MSFDN: multi-scale spatial-spectral-frequency joint denoising network for hyperspectral images

Hyperspectral images often suffer from various types of noise, such as Gaussian noise, impulse noise, stripe noise, and deadline, which are caused by weather conditions and sensor equipment. Hyperspectral denoising aims to remove noise and obtain clear images. Therefore, in order to more accurately...

Full description

Saved in:
Bibliographic Details
Main Authors: Kai Ren, Weiwei Sun, Xiangchao Meng, Gang Yang
Format: Article
Language:English
Published: Taylor & Francis Group 2025-03-01
Series:Geo-spatial Information Science
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/10095020.2025.2477552
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850280596089077760
author Kai Ren
Weiwei Sun
Xiangchao Meng
Gang Yang
author_facet Kai Ren
Weiwei Sun
Xiangchao Meng
Gang Yang
author_sort Kai Ren
collection DOAJ
description Hyperspectral images often suffer from various types of noise, such as Gaussian noise, impulse noise, stripe noise, and deadline, which are caused by weather conditions and sensor equipment. Hyperspectral denoising aims to remove noise and obtain clear images. Therefore, in order to more accurately describe and extract noise, and obtain better denoising results, we propose a novel approach called the multi-scale spatial-spectral-frequency joint denoising network for hyperspectral images (MSFDN). Considering the spatial-spectral distribution characteristics of noisy signals, MSFDN first converts the hyperspectral image into a low-dimensional subspace by constructing a subspace projection network. Then, the frequency distribution characteristics of noise signals in subspaces are described, and the noise signals are removed by designing a noise separation network. Finally, a subspace back projection network is constructed to reconstruct the initialized denoising image, and the conditional diffusion model is used to refine the initialized denoising results. It is worth noting that the above framework is embedded in the UNet network. Extensive experiments are conducted on simulated and real datasets. The experimental results demonstrate that MSFDN outperforms other state-of-the-art methods and exhibits robustness.
format Article
id doaj-art-7e3592bd8ca649bd853f2d6c6d71002d
institution OA Journals
issn 1009-5020
1993-5153
language English
publishDate 2025-03-01
publisher Taylor & Francis Group
record_format Article
series Geo-spatial Information Science
spelling doaj-art-7e3592bd8ca649bd853f2d6c6d71002d2025-08-20T01:48:40ZengTaylor & Francis GroupGeo-spatial Information Science1009-50201993-51532025-03-0112010.1080/10095020.2025.2477552MSFDN: multi-scale spatial-spectral-frequency joint denoising network for hyperspectral imagesKai Ren0Weiwei Sun1Xiangchao Meng2Gang Yang3Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, ChinaDepartment of Geography and Spatial Information Techniques, Ningbo University, Ningbo, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, ChinaDepartment of Geography and Spatial Information Techniques, Ningbo University, Ningbo, ChinaHyperspectral images often suffer from various types of noise, such as Gaussian noise, impulse noise, stripe noise, and deadline, which are caused by weather conditions and sensor equipment. Hyperspectral denoising aims to remove noise and obtain clear images. Therefore, in order to more accurately describe and extract noise, and obtain better denoising results, we propose a novel approach called the multi-scale spatial-spectral-frequency joint denoising network for hyperspectral images (MSFDN). Considering the spatial-spectral distribution characteristics of noisy signals, MSFDN first converts the hyperspectral image into a low-dimensional subspace by constructing a subspace projection network. Then, the frequency distribution characteristics of noise signals in subspaces are described, and the noise signals are removed by designing a noise separation network. Finally, a subspace back projection network is constructed to reconstruct the initialized denoising image, and the conditional diffusion model is used to refine the initialized denoising results. It is worth noting that the above framework is embedded in the UNet network. Extensive experiments are conducted on simulated and real datasets. The experimental results demonstrate that MSFDN outperforms other state-of-the-art methods and exhibits robustness.https://www.tandfonline.com/doi/10.1080/10095020.2025.2477552Hyperspectral imagedenoisingspatial-spectral-frequencydeep learning
spellingShingle Kai Ren
Weiwei Sun
Xiangchao Meng
Gang Yang
MSFDN: multi-scale spatial-spectral-frequency joint denoising network for hyperspectral images
Geo-spatial Information Science
Hyperspectral image
denoising
spatial-spectral-frequency
deep learning
title MSFDN: multi-scale spatial-spectral-frequency joint denoising network for hyperspectral images
title_full MSFDN: multi-scale spatial-spectral-frequency joint denoising network for hyperspectral images
title_fullStr MSFDN: multi-scale spatial-spectral-frequency joint denoising network for hyperspectral images
title_full_unstemmed MSFDN: multi-scale spatial-spectral-frequency joint denoising network for hyperspectral images
title_short MSFDN: multi-scale spatial-spectral-frequency joint denoising network for hyperspectral images
title_sort msfdn multi scale spatial spectral frequency joint denoising network for hyperspectral images
topic Hyperspectral image
denoising
spatial-spectral-frequency
deep learning
url https://www.tandfonline.com/doi/10.1080/10095020.2025.2477552
work_keys_str_mv AT kairen msfdnmultiscalespatialspectralfrequencyjointdenoisingnetworkforhyperspectralimages
AT weiweisun msfdnmultiscalespatialspectralfrequencyjointdenoisingnetworkforhyperspectralimages
AT xiangchaomeng msfdnmultiscalespatialspectralfrequencyjointdenoisingnetworkforhyperspectralimages
AT gangyang msfdnmultiscalespatialspectralfrequencyjointdenoisingnetworkforhyperspectralimages