HSFMamba: Hierarchical Selective Fusion Mamba Network for Optics-Guided Joint Super-Resolution and Denoising of Noise-Corrupted SAR Images

Synthetic Aperture Radar (SAR) image interpretation has attracted widespread attention in remote sensing applications. However, the performance of existing methods is severely hindered by inherent limitations of SAR imaging mechanisms, such as speckle noise and low resolution. With the continuous ad...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhicheng Zhao, Qing Gao, Jinquan Yan, Chenglong Li, Jin Tang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11045185/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849702084347166720
author Zhicheng Zhao
Qing Gao
Jinquan Yan
Chenglong Li
Jin Tang
author_facet Zhicheng Zhao
Qing Gao
Jinquan Yan
Chenglong Li
Jin Tang
author_sort Zhicheng Zhao
collection DOAJ
description Synthetic Aperture Radar (SAR) image interpretation has attracted widespread attention in remote sensing applications. However, the performance of existing methods is severely hindered by inherent limitations of SAR imaging mechanisms, such as speckle noise and low resolution. With the continuous advancement of remote sensing, it has become increasingly feasible to simultaneously acquire optical and SAR images. Given rich details in optical images, it is crucial to exploit this valuable information to guide quality enhancement of SAR images, thereby significantly improving their performance for practical applications. In this work, we propose a novel Hierarchical Selective Fusion Mamba Network (HSFMamba) for optics-guided joint super-resolution and denoising of SAR images, which simultaneously addresses resolution limitations and noise corruption in a unified framework. HSFMamba leverages the long-range modeling capability of the state space model with linear complexity and incorporates optical images through two progressive cross-selection scan mechanisms to perform high-quality reconstruction of SAR images corrupted by speckle noise. Specifically, we design a cross-modal feature selection module that dynamically identifies significant representations in optical images, thereby progressively extracting key information. To further leverage optical details while mitigating SAR speckle noise, we develop a frequency-spatial adaptive aggregation module aimed at better restoring image details, effectively enhancing critical high-frequency information. Additionally, we construct a well-aligned and high-resolution dataset for optics-guided joint SAR image super-resolution and denoising, comprising 3,200 optical-SAR image pairs, totaling 25,600 pairs across eight degradation modes. Extensive experiments demonstrate that HSFMamba effectively utilizes optical information to improve SAR image quality, outperforming several state-of-the-art methods.
format Article
id doaj-art-05dc4d551bd64b2aa58b1f4167e0b8b7
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-05dc4d551bd64b2aa58b1f4167e0b8b72025-08-20T03:17:46ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118164451646110.1109/JSTARS.2025.358121611045185HSFMamba: Hierarchical Selective Fusion Mamba Network for Optics-Guided Joint Super-Resolution and Denoising of Noise-Corrupted SAR ImagesZhicheng Zhao0https://orcid.org/0000-0002-2761-7399Qing Gao1Jinquan Yan2Chenglong Li3https://orcid.org/0000-0002-7233-2739Jin Tang4https://orcid.org/0000-0001-8375-3590Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education, School of Artificial Intelligence, Anhui University, Hefei, ChinaAnhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, ChinaInformation Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education, School of Artificial Intelligence, Anhui University, Hefei, ChinaInformation Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education, School of Artificial Intelligence, Anhui University, Hefei, ChinaAnhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, ChinaSynthetic Aperture Radar (SAR) image interpretation has attracted widespread attention in remote sensing applications. However, the performance of existing methods is severely hindered by inherent limitations of SAR imaging mechanisms, such as speckle noise and low resolution. With the continuous advancement of remote sensing, it has become increasingly feasible to simultaneously acquire optical and SAR images. Given rich details in optical images, it is crucial to exploit this valuable information to guide quality enhancement of SAR images, thereby significantly improving their performance for practical applications. In this work, we propose a novel Hierarchical Selective Fusion Mamba Network (HSFMamba) for optics-guided joint super-resolution and denoising of SAR images, which simultaneously addresses resolution limitations and noise corruption in a unified framework. HSFMamba leverages the long-range modeling capability of the state space model with linear complexity and incorporates optical images through two progressive cross-selection scan mechanisms to perform high-quality reconstruction of SAR images corrupted by speckle noise. Specifically, we design a cross-modal feature selection module that dynamically identifies significant representations in optical images, thereby progressively extracting key information. To further leverage optical details while mitigating SAR speckle noise, we develop a frequency-spatial adaptive aggregation module aimed at better restoring image details, effectively enhancing critical high-frequency information. Additionally, we construct a well-aligned and high-resolution dataset for optics-guided joint SAR image super-resolution and denoising, comprising 3,200 optical-SAR image pairs, totaling 25,600 pairs across eight degradation modes. Extensive experiments demonstrate that HSFMamba effectively utilizes optical information to improve SAR image quality, outperforming several state-of-the-art methods.https://ieeexplore.ieee.org/document/11045185/Denoisingmambamultimodaloptics-guidedremote sensingSynthetic aperture radar (SAR) image super-resolution (SR)
spellingShingle Zhicheng Zhao
Qing Gao
Jinquan Yan
Chenglong Li
Jin Tang
HSFMamba: Hierarchical Selective Fusion Mamba Network for Optics-Guided Joint Super-Resolution and Denoising of Noise-Corrupted SAR Images
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Denoising
mamba
multimodal
optics-guided
remote sensing
Synthetic aperture radar (SAR) image super-resolution (SR)
title HSFMamba: Hierarchical Selective Fusion Mamba Network for Optics-Guided Joint Super-Resolution and Denoising of Noise-Corrupted SAR Images
title_full HSFMamba: Hierarchical Selective Fusion Mamba Network for Optics-Guided Joint Super-Resolution and Denoising of Noise-Corrupted SAR Images
title_fullStr HSFMamba: Hierarchical Selective Fusion Mamba Network for Optics-Guided Joint Super-Resolution and Denoising of Noise-Corrupted SAR Images
title_full_unstemmed HSFMamba: Hierarchical Selective Fusion Mamba Network for Optics-Guided Joint Super-Resolution and Denoising of Noise-Corrupted SAR Images
title_short HSFMamba: Hierarchical Selective Fusion Mamba Network for Optics-Guided Joint Super-Resolution and Denoising of Noise-Corrupted SAR Images
title_sort hsfmamba hierarchical selective fusion mamba network for optics guided joint super resolution and denoising of noise corrupted sar images
topic Denoising
mamba
multimodal
optics-guided
remote sensing
Synthetic aperture radar (SAR) image super-resolution (SR)
url https://ieeexplore.ieee.org/document/11045185/
work_keys_str_mv AT zhichengzhao hsfmambahierarchicalselectivefusionmambanetworkforopticsguidedjointsuperresolutionanddenoisingofnoisecorruptedsarimages
AT qinggao hsfmambahierarchicalselectivefusionmambanetworkforopticsguidedjointsuperresolutionanddenoisingofnoisecorruptedsarimages
AT jinquanyan hsfmambahierarchicalselectivefusionmambanetworkforopticsguidedjointsuperresolutionanddenoisingofnoisecorruptedsarimages
AT chenglongli hsfmambahierarchicalselectivefusionmambanetworkforopticsguidedjointsuperresolutionanddenoisingofnoisecorruptedsarimages
AT jintang hsfmambahierarchicalselectivefusionmambanetworkforopticsguidedjointsuperresolutionanddenoisingofnoisecorruptedsarimages