Styled and characteristic Peking opera facial makeup synthesis with Co-training and Transfer Conditional StyleGAN2

Styled and characteristic Peking opera facial makeup synthesis with Co-training and Transfer Conditional StyleGAN2 | 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 Styled and characteristic Peking opera facial makeup synthesis with Co-training and Transfer Conditional StyleGAN2 Yinghua Shen, Oran Duan, Xiaoyu Xin, Ming Yan, Zhe Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4539085/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 14 Oct, 2024 Read the published version in npj Heritage Science → Version 1 posted 9 You are reading this latest preprint version Abstract Against the backdrop of the deep integration of culture and technology, research and practice in digitization of intangible cultural heritage has continued to deepen. However, due to the lack of data and training, it is still very difficult to apply artificial intelligence to the field of cultural heritage protection. This article integrates image generation technology into the digital protection of Peking opera facial makeup, using a self-built Peking opera facial makeup dataset. Based on the StyleGAN2 network, we propose a style generative cooperative training network Co-StyleGAN2, which integrates the Adaptive Data Augmentation to alleviate the problem of discriminator overfitting and introduces the idea of cooperative training to design a dual discriminator collaborative training network structure to stabilize the training process. We designed a Peking opera facial makeup image conditional generation network TC-StyleGAN2 which is transferred from unconditional generation network. The weights of the unconditional pre-training model are fixed, and an adaptive filtering modulation module is added to modulate the category parameters to complete the conversion from unconditional to conditional StyleGAN2 to deal with the training difficulty of conditional GANs on limited data, which suffer from severe mode collapse. The experimental results shows that the training strategy proposed in this article is better than the comparison algorithm, and the image generation quality and diversity have been improved. Digital modeling Chinese heritage Peking opera facial makeup Image generation StyleGAN2 Co-training Transfer learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 14 Oct, 2024 Read the published version in npj Heritage Science → Version 1 posted Editorial decision: Revision requested 24 Jul, 2024 Reviews received at journal 23 Jul, 2024 Reviewers agreed at journal 29 Jun, 2024 Reviewers agreed at journal 24 Jun, 2024 Reviewers agreed at journal 23 Jun, 2024 Reviewers invited by journal 23 Jun, 2024 Editor assigned by journal 18 Jun, 2024 Submission checks completed at journal 18 Jun, 2024 First submitted to journal 06 Jun, 2024 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-4539085","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":319041845,"identity":"1d2698bf-5398-4786-bbe6-026305bc61f0","order_by":0,"name":"Yinghua Shen","email":"","orcid":"","institution":"Communication University of China","correspondingAuthor":false,"prefix":"","firstName":"Yinghua","middleName":"","lastName":"Shen","suffix":""},{"id":319041846,"identity":"b275d87e-60d5-4607-bde7-8af1106e40d2","order_by":1,"name":"Oran Duan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyElEQVRIiWNgGAWjYLACHiDmhzCZSdAi2UCyFoMDxGrhlz787MHbNrs84+NnDD8wVFgnNrCfPYBXi2Rfmrnh3LbkYrMzOcYSDGfSExt48hLwajE4w2AmzdvGnLjtBo8ZA2Pb4cQGCR4DAlrYvwG11CdungHS8o8oLTwgWw4nbpAAaWkgQotkD0+Z5JxzxxNnnEkrlkg4lm7cxpODXws/D/s2iTdl1Yn97Yc3fvhQYy3bz34GvxZUkADEbCSoHwWjYBSMglGAAwAAuJU9ZgiAnQUAAAAASUVORK5CYII=","orcid":"","institution":"Communication University of China","correspondingAuthor":true,"prefix":"","firstName":"Oran","middleName":"","lastName":"Duan","suffix":""},{"id":319041847,"identity":"cfafc4e4-41d6-4bee-bb16-8612e77a57fc","order_by":2,"name":"Xiaoyu Xin","email":"","orcid":"","institution":"Communication University of China","correspondingAuthor":false,"prefix":"","firstName":"Xiaoyu","middleName":"","lastName":"Xin","suffix":""},{"id":319041848,"identity":"a51fca7c-cd3e-49c9-bf88-66c5e92caeb8","order_by":3,"name":"Ming Yan","email":"","orcid":"","institution":"Communication University of China","correspondingAuthor":false,"prefix":"","firstName":"Ming","middleName":"","lastName":"Yan","suffix":""},{"id":319041849,"identity":"b27ff843-56bb-4373-a5a2-2de67937339d","order_by":4,"name":"Zhe Li","email":"","orcid":"","institution":"Osaka University","correspondingAuthor":false,"prefix":"","firstName":"Zhe","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2024-06-06 09:51:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4539085/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4539085/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s40494-024-01463-3","type":"published","date":"2024-10-14T15:58:05+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":67149083,"identity":"a669fd4c-65d2-4c0a-a875-dc7495439b98","added_by":"auto","created_at":"2024-10-21 16:11:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1392205,"visible":true,"origin":"","legend":"","description":"","filename":"manuscriptV5TitlePageEdit.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4539085/v1_covered_0ebe9164-ecfa-4d3a-b1a7-6a27105e9235.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Styled and characteristic Peking opera facial makeup synthesis with Co-training and Transfer Conditional StyleGAN2","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"[email protected]","identity":"npj-heritage-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"hsci","sideBox":"Learn more about [Heritage Science](http://heritagesciencejournal.springeropen.com)","snPcode":"40494","submissionUrl":"https://submission.nature.com/new-submission/40494/3","title":"npj Heritage Science","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Digital modeling, Chinese heritage, Peking opera facial makeup, Image generation, StyleGAN2, Co-training, Transfer learning","lastPublishedDoi":"10.21203/rs.3.rs-4539085/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4539085/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Against the backdrop of the deep integration of culture and technology, research and practice in digitization of intangible cultural heritage has continued to deepen. However, due to the lack of data and training, it is still very difficult to apply artificial intelligence to the field of cultural heritage protection. This article integrates image generation technology into the digital protection of Peking opera facial makeup, using a self-built Peking opera facial makeup dataset. Based on the StyleGAN2 network, we propose a style generative cooperative training network Co-StyleGAN2, which integrates the Adaptive Data Augmentation to alleviate the problem of discriminator overfitting and introduces the idea of cooperative training to design a dual discriminator collaborative training network structure to stabilize the training process. We designed a Peking opera facial makeup image conditional generation network TC-StyleGAN2 which is transferred from unconditional generation network. The weights of the unconditional pre-training model are fixed, and an adaptive filtering modulation module is added to modulate the category parameters to complete the conversion from unconditional to conditional StyleGAN2 to deal with the training difficulty of conditional GANs on limited data, which suffer from severe mode collapse. The experimental results shows that the training strategy proposed in this article is better than the comparison algorithm, and the image generation quality and diversity have been improved.","manuscriptTitle":"Styled and characteristic Peking opera facial makeup synthesis with Co-training and Transfer Conditional StyleGAN2","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-26 04:52:05","doi":"10.21203/rs.3.rs-4539085/v1","editorialEvents":[{"type":"communityComments","content":1},{"type":"decision","content":"Revision requested","date":"2024-07-24T19:52:29+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-23T22:51:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"29165357325321450075556337080181429912","date":"2024-06-29T04:52:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"151301323443188525109592248078925600187","date":"2024-06-24T04:54:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"177994469007619170087125031530204464573","date":"2024-06-23T20:24:05+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-06-23T19:36:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-06-18T13:13:59+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-06-18T13:12:54+00:00","index":"","fulltext":""},{"type":"submitted","content":"Heritage Science","date":"2024-06-06T09:48:47+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-heritage-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"hsci","sideBox":"Learn more about [Heritage Science](http://heritagesciencejournal.springeropen.com)","snPcode":"40494","submissionUrl":"https://submission.nature.com/new-submission/40494/3","title":"npj Heritage Science","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"7acd3d6b-3c28-4b0a-99e5-a9655cd66aac","owner":[],"postedDate":"June 26th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-10-21T16:04:32+00:00","versionOfRecord":{"articleIdentity":"rs-4539085","link":"https://doi.org/10.1186/s40494-024-01463-3","journal":{"identity":"npj-heritage-science","isVorOnly":false,"title":"npj Heritage Science"},"publishedOn":"2024-10-14 15:58:05","publishedOnDateReadable":"October 14th, 2024"},"versionCreatedAt":"2024-06-26 04:52:05","video":"","vorDoi":"10.1186/s40494-024-01463-3","vorDoiUrl":"https://doi.org/10.1186/s40494-024-01463-3","workflowStages":[]},"version":"v1","identity":"rs-4539085","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4539085","identity":"rs-4539085","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}