{"paper_id":"4d44b302-0162-4cdc-ad51-e909bcdaedc0","body_text":"Remote Sensing Multi-View Stereo using ConvLSTM Guided Iterative Depth Refinement | 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 Remote Sensing Multi-View Stereo using ConvLSTM Guided Iterative Depth Refinement Xuebin Wei, Yunxin Ye, Feng Cai, Liyan Wu, Feng Shao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7521676/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 21 You are reading this latest preprint version Abstract Multi-view 3D reconstruction from remote sensing imagery has emerged as a critical re-search direction in both computer vision and remote sensing. While deep learning-based methods have demonstrated remarkable success in close-range reconstruction, remote sensing scenarios continue to pose significant challenges. These include edge blurring due to varying viewpoints, noise artifacts in shadowed regions, and discontinuous depth estimates in areas with smoothly varying elevation, all of which hinder accurate matching and degrade reconstruction quality. To address these issues, we propose a novel end-to-end network, termed CGIDR-Net, which enhances remote sensing multi-view stereo (MVS) reconstruction through ConvLSTM guided iterative depth refinement. Specifically, we design a Deformable Channel Transformation Module (DCTM) to alleviate edge blurring across views by adaptively capturing spatial and channel-wise variations. Furthermore, we introduce a Differentiable 3D Masked Warping (MW) mechanism that leverages learnable masks to construct a more reliable cost volume, effectively sup-pressing occlusions and geometric distortions. Finally, we incorporate an Iterative Depth Refinement Module (IDRM) based on ConvLSTM, which progressively integrates spatial and contextual cues to refine depth predictions. Extensive experiments on several public datasets, including WHU, LuoJia-MVS, WHU-OMVS, and DTU, demonstrate that CGIDR-Net achieves superior performance in both accuracy and robustness compared to existing state-of-the-art methods. Remote sensing multi-view stereo 3D reconstruction depth estimation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 22 Sep, 2025 Reviews received at journal 22 Sep, 2025 Reviews received at journal 21 Sep, 2025 Reviews received at journal 18 Sep, 2025 Reviews received at journal 15 Sep, 2025 Reviewers agreed at journal 12 Sep, 2025 Reviewers agreed at journal 08 Sep, 2025 Reviewers agreed at journal 08 Sep, 2025 Reviewers agreed at journal 08 Sep, 2025 Reviewers agreed at journal 08 Sep, 2025 Reviewers agreed at journal 08 Sep, 2025 Reviewers agreed at journal 08 Sep, 2025 Reviewers agreed at journal 07 Sep, 2025 Reviews received at journal 06 Sep, 2025 Reviewers agreed at journal 06 Sep, 2025 Reviewers agreed at journal 06 Sep, 2025 Reviewers agreed at journal 06 Sep, 2025 Reviewers invited by journal 06 Sep, 2025 Editor assigned by journal 03 Sep, 2025 Submission checks completed at journal 03 Sep, 2025 First submitted to journal 02 Sep, 2025 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-7521676\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":false,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":512213964,\"identity\":\"c5c86cd1-cac9-4846-9111-0b54dbc0d40e\",\"order_by\":0,\"name\":\"Xuebin Wei\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Digital Ningbo Technology Co., Ltd\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Xuebin\",\"middleName\":\"\",\"lastName\":\"Wei\",\"suffix\":\"\"},{\"id\":512213965,\"identity\":\"4868b2eb-c6ad-48f9-9d5e-4ea8f49e0814\",\"order_by\":1,\"name\":\"Yunxin Ye\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Ningbo University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Yunxin\",\"middleName\":\"\",\"lastName\":\"Ye\",\"suffix\":\"\"},{\"id\":512213966,\"identity\":\"dc5a8bc7-5ac7-4a92-b7c1-c42381558eb6\",\"order_by\":2,\"name\":\"Feng Cai\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Ningbo Artificial Intelligence Institute of Shanghai Jiao Tong University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Feng\",\"middleName\":\"\",\"lastName\":\"Cai\",\"suffix\":\"\"},{\"id\":512213967,\"identity\":\"b99c3911-8f2d-49cd-8e1e-1c74f1b83189\",\"order_by\":3,\"name\":\"Liyan Wu\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Digital Ningbo Technology Co., Ltd\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Liyan\",\"middleName\":\"\",\"lastName\":\"Wu\",\"suffix\":\"\"},{\"id\":512213968,\"identity\":\"0fe53647-dce5-4bee-b071-7a58635b9a1b\",\"order_by\":4,\"name\":\"Feng Shao\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2ElEQVRIiWNgGAWjYDACCSCuAGJ+Bh4Ql5lILWeAWLKBZC0GB4jVIj+7+eGDAxV37Dbf7j0mwVBhndjAfvYAXi0Gd44ZGxw48yx5251zaRIMZ9ITG3jyEvBrkUgwk/7YdjjZ7EaOmQRj2+HEBgkeA/wOm5H+TeLgv8PJxjNAWv4RoYUBZPjBhsN2BhIgLQ1EaDG4kVNscODY4QSJG3nJFgnH0o3beHIIOmzjgwM1h+35Z+QevPGhxlq2n/0MAYdBQWIDiEwAYjai1AOBPbEKR8EoGAWjYAQCAJBBSTv+OpCvAAAAAElFTkSuQmCC\",\"orcid\":\"\",\"institution\":\"Ningbo University\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Feng\",\"middleName\":\"\",\"lastName\":\"Shao\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2025-09-03 01:23:03\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-7521676/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-7521676/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":91139777,\"identity\":\"cd8938e0-3025-4950-a1b1-f4a056684689\",\"added_by\":\"auto\",\"created_at\":\"2025-09-12 04:25:04\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":1360814,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"RemoteSensingMultiViewStereousingConvLSTMGuidedIterativeDepthRefinement.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7521676/v1_covered_a7004190-6334-4394-a12e-14d5f8423044.pdf\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"Remote Sensing Multi-View Stereo using ConvLSTM Guided Iterative Depth Refinement\",\"fulltext\":[],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":false,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":false,\"hideJournal\":false,\"highlight\":\"\",\"institution\":\"\",\"isAcceptedByJournal\":true,\"isAuthorSuppliedPdf\":true,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":false,\"isPdf\":true,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"identity\":\"the-journal-of-supercomputing\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":false,\"externalIdentity\":\"\",\"sideBox\":\"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)\",\"snPcode\":\"11227\",\"submissionUrl\":\"https://submission.nature.com/new-submission/11227/3\",\"title\":\"The Journal of Supercomputing\",\"twitterHandle\":\"\",\"acdcEnabled\":true,\"dfaEnabled\":true,\"editorialSystem\":\"stoa\",\"reportingPortfolio\":\"Springer Hybrid\",\"inReviewEnabled\":true,\"inReviewRevisionsEnabled\":false},\"keywords\":\"Remote sensing, multi-view stereo, 3D reconstruction, depth estimation\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-7521676/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-7521676/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003cp\\u003eMulti-view 3D reconstruction from remote sensing imagery has emerged as a critical re-search direction in both computer vision and remote sensing. While deep learning-based methods have demonstrated remarkable success in close-range reconstruction, remote sensing scenarios continue to pose significant challenges. These include edge blurring due to varying viewpoints, noise artifacts in shadowed regions, and discontinuous depth estimates in areas with smoothly varying elevation, all of which hinder accurate matching and degrade reconstruction quality. To address these issues, we propose a novel end-to-end network, termed CGIDR-Net, which enhances remote sensing multi-view stereo (MVS) reconstruction through ConvLSTM guided iterative depth refinement. Specifically, we design a Deformable Channel Transformation Module (DCTM) to alleviate edge blurring across views by adaptively capturing spatial and channel-wise variations. Furthermore, we introduce a Differentiable 3D Masked Warping (MW) mechanism that leverages learnable masks to construct a more reliable cost volume, effectively sup-pressing occlusions and geometric distortions. Finally, we incorporate an Iterative Depth Refinement Module (IDRM) based on ConvLSTM, which progressively integrates spatial and contextual cues to refine depth predictions. Extensive experiments on several public datasets, including WHU, LuoJia-MVS, WHU-OMVS, and DTU, demonstrate that CGIDR-Net achieves superior performance in both accuracy and robustness compared to existing state-of-the-art methods.\\u003c/p\\u003e\",\"manuscriptTitle\":\"Remote Sensing Multi-View Stereo using ConvLSTM Guided Iterative Depth Refinement\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2025-09-12 04:08:34\",\"doi\":\"10.21203/rs.3.rs-7521676/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0},{\"type\":\"decision\",\"content\":\"Revision requested\",\"date\":\"2025-09-22T20:28:05+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2025-09-22T05:44:17+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2025-09-21T07:26:15+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2025-09-18T06:54:59+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2025-09-16T02:36:27+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"50654477003873699399071136948550614118\",\"date\":\"2025-09-12T05:52:27+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"53082182358298802151328548731919973684\",\"date\":\"2025-09-09T01:24:51+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"8313048192760182356618228923452732340\",\"date\":\"2025-09-09T01:20:04+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"142206327514728934741697340267168919288\",\"date\":\"2025-09-08T11:23:32+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"142746431540234890341773687717084383714\",\"date\":\"2025-09-08T11:19:01+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"122324064417359842401479383151239712701\",\"date\":\"2025-09-08T08:25:01+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"227805523506769626780097038689530394054\",\"date\":\"2025-09-08T05:30:26+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"133299858303158777307258074633557993927\",\"date\":\"2025-09-07T04:41:31+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2025-09-07T03:01:54+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"281350663610810609639763261767706815074\",\"date\":\"2025-09-07T02:43:17+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"83908756052198266259765414393533040391\",\"date\":\"2025-09-07T01:26:34+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"196840981025389833271641257860023188505\",\"date\":\"2025-09-07T01:20:05+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewersInvited\",\"content\":\"\",\"date\":\"2025-09-07T01:10:58+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorAssigned\",\"content\":\"\",\"date\":\"2025-09-03T13:33:31+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"checksComplete\",\"content\":\"\",\"date\":\"2025-09-03T13:33:08+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"submitted\",\"content\":\"The Journal of Supercomputing\",\"date\":\"2025-09-03T01:06:59+00:00\",\"index\":\"\",\"fulltext\":\"\"}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"identity\":\"the-journal-of-supercomputing\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":false,\"externalIdentity\":\"\",\"sideBox\":\"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)\",\"snPcode\":\"11227\",\"submissionUrl\":\"https://submission.nature.com/new-submission/11227/3\",\"title\":\"The Journal of Supercomputing\",\"twitterHandle\":\"\",\"acdcEnabled\":true,\"dfaEnabled\":true,\"editorialSystem\":\"stoa\",\"reportingPortfolio\":\"Springer Hybrid\",\"inReviewEnabled\":true,\"inReviewRevisionsEnabled\":false}}],\"origin\":\"\",\"ownerIdentity\":\"4e0580c8-e47f-45eb-8845-bdd6f4092ff4\",\"owner\":[],\"postedDate\":\"September 12th, 2025\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"under-review\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2025-10-22T15:23:25+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2025-09-12 04:08:34\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-7521676\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-7521676\",\"identity\":\"rs-7521676\",\"version\":[\"v1\"]},\"buildId\":\"8U1c8b4HqxoKbykW_rLl7\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}