{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:08:20Z","timestamp":1790273300670,"version":"4.1.0"},"reference-count":30,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>To improve the quality and style consistency of cartoon generation in animated image scenes, this study proposes an image cartoon generation model that integrates improved generative adversarial networks and preservation networks. The model achieves collaborative optimization of local details, global structure, and diverse styles in images by introducing a multi-style mapping module, a multi-head discriminator, a Euclidean distance decay attention mechanism, and a thin plate spline geometric consistency module. This study employs two publicly available scene image datasets, setting up four typical simulation testing environments and comparing them with three mainstream image generation methods. The experiment showed that the model performed well in key indicators such as generation quality, processing efficiency, and structural preservation, with a peak signal-to-noise ratio of up to 29.2 dB, the Fr\u00e9chet Inception Distance was 35.2, and a processing efficiency of 8.0 FPS. In addition, the generated cartoon image had a structural similarity index of 0.89 with the original image, and the running memory usage was controlled within 3.9GB. The image generation model has overcome the style drift and geometric distortion in existing animated cartoonization, providing a high-fidelity and low-cost automated solution for film and television production, game development, and digital content creation.<\/jats:p>","DOI":"10.1371\/journal.pone.0347014","type":"journal-article","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:34:13Z","timestamp":1790271253000},"page":"e0347014","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cartoon style generation of animated image scenes based on improved GAN and RetNet"],"prefix":"10.1371","volume":"21","author":[{"given":"Zhenyao","family":"Jin","sequence":"first","affiliation":[{"name":"Graduate School, Cheongju University","place":["Heongju, Korea"]},{"name":"School of Design and Art, Shandong Huayu University of Technology","place":["Dezhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9356-658X","authenticated-orcid":true,"given":"Lei","family":"Yang","sequence":"additional","affiliation":[{"name":"Graduate School, Cheongju University","place":["Heongju, Korea"]},{"name":"School of Design and Art, Shandong Huayu University of Technology","place":["Dezhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,24]]},"reference":[{"issue":"1","key":"pone.0347014.ref001","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1007\/s11042-023-15930-9","article-title":"Optimized deep learning vision system for human action recognition from drone images","volume":"83","author":"H Samma","year":"2023","journal-title":"Multimed Tools Appl"},{"issue":"6","key":"pone.0347014.ref002","doi-asserted-by":"crossref","first-page":"3971","DOI":"10.1007\/s00371-024-03404-4","article-title":"Attention mechanism-based generative adversarial networks for image cartoonization","volume":"40","author":"W Zhao","year":"2024","journal-title":"Vis Comput"},{"issue":"3","key":"pone.0347014.ref003","first-page":"170","article-title":"Machine learning methodology for identifying vehicles using image processing","author":"M Hasanvand","year":"2023","journal-title":"AIA"},{"issue":"9","key":"pone.0347014.ref004","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/s10462-024-10897-x","article-title":"GAN based augmentation using a hybrid loss function for dermoscopy images","volume":"57","author":"E Goceri","year":"2024","journal-title":"Artif Intell Rev"},{"issue":"12","key":"pone.0347014.ref005","first-page":"9181","article-title":"NeuroGAN: image reconstruction from EEG signals via an attention-based GAN","volume":"35","author":"R Mishra","year":"2023","journal-title":"Neural Comput Appl"},{"issue":"30","key":"pone.0347014.ref006","doi-asserted-by":"crossref","first-page":"47751","DOI":"10.1007\/s11042-023-15313-0","article-title":"DGCA: high resolution image inpainting via DR-GAN and contextual attention","volume":"82","author":"Y Chen","year":"2023","journal-title":"Multimed Tools Appl"},{"key":"pone.0347014.ref007","first-page":"113303","article-title":"Expo-GAN: A style transfer generative adversarial network for exhibition hall design based on optimized cyclic and neural architecture search","volume":"83","author":"Q Xie","year":"2025","journal-title":"Comput Mater Contin"},{"key":"pone.0347014.ref008","doi-asserted-by":"crossref","first-page":"113303","DOI":"10.1016\/j.asoc.2025.113303","article-title":"Generative adversarial network based on CNN classifier predicted scores for image style transfer","volume":"178","author":"LM Gladence","year":"2025","journal-title":"Applied Soft Computing"},{"key":"pone.0347014.ref009","doi-asserted-by":"crossref","first-page":"110164","DOI":"10.1016\/j.compeleceng.2025.110164","article-title":"GAL-GAN: Global styles and local high-frequency learning based generative adversarial network for image cartoonization","volume":"123","author":"L Li","year":"2025","journal-title":"Comput Electr Eng"},{"issue":"1","key":"pone.0347014.ref010","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1186\/s40662-025-00426-4","article-title":"Associations between RetNet gene polymorphisms and the efficacy of orthokeratology for myopia control: a retrospective clinical study","volume":"12","author":"R Xia","year":"2025","journal-title":"Eye Vis (Lond)"},{"key":"pone.0347014.ref011","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1007\/s00530-025-01843-0","article-title":"MSCC-RetNet: A multi-scale color corrected retinex network for underwater image enhancement","author":"B Sun","year":"2025","journal-title":"Multimed. Syst"},{"key":"pone.0347014.ref012","doi-asserted-by":"crossref","first-page":"108626","DOI":"10.1016\/j.compbiomed.2024.108626","article-title":"EEGDiR: Electroencephalogram denoising network for temporal information storage and global modeling through Retentive Network","volume":"177","author":"B Wang","year":"2024","journal-title":"Comput Biol Med"},{"key":"pone.0347014.ref013","doi-asserted-by":"crossref","unstructured":"Qiu Y, Zhang K, Wang C, Luo W, Li H, Jin Z. MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), 2023. 12756\u201367. https:\/\/doi.org\/10.1109\/iccv51070.2023.01176","DOI":"10.1109\/ICCV51070.2023.01176"},{"key":"pone.0347014.ref014","doi-asserted-by":"crossref","first-page":"110625","DOI":"10.1016\/j.patcog.2024.110625","article-title":"Toward a deeper understanding: RetNet viewed through convolution.","volume":"155","author":"C Li","year":"2024","journal-title":"Pattern Recognit"},{"key":"pone.0347014.ref015","doi-asserted-by":"crossref","first-page":"169","DOI":"10.62762\/TETAI.2025.549572","article-title":"The Accountability Paradox: How Generative AI Challenges Our Notions of Responsibility.","volume":"2","author":"Y Shao","year":"2025","journal-title":"ICCK Transactions on Emerging Topics in Artificial Intelligence"},{"key":"pone.0347014.ref016","doi-asserted-by":"crossref","first-page":"4","DOI":"10.62762\/FEIR.2024.649562","article-title":"Exploration of Course Resources and Modes under Generative Artificial Intelligence.","volume":"1","author":"H Zhang","year":"2025","journal-title":"Frontiers in Educational Innovation and Research"},{"issue":"4","key":"pone.0347014.ref017","doi-asserted-by":"crossref","first-page":"11088","DOI":"10.1109\/TCE.2025.3625642","article-title":"Enhancing Privacy-Preserved Iris Recognition in Consumer Electronics: A Soft Actor-Critic and GAN-Based Digital Forensic Framework With Bayesian Hyperparameter Optimization","volume":"71","author":"J Yang","year":"2025","journal-title":"IEEE Trans Consumer Electron"},{"issue":"1","key":"pone.0347014.ref018","doi-asserted-by":"crossref","first-page":"39","DOI":"10.60087\/jaigs.v5i1.162","article-title":"GPU-Optimized Image Processing and Generation Based on Deep Learning and Computer Vision","volume":"5","author":"Y Lin","year":"2024","journal-title":"JAIGS"},{"issue":"2","key":"pone.0347014.ref019","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1007\/s11242-023-01913-9","article-title":"Towards Large-Scale DRP Simulations: Generation of Large Super-Resolution images and Extraction of Large Pore Network Models","volume":"147","author":"M Regaieg","year":"2023","journal-title":"Transp Porous Med"},{"issue":"8","key":"pone.0347014.ref020","doi-asserted-by":"crossref","first-page":"8526","DOI":"10.1609\/aaai.v38i8.28696","article-title":"AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model","volume":"38","author":"T Hu","year":"2024","journal-title":"AAAI"},{"issue":"15","key":"pone.0347014.ref021","doi-asserted-by":"crossref","first-page":"2109","DOI":"10.1111\/mice.12970","article-title":"Transformer\u2010optimized generation, detection, and tracking network for images with drainage pipeline defects","volume":"38","author":"D Ma","year":"2023","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"issue":"8","key":"pone.0347014.ref022","doi-asserted-by":"crossref","first-page":"1979","DOI":"10.14778\/3594512.3594527","article-title":"Towards Efficient Index Construction and Approximate Nearest Neighbor Search in High-Dimensional Spaces","volume":"16","author":"X Zhao","year":"2023","journal-title":"Proc VLDB Endow"},{"issue":"1","key":"pone.0347014.ref023","doi-asserted-by":"crossref","first-page":"53","DOI":"10.24002\/jarina.v2i1.6662","article-title":"A Review of AI Image Generator: Influences, Challenges, and Future Prospects for Architectural Field","volume":"2","author":"EVP Beyan","year":"2023","journal-title":"JARINA"},{"issue":"11","key":"pone.0347014.ref024","doi-asserted-by":"crossref","first-page":"5501","DOI":"10.1016\/j.asr.2023.03.022","article-title":"Generation of fused visible and thermal-infrared images for uncooperative spacecraft proximity navigation","volume":"73","author":"GL Civardi","year":"2024","journal-title":"Advances in Space Research"},{"issue":"1","key":"pone.0347014.ref025","doi-asserted-by":"crossref","first-page":"50","DOI":"10.60087\/jaigs.v5i1.163","article-title":"Image Processing and Optimization Using Deep Learning-Based Generative Adversarial Networks (GANs)","volume":"5","author":"Y Zhang","year":"2024","journal-title":"JAIGS"},{"key":"pone.0347014.ref026","doi-asserted-by":"crossref","first-page":"6271","DOI":"10.1007\/s11042-022-13596-3","article-title":"Neural style transfer for image steganography and destylization with supervised image to image translation","volume":"82","author":"M Garg","year":"2023","journal-title":"Multimed. Tools Appl"},{"issue":"4","key":"pone.0347014.ref027","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1016\/j.vrih.2023.06.010","article-title":"Generating animatable 3D cartoon faces from single portraits","volume":"6","author":"C Pan","year":"2024","journal-title":"Virtual Reality & Intelligent Hardware"},{"issue":"2","key":"pone.0347014.ref028","doi-asserted-by":"crossref","first-page":"506","DOI":"10.26599\/TST.2023.9010028","article-title":"Synthesis, Style Editing, and Animation of 3D Cartoon Face","volume":"29","author":"M Guo","year":"2024","journal-title":"Tsinghua Sci Technol"},{"issue":"4","key":"pone.0347014.ref029","first-page":"73","article-title":"A study on the improvement of CartoonGAN image quality for nonlinear edge reinforcement using SRCNN quality enhancement processing","author":"HW Lee","year":"2024","journal-title":"J. Korea Comput. Graph. Soc"},{"issue":"3","key":"pone.0347014.ref030","doi-asserted-by":"crossref","first-page":"1902","DOI":"10.1109\/JBHI.2025.3631973","article-title":"DGAN-MPCC: A Novel Dual-GAN Enhanced Multi-Positive Contrastive Clustering Method for Omics Data","volume":"30","author":"J Wang","year":"2026","journal-title":"IEEE J Biomed Health Inform"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0347014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:34:25Z","timestamp":1790271265000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0347014"}},"subtitle":[],"editor":[{"given":"Xiaowei","family":"Li","sequence":"first","affiliation":[{"name":"Sichuan University","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,24]]},"references-count":30,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0347014","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,24]]}}}