HSR-Diff:Hyperspectral Image Super-Resolution via Conditional Diffusion Models

TL;DR

This paper introduces HSR-Diff, a novel hyperspectral image super-resolution method using conditional diffusion models that iteratively refines low-resolution images into high-resolution ones by leveraging high-resolution multispectral images and advanced denoising transformers.

Contribution

The paper proposes a new diffusion-based super-resolution framework for hyperspectral images that combines hierarchical feature conditioning and progressive learning for improved results.

Findings

Outperforms state-of-the-art methods on four public datasets

Effectively integrates high-resolution multispectral images with low-resolution hyperspectral images

Demonstrates superior image quality and detail preservation

Abstract

Despite the proven significance of hyperspectral images (HSIs) in performing various computer vision tasks, its potential is adversely affected by the low-resolution (LR) property in the spatial domain, resulting from multiple physical factors. Inspired by recent advancements in deep generative models, we propose an HSI Super-resolution (SR) approach with Conditional Diffusion Models (HSR-Diff) that merges a high-resolution (HR) multispectral image (MSI) with the corresponding LR-HSI. HSR-Diff generates an HR-HSI via repeated refinement, in which the HR-HSI is initialized with pure Gaussian noise and iteratively refined. At each iteration, the noise is removed with a Conditional Denoising Transformer (CDF ormer) that is trained on denoising at different noise levels, conditioned on the hierarchical feature maps of HR-MSI and LR-HSI. In addition, a progressive learning strategy is employed to exploit the global information of full-resolution images. Systematic experiments have been conducted on four public datasets, demonstrating that HSR-Diff outperforms state-of-the-art methods.