Comparing Deep Learning Approaches for SAR Imaging: Electromagnetic and Segmentation-Driven Simulation versus Image-to-Image Style Transfer

Comparing Deep Learning Approaches for SAR Imaging: Electromagnetic and Segmentation-Driven Simulation versus Image-to-Image Style Transfer | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Comparing Deep Learning Approaches for SAR Imaging: Electromagnetic and Segmentation-Driven Simulation versus Image-to-Image Style Transfer Nathan Letheule, Flora Weissgerber, Sylvain Lobry, Elise Colin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4805717/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract This article explores two innovative approaches to simulating synthetic aperture radar (SAR) images from their optical modality equivalents using deep learning methods; one approach also incorporates a physical simulator. The goal is to generate realistic images of large scenes, which could be used for training supervised recognition algorithms or pilot training. We explore, on one hand, the use of conditional generative adversarial networks (cGAN) for supervised transfer from the optical to the radar modality. On the other hand, we use EMPRISE, a physical simulator developed by ONERA, which utilizes a description of materials present in the scene, and we consider achieving this description through supervised semantic segmentation of the optical image. The evaluation of the realism of the obtained SAR images focuses on the fidelity of textures, as well as the presence of bright scatterers. We propose to use the Bhattacharyya distance between the second and third log-cumulant diagrams of the real and simulated images to assess the fidelity of textures. We consider three complementary criteria for evaluating bright point similarity, in particular the chamfer distance between the point clouds detected in both real and simulated images. In our dataset, the cGAN model fails to generate bright points effectively, whereas EMPRISE generates a point cloud with an approximate chamfer distance of 15 pixels. Moreover, EMPRISE tends to overgenerate bright points in the simulated images but demonstrates superior performance in urban areas. Concerning textures, the Bhattacharyya distance for cGAN is approximately 1.72, indicating degraded performance over forested regions, whereas for EMPRISE, this distance is about 0.10, showing the best results in the same forest areas. The results demonstrate that while the cGAN approach produces images with realistic content, it falls short in accurately simulating micro-textures and bright scatterers. Despite being constrained by segmentation into a limited number of classes and exhibiting modest performance, the EMPRISE simulation proves to be more effective than cGAN at reproducing real SAR features. Artificial Intelligence and Machine Learning Geographic Information Systems Simulation Radar Deep Learning Remote sensing Semantic segmentation Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4805717","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":332015086,"identity":"2b7675f3-fbd3-463e-b2da-68e646f0a4ff","order_by":0,"name":"Nathan Letheule","email":"","orcid":"","institution":"ONERA, DTIS/DEMR, Université Paris Saclay","correspondingAuthor":false,"prefix":"","firstName":"Nathan","middleName":"","lastName":"Letheule","suffix":""},{"id":332015087,"identity":"102084c3-1df6-4a62-ad9d-ae41d190fae4","order_by":1,"name":"Flora Weissgerber","email":"","orcid":"","institution":"ONERA, DTIS, Université Paris Saclay","correspondingAuthor":false,"prefix":"","firstName":"Flora","middleName":"","lastName":"Weissgerber","suffix":""},{"id":332015088,"identity":"5f67d2e7-a4db-4235-8391-b5551c80e747","order_by":2,"name":"Sylvain Lobry","email":"","orcid":"","institution":"LIPADE, Université Paris Cité","correspondingAuthor":false,"prefix":"","firstName":"Sylvain","middleName":"","lastName":"Lobry","suffix":""},{"id":332015089,"identity":"02876106-88f2-48e0-809f-727fcc60c487","order_by":3,"name":"Elise Colin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3klEQVRIiWNgGAWjYDACdsYGMM3HzMD4ACIEo3EBZqgWNmYGZgOokAEBLVCaDYgkiNLCz8zc/OEDg50cGzvvsYqPO2zy+RuY2T7g0yLZzNgmOYMh2ZiNmS/t5swzaZYzDjAzz8CnxeAwYxszD8OBRCBpdpu37bABwwH+w3gdZn+YsfnzH6iWYt62/wbyQFvwajEAhpg0A1QLM2/bAQMDQlokgA6T7DEA+YXHWHJmW7KB4WECWvjb2x9/+FFhJ8fPf8bww8c2OwO54834tUCdh8whRsMoGAWjYBSMAvwAAPzUOKkQcybpAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-7401-8073","institution":"ONERA, DTIS, Université Paris Saclay","correspondingAuthor":true,"prefix":"","firstName":"Elise","middleName":"","lastName":"Colin","suffix":""}],"badges":[],"createdAt":"2024-07-26 06:18:35","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-4805717/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4805717/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":61370727,"identity":"fcd913cc-1ee1-42c2-9665-070c5e45efd5","added_by":"auto","created_at":"2024-07-30 02:54:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1802006,"visible":true,"origin":"","legend":"","description":"","filename":"Letheulesegmentation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4805717/v1_covered_272b740c-7fba-4a25-bae6-26511c7e94aa.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eComparing Deep Learning Approaches for SAR Imaging: Electromagnetic and Segmentation-Driven Simulation versus Image-to-Image Style Transfer\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[{"identity":"910e3219-fb8f-453f-a4a4-8d2d0893e46d","identifier":"10.13039/501100018833","name":"Agence de l’Innovation de Defense","awardNumber":"PhD Grant","order_by":0}],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Onera (France)","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Simulation, Radar, Deep Learning, Remote sensing, Semantic segmentation","lastPublishedDoi":"10.21203/rs.3.rs-4805717/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4805717/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis article explores two innovative approaches to simulating synthetic aperture radar (SAR) images from their optical modality equivalents using deep learning methods; one approach also incorporates a physical simulator. The goal is to generate realistic images of large scenes, which could be used for training supervised recognition algorithms or pilot training. We explore, on one hand, the use of conditional generative adversarial networks (cGAN) for supervised transfer from the optical to the radar modality. On the other hand, we use EMPRISE, a physical simulator developed by ONERA, which utilizes a description of materials present in the scene, and we consider achieving this description through supervised semantic segmentation of the optical image. The evaluation of the realism of the obtained SAR images focuses on the fidelity of textures, as well as the presence of bright scatterers. We propose to use the Bhattacharyya distance between the second and third log-cumulant diagrams of the real and simulated images to assess the fidelity of textures. We consider three complementary criteria for evaluating bright point similarity, in particular the chamfer distance between the point clouds detected in both real and simulated images. \u0026nbsp;In our dataset, the cGAN model fails to generate bright points effectively, whereas EMPRISE generates a point cloud with an approximate chamfer distance of 15 pixels. Moreover, EMPRISE tends to overgenerate bright points in the simulated images but demonstrates superior performance in urban areas. Concerning textures, the Bhattacharyya distance for cGAN is approximately 1.72, indicating degraded performance over forested regions, whereas for EMPRISE, this distance is about 0.10, showing the best results in the same forest areas. The results demonstrate that while the cGAN approach produces images with realistic content, it falls short in accurately simulating micro-textures and bright scatterers. Despite being constrained by segmentation into a limited number of classes and exhibiting modest performance, the EMPRISE simulation proves to be more effective than cGAN at reproducing real SAR features.\u003c/p\u003e","manuscriptTitle":"Comparing Deep Learning Approaches for SAR Imaging: Electromagnetic and Segmentation-Driven Simulation versus Image-to-Image Style Transfer","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-30 02:46:50","doi":"10.21203/rs.3.rs-4805717/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"35520fff-55db-4c26-97a6-31d141c39108","owner":[],"postedDate":"July 30th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":35260419,"name":"Artificial Intelligence and Machine Learning"},{"id":35260420,"name":"Geographic Information Systems"}],"tags":[],"updatedAt":"2024-07-30T02:46:50+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-30 02:46:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4805717","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4805717","identity":"rs-4805717","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}