Reconstruction of 3D multiphase microstructures using denoising diffusion models

Reconstruction of 3D multiphase microstructures using denoising diffusion models | 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 Reconstruction of 3D multiphase microstructures using denoising diffusion models Ali Aouf, Eric Laloy, Bart Rogiers, Christophe De Vleeschower This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7448759/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 The reconstruction of three-dimensional (3D) multiphase microstructures is essential for understanding the physical properties of porous materials. In this study, we evaluate the performance of Denoising Diffusion Probabilistic Models (DDPMs) and Generative Adversarial Networks (GANs), specifically WGAN-GP and iWGAN, in generating 3D representations of multiphase materials with varying degrees of heterogeneity: homogeneous illite clay, heterogeneous Boom Clay, and highly complex concrete. Our findings demonstrate that DDPMs outperform GANs in capturing the intricate spatial statistics and multiphase structures of these materials. While GAN-generated samples exhibit mode collapse and structures that do not resemble the ground truth, DDPMs produce microstructures that better preserve phase distributions and morphological characteristics. These results highlight the potential of diffusion models for realistic 3D microstructure synthesis, paving the way for improved simulations in subsurface and construction material applications. 3D Microstructure Generation Denoising Diffusion Models Generative Adversarial Networks Multiphase Materials Computational Imaging Generative AI Full Text Additional Declarations No competing interests reported. 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-7448759","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":531858580,"identity":"5e6a491a-41fa-40dc-9ea6-87ac91c838ef","order_by":0,"name":"Ali Aouf","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2ElEQVRIiWNgGAWjYDACdsYGEMXPz8DADBYwIKiFGaJFcmYD8VoglOSGA8Rq4W9mbmD4UXFYwvj84ccGPyruMJizN+DXInGYsYGx58xhCbMbacaJPWeeMVj2HCBgDVALA2/b4TqzGzzMhxnbDjMY3EjAr0MeZMvfNqDD+s8AtfwDarn/AL8WA6AWZqAtEgYMOczJjA0gWwi4yxCo5bDMmXQJCaBfDHuOHeax7CHgMLnj7Q8fvqmwluDvP/xY4kfNYTlz9gMErAECFCU8hNWPglEwCkbBKCAIAK8zQsJFtMYxAAAAAElFTkSuQmCC","orcid":"","institution":"Université Catholique de Louvain","correspondingAuthor":true,"prefix":"","firstName":"Ali","middleName":"","lastName":"Aouf","suffix":""},{"id":531858581,"identity":"a7a0dcc2-6124-448e-b0b4-3cec5a4236f6","order_by":1,"name":"Eric Laloy","email":"","orcid":"","institution":"Belgian Nuclear Research Centre","correspondingAuthor":false,"prefix":"","firstName":"Eric","middleName":"","lastName":"Laloy","suffix":""},{"id":531858582,"identity":"6bfea0d5-db1c-4c27-b982-2450371c75a8","order_by":2,"name":"Bart Rogiers","email":"","orcid":"","institution":"Belgian Nuclear Research Centre","correspondingAuthor":false,"prefix":"","firstName":"Bart","middleName":"","lastName":"Rogiers","suffix":""},{"id":531858583,"identity":"46386763-b1a8-47c0-8b36-feb53c2d4f21","order_by":3,"name":"Christophe De Vleeschower","email":"","orcid":"","institution":"Université Catholique de Louvain","correspondingAuthor":false,"prefix":"","firstName":"Christophe","middleName":"","lastName":"De Vleeschower","suffix":""}],"badges":[],"createdAt":"2025-08-25 01:38:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7448759/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7448759/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93898296,"identity":"96ce5963-8ef2-48ec-986b-3635f450fe01","added_by":"auto","created_at":"2025-10-20 04:11:55","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6020,"visible":true,"origin":"","legend":"","description":"","filename":"3b037e25b56e47c19795dcc7e9fef09f.json","url":"https://assets-eu.researchsquare.com/files/rs-7448759/v1/8aea92b7bc03cc01a8442d77.json"},{"id":93898794,"identity":"2b115d55-61fb-47fc-9547-8efb1259eb0e","added_by":"auto","created_at":"2025-10-20 04:20:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5196238,"visible":true,"origin":"","legend":"","description":"","filename":"papermanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7448759/v1_covered_fb211dcb-34c6-45b1-ab1a-63112c2dbd4c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Reconstruction of 3D multiphase microstructures using denoising diffusion models","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","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":"3D Microstructure Generation, Denoising Diffusion Models, Generative Adversarial Networks, Multiphase Materials, Computational Imaging, Generative AI","lastPublishedDoi":"10.21203/rs.3.rs-7448759/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7448759/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The reconstruction of three-dimensional (3D) multiphase microstructures is essential for understanding the physical properties of porous materials. In this study, we evaluate the performance of Denoising Diffusion Probabilistic Models (DDPMs) and Generative Adversarial Networks (GANs), specifically WGAN-GP and iWGAN, in generating 3D representations of multiphase materials with varying degrees of heterogeneity: homogeneous illite clay, heterogeneous Boom Clay, and highly complex concrete. Our findings demonstrate that DDPMs outperform GANs in capturing the intricate spatial statistics and multiphase structures of these materials. While GAN-generated samples exhibit mode collapse and structures that do not resemble the ground truth, DDPMs produce microstructures that better preserve phase distributions and morphological characteristics. These results highlight the potential of diffusion models for realistic 3D microstructure synthesis, paving the way for improved simulations in subsurface and construction material applications.","manuscriptTitle":"Reconstruction of 3D multiphase microstructures using denoising diffusion models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-20 04:11:50","doi":"10.21203/rs.3.rs-7448759/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":"821acb06-d390-43c7-89ac-c2f1ad4f6b04","owner":[],"postedDate":"October 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-24T14:23:21+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-20 04:11:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7448759","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7448759","identity":"rs-7448759","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}