AnimeINR: Spatio-Temporal Implicit Neural Representation for Arbitrary-Scale Animation Video Super-Resolution

AnimeINR: Spatio-Temporal Implicit Neural Representation for Arbitrary-Scale Animation Video Super-Resolution | 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 Article AnimeINR: Spatio-Temporal Implicit Neural Representation for Arbitrary-Scale Animation Video Super-Resolution Qin Jiang, Qinglin Wang, Lihua Chi, Zhengqiu Deng, Xinhai Chen, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4603382/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 Existing methods for video super-resolution (VSR) and video frame interpolation (VFI) primarily concentrate on devising a general pipeline suitable for open-domain videos. However, these approaches tend to overlook the inherent distinctions in animation data. Specifically, animation often features lines and smooth areas that lack textures, thereby complicating the estimation of inter-frame motions. Moreover, the exaggerated expressions common in animation introduce non-linear and highly altered motion characteristics, which can significantly limit the performance of existing methods when applied to the animation domain.In this paper, we present the first attempt to tackle the challenge of Implicit Neural Representation for achieving Space-Time Video Super-Resolution (STVSR) at arbitrary spatial and temporal scales within the animation domain. To this end, we propose a novel unified pipeline named AnimeINR, comprising three specialized modules: the Spatial Implicit Neural Representation, which defines a continuous feature domain for decoding arbitrary-scale 2D spatial coordinates into corresponding features; the mask-guided Motion Latent Learning module, which predicts motion flow between adjacent frames to enable accurate feature warping; and the Temporal Implicit Neural Representation module, which applies 3D sampling to extract relative spatial and temporal information and decode them into RGB values. Additionally, we have curated a real-world animation video dataset to evaluate the performance of state-of-the-art STVSR methods. Experimental results demonstrate that our AnimeINR framework achieves superior performance in animation STVSR across arbitrary scales. Physical sciences/Engineering Physical sciences/Mathematics and computing 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-4603382","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":328325909,"identity":"965b8de7-e78a-4498-a44c-f6bf859d5b58","order_by":0,"name":"Qin Jiang","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Qin","middleName":"","lastName":"Jiang","suffix":""},{"id":328325910,"identity":"f015176c-bc35-4ad3-aefc-30f1f56ff01f","order_by":1,"name":"Qinglin Wang","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Qinglin","middleName":"","lastName":"Wang","suffix":""},{"id":328325911,"identity":"17ebff52-a5c4-4f7d-856d-5bffd9f12a60","order_by":2,"name":"Lihua Chi","email":"","orcid":"","institution":"Hunan GuoKe Computility Technology Co.,Ltd","correspondingAuthor":false,"prefix":"","firstName":"Lihua","middleName":"","lastName":"Chi","suffix":""},{"id":328325912,"identity":"6d75e789-e6e5-4bde-9bc9-b19188f78230","order_by":3,"name":"Zhengqiu Deng","email":"","orcid":"","institution":"Hunan Malanshan Video Advanced Technology Research Institute Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Zhengqiu","middleName":"","lastName":"Deng","suffix":""},{"id":328325913,"identity":"e6528270-f33f-4920-86b0-d40543272fe0","order_by":4,"name":"Xinhai Chen","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Xinhai","middleName":"","lastName":"Chen","suffix":""},{"id":328325914,"identity":"34ce7d8e-c435-487e-b77c-99aae292bade","order_by":5,"name":"Binbing Tang","email":"","orcid":"","institution":"Changsha Plan Technology Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Binbing","middleName":"","lastName":"Tang","suffix":""},{"id":328325915,"identity":"2a8a97a7-1ff2-422b-85c2-9ca2466362c0","order_by":6,"name":"Shaohe Lv","email":"","orcid":"","institution":"Changsha Malanshan Inv. \u0026 Dev Construction Co. Ltd","correspondingAuthor":false,"prefix":"","firstName":"Shaohe","middleName":"","lastName":"Lv","suffix":""},{"id":328325916,"identity":"f9d1946b-0ab2-4403-994b-ab9d7d9b0058","order_by":7,"name":"Jinsheng Deng","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Jinsheng","middleName":"","lastName":"Deng","suffix":""},{"id":328325917,"identity":"2416768a-4a81-4e0e-93b1-05e2258f62cd","order_by":8,"name":"Richard Zhou","email":"","orcid":"","institution":"Zhousuyue Digital Video Ltd","correspondingAuthor":false,"prefix":"","firstName":"Richard","middleName":"","lastName":"Zhou","suffix":""},{"id":328325918,"identity":"b16a6012-3fa7-48fa-8f87-c38455c04794","order_by":9,"name":"Jie Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAw0lEQVRIiWNgGAWjYBACPmYGBoMEBhsgMwGI2YjQwgbRkgZkJhOrBUIdJkULO49BwYOK83kGx/MPMHwoO8zAP7uBkMN4DAwSztwuNjjzmIFxxrnDDBJ3DhChJbHtduKGG8kMzLxthxkMJBKI0fLvHETLX+K1NByAaGEkTgtbgUHCseTEmWceGxzsOZfOI3GDgBZ+/sPbDH/U2CX2HU98+OBHmbUc/wwCWkAWGcBYB4CYh6B6IGB+QIyqUTAKRsEoGMEAAF3YPv8FMH/0AAAAAElFTkSuQmCC","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":true,"prefix":"","firstName":"Jie","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2024-06-19 05:36:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4603382/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4603382/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96251106,"identity":"1859b7b0-fd27-42f4-bf29-fc4478747461","added_by":"auto","created_at":"2025-11-19 07:39:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6370388,"visible":true,"origin":"","legend":"","description":"","filename":"TemplateforsubmissionstoScientificReports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4603382/v1_covered_9354794b-5796-4b6e-94c9-eec10affd784.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"AnimeINR: Spatio-Temporal Implicit Neural Representation for Arbitrary-Scale Animation Video Super-Resolution","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":"","lastPublishedDoi":"10.21203/rs.3.rs-4603382/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4603382/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Existing methods for video super-resolution (VSR) and video frame interpolation (VFI) primarily concentrate on devising a general pipeline suitable for open-domain videos. However, these approaches tend to overlook the inherent distinctions in animation data. Specifically, animation often features lines and smooth areas that lack textures, thereby complicating the estimation of inter-frame motions. Moreover, the exaggerated expressions common in animation introduce non-linear and highly altered motion characteristics, which can significantly limit the performance of existing methods when applied to the animation domain.In this paper, we present the first attempt to tackle the challenge of Implicit Neural Representation for achieving Space-Time Video Super-Resolution (STVSR) at arbitrary spatial and temporal scales within the animation domain. To this end, we propose a novel unified pipeline named AnimeINR, comprising three specialized modules: the Spatial Implicit Neural Representation, which defines a continuous feature domain for decoding arbitrary-scale 2D spatial coordinates into corresponding features; the mask-guided Motion Latent Learning module, which predicts motion flow between adjacent frames to enable accurate feature warping; and the Temporal Implicit Neural Representation module, which applies 3D sampling to extract relative spatial and temporal information and decode them into RGB values. Additionally, we have curated a real-world animation video dataset to evaluate the performance of state-of-the-art STVSR methods. Experimental results demonstrate that our AnimeINR framework achieves superior performance in animation STVSR across arbitrary scales.","manuscriptTitle":"AnimeINR: Spatio-Temporal Implicit Neural Representation for Arbitrary-Scale Animation Video Super-Resolution","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-18 04:20:27","doi":"10.21203/rs.3.rs-4603382/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":"1e1fff1b-1084-40b5-987d-c6708debcdf3","owner":[],"postedDate":"July 18th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":34751254,"name":"Physical sciences/Engineering"},{"id":34751255,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-11-18T08:54:20+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-18 04:20:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4603382","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4603382","identity":"rs-4603382","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}