.com/paper/2506.05041/) (2025)
- [Hybrid Deep Learning for Hyperspectral Single Image Super-Resolution](https://mlsanity.com/paper/2510.00033/) (2025)
- [Diffusion-Denoised Hyperspectral Gaussian Splatting](https://mlsanity.com/paper/2505.21890/) (2025)
- [GEWDiff: Geometric Enhanced Wavelet-based Diffusion Model for Hyperspectral Image Super-resolution](https://mlsanity.com/paper/2511.07103/) (2025)
- [FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution](https://mlsanity.com/paper/2506.11545/) (2025)
- [HDW-SR: High-Frequency Guided Diffusion Model based on Wavelet Decomposition for Image Super-Resolution](https://mlsanity.com/paper/2511.13175/) (2025)
- [A Dual-Domain Convolutional Network for Hyperspectral Single-Image Super-Resolution](https://mlsanity.com/paper/2512.09546/) (2025)

## Abstract (arXiv)

Existing hyperspectral image (HSI) super-resolution (SR) methods struggle to effectively capture the complex spectral-spatial relationships and low-level details, while diffusion models represent a promising generative model known for their exceptional performance in modeling complex relations and learning high and low-level visual features. The direct application of diffusion models to HSI SR is hampered by challenges such as difficulties in model convergence and protracted inference time. In this work, we introduce a novel Group-Autoencoder (GAE) framework that synergistically combines with the diffusion model to construct a highly effective HSI SR model (DMGASR). Our proposed GAE framework encodes high-dimensional HSI data into low-dimensional latent space where the diffusion model works, thereby alleviating the difficulty of training the diffusion model while maintaining band correlation and considerably reducing inference time. Experimental results on both natural and remote sensing hyperspectral datasets demonstrate that the proposed method is superior to other state-of-the-art methods both visually and metrically.