Image Generation and Super-Resolution Reconstruction of Synthetic Aperture Radar Images Based on an Improved Single-Image Generative Adversarial Network

This paper presents a novel method for the super-resolution reconstruction and generation of synthetic aperture radar (SAR) images with an improved single-image generative adversarial network (ISinGAN). Unlike traditional machine learning methods typically requiring large datasets, SinGAN needs only...

Full description

Saved in:
Bibliographic Details
Main Authors: Xuguang Yang, Lixia Nie, Yun Zhang, Ling Zhang
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/16/5/370
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327029693972480
author Xuguang Yang
Lixia Nie
Yun Zhang
Ling Zhang
author_facet Xuguang Yang
Lixia Nie
Yun Zhang
Ling Zhang
author_sort Xuguang Yang
collection DOAJ
description This paper presents a novel method for the super-resolution reconstruction and generation of synthetic aperture radar (SAR) images with an improved single-image generative adversarial network (ISinGAN). Unlike traditional machine learning methods typically requiring large datasets, SinGAN needs only a single input image to extract internal structural details and generate high-quality samples. To improve this framework further, we introduced SinGAN with a self-attention module and incorporated noise specific to SAR images. These enhancements ensure that the generated images are more aligned with real-world SAR scenarios while also improving the robustness of the SinGAN framework. Experimental results demonstrate that ISinGAN significantly enhances SAR image resolution and target recognition performance.
format Article
id doaj-art-d3e8c2758fd44a23a38aec1d12ce6710
institution Kabale University
issn 2078-2489
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-d3e8c2758fd44a23a38aec1d12ce67102025-08-20T03:47:58ZengMDPI AGInformation2078-24892025-04-0116537010.3390/info16050370Image Generation and Super-Resolution Reconstruction of Synthetic Aperture Radar Images Based on an Improved Single-Image Generative Adversarial NetworkXuguang Yang0Lixia Nie1Yun Zhang2Ling Zhang3School of Mathematics and Information Engineering, Longdong University, Qingyang 745000, ChinaSchool of Mathematics and Information Engineering, Longdong University, Qingyang 745000, ChinaSchool of Electronic Information Engineering, Harbin Institute of Technology, Harbin 150001, ChinaCollege of Engineering, Ocean University of China, Qingdao 266100, ChinaThis paper presents a novel method for the super-resolution reconstruction and generation of synthetic aperture radar (SAR) images with an improved single-image generative adversarial network (ISinGAN). Unlike traditional machine learning methods typically requiring large datasets, SinGAN needs only a single input image to extract internal structural details and generate high-quality samples. To improve this framework further, we introduced SinGAN with a self-attention module and incorporated noise specific to SAR images. These enhancements ensure that the generated images are more aligned with real-world SAR scenarios while also improving the robustness of the SinGAN framework. Experimental results demonstrate that ISinGAN significantly enhances SAR image resolution and target recognition performance.https://www.mdpi.com/2078-2489/16/5/370generative adversarial networkimage generationsuper resolution
spellingShingle Xuguang Yang
Lixia Nie
Yun Zhang
Ling Zhang
Image Generation and Super-Resolution Reconstruction of Synthetic Aperture Radar Images Based on an Improved Single-Image Generative Adversarial Network
Information
generative adversarial network
image generation
super resolution
title Image Generation and Super-Resolution Reconstruction of Synthetic Aperture Radar Images Based on an Improved Single-Image Generative Adversarial Network
title_full Image Generation and Super-Resolution Reconstruction of Synthetic Aperture Radar Images Based on an Improved Single-Image Generative Adversarial Network
title_fullStr Image Generation and Super-Resolution Reconstruction of Synthetic Aperture Radar Images Based on an Improved Single-Image Generative Adversarial Network
title_full_unstemmed Image Generation and Super-Resolution Reconstruction of Synthetic Aperture Radar Images Based on an Improved Single-Image Generative Adversarial Network
title_short Image Generation and Super-Resolution Reconstruction of Synthetic Aperture Radar Images Based on an Improved Single-Image Generative Adversarial Network
title_sort image generation and super resolution reconstruction of synthetic aperture radar images based on an improved single image generative adversarial network
topic generative adversarial network
image generation
super resolution
url https://www.mdpi.com/2078-2489/16/5/370
work_keys_str_mv AT xuguangyang imagegenerationandsuperresolutionreconstructionofsyntheticapertureradarimagesbasedonanimprovedsingleimagegenerativeadversarialnetwork
AT lixianie imagegenerationandsuperresolutionreconstructionofsyntheticapertureradarimagesbasedonanimprovedsingleimagegenerativeadversarialnetwork
AT yunzhang imagegenerationandsuperresolutionreconstructionofsyntheticapertureradarimagesbasedonanimprovedsingleimagegenerativeadversarialnetwork
AT lingzhang imagegenerationandsuperresolutionreconstructionofsyntheticapertureradarimagesbasedonanimprovedsingleimagegenerativeadversarialnetwork