{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:40:12Z","timestamp":1777696812613,"version":"3.51.4"},"reference-count":31,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:00:00Z","timestamp":1731888000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Intelligent Decision Technologies"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>In film and television production, efficient and precise image processing is vital for achieving realistic visual effects. Therefore, exploring and applying advanced image processing technologies has become an essential method for elevating the production quality of film and television projects. This work investigates the application of artificial intelligence (AI) technology in the processing and production of animated images in film and television scenarios. By comparing the performance of standard Generative Adversarial Network (GAN), DenseNet, and CycleGAN models under different noise conditions, it is found that CycleGAN performs the best in image denoising and detail restoration. Experimental results demonstrate that CycleGAN achieves a Peak Signal-to-noise Ratio (PSNR) of 30.1\u2005dB and a Structural Similarity Index Measure (SSIM) of 0.88 under Gaussian noise conditions. Moreover, CycleGAN achieves a PSNR of 29.5\u2005dB and an SSIM of 0.85 under salt-and-pepper noise conditions. It outperforms the other models in both conditions. Additionally, CycleGAN's mean absolute error is significantly lower than that of the other models. This work demonstrates that CycleGAN can more effectively handle complex noise and generate high-quality images under unsupervised learning conditions. These findings provide new directions for future image processing research and offer important references for model selection in practical applications. This work not only offers new perspectives on the development of animation image processing technology but also establishes a theoretical foundation for applying advanced AI techniques in film and television production. Through comparative analysis of various deep learning models, this work highlights the superior performance of CycleGAN under complex noise conditions. This advancement not only drives progress in image processing technology but also provides effective solutions for efficient production and quality enhancement of future film and television works.<\/jats:p>","DOI":"10.1177\/18724981241297464","type":"journal-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T08:05:11Z","timestamp":1743062711000},"page":"118-131","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Film image processing and production based on high-performance calculation"],"prefix":"10.1177","volume":"19","author":[{"given":"Xin","family":"Liu","sequence":"first","affiliation":[{"name":"School of Art and Design, Lanzhou Jiaotong University, Lanzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2024,11,18]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"30","article-title":"Artificial intelligence and film and television content production: current situation and future","volume":"216","author":"Zhang W","year":"2019","unstructured":"Zhang W. Artificial intelligence and film and television content production: current situation and future. Mod Telev Technol 2019; 216: 30\u201333.","journal-title":"Mod Telev Technol"},{"key":"e_1_3_2_3_2","first-page":"84","article-title":"From going out of the screen to entering the film \u2013 the history and current situation of 3D film technology","volume":"000","author":"Che L","year":"2019","unstructured":"Che L. From going out of the screen to entering the film \u2013 the history and current situation of 3D film technology. Contemp Film 2019; 000: 84\u201391.","journal-title":"Contemp Film"},{"key":"e_1_3_2_4_2","first-page":"121","article-title":"On the application of digital media art in film and animation","volume":"482","author":"Han X","year":"2020","unstructured":"Han X. On the application of digital media art in film and animation. Rep Obs 2020; 482: 121\u2013121.","journal-title":"Rep Obs"},{"key":"e_1_3_2_5_2","first-page":"2","article-title":"Progress and application of computer image processing technology in medical imaging","volume":"4","author":"Li P","year":"2020","unstructured":"Li P, Jian W, Shaoxin Y. Progress and application of computer image processing technology in medical imaging. Image Res Med Appl 2020; 4: 2\u20135.","journal-title":"Image Res Med Appl"},{"key":"e_1_3_2_6_2","first-page":"28","article-title":"5g And artificial intelligence are the main battlefield of industrial transformation","volume":"000","author":"Huang Q","year":"2019","unstructured":"Huang Q, Jun H. 5g And artificial intelligence are the main battlefield of industrial transformation. New Chongqing 2019; 000: 28\u201330.","journal-title":"New Chongqing"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cej.2023.143272"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40820-023-01203-5"},{"key":"e_1_3_2_9_2","first-page":"76","article-title":"Inverse kinematics for A 3-R robot using artificial neural network and modified particle swarm optimization","volume":"101","author":"Samta S","year":"2020","unstructured":"Samta S, Parvez Y, Chauhan NR. Inverse kinematics for A 3-R robot using artificial neural network and modified particle swarm optimization. J Inst Eng (India): Ser C: Mech Prod Aerosp Mar Eng 2020; 101: 76\u201389.","journal-title":"J Inst Eng (India): Ser C: Mech Prod Aerosp Mar Eng"},{"key":"e_1_3_2_10_2","first-page":"324","article-title":"Prediction of tropical cyclone generation frequency in the northwest pacific using artificial neural network model","volume":"24","author":"Hai Y","year":"2019","unstructured":"Hai Y, Guanghua C. Prediction of tropical cyclone generation frequency in the northwest pacific using artificial neural network model. Clim Environ Res 2019; 24: 324\u2013332.","journal-title":"Clim Environ Res"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42600-020-00046-y"},{"key":"e_1_3_2_12_2","first-page":"203","article-title":"Application of lightweight Gan super-resolution image reconstruction algorithm in real-time face recognition","volume":"41","author":"Zeng F","year":"2020","unstructured":"Zeng F, Lei Z, Yan Z, et\u00a0al. Application of lightweight Gan super-resolution image reconstruction algorithm in real-time face recognition. Small Microcomput Syst 2020; 41: 203\u2013208.","journal-title":"Small Microcomput Syst"},{"key":"e_1_3_2_13_2","first-page":"31","article-title":"Why imaging data alone is not enough: aI-based integration of imaging, omics, and clinical data","volume":"46","author":"Andreas H","year":"2019","unstructured":"Andreas H, Haibe-Kains B, Jurisica I. Why imaging data alone is not enough: aI-based integration of imaging, omics, and clinical data. Eur J Nucl Med Mol Imaging 2019; 46: 31\u201335.","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"e_1_3_2_14_2","first-page":"7","article-title":"Research on low illumination image enhancement algorithm based on GaN","volume":"48","author":"Huang L","year":"2020","unstructured":"Huang L, Shaozhen y. Research on low illumination image enhancement algorithm based on GaN. J Fuzhou Univ: Nat Sci Ed 2020; 48: 7\u20139.","journal-title":"J Fuzhou Univ: Nat Sci Ed"},{"key":"e_1_3_2_15_2","first-page":"70","article-title":"Preliminary study on COVID-19 recognition in high resolution CT based on deep learning algorithm model","volume":"562","author":"Yang S","year":"2020","unstructured":"Yang S, Fei S. Preliminary study on COVID-19 recognition in high resolution CT based on deep learning algorithm model. Shanghai Pharm 2020; 562: 70\u201371.","journal-title":"Shanghai Pharm"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/s11036-019-01387-4","article-title":"Efficient machine learning model for movie recommender systems using multi-cloud environment","volume":"24","author":"Indira K","year":"2019","unstructured":"Indira K, Kavithadevi MK. Efficient machine learning model for movie recommender systems using multi-cloud environment. Mobile Networks Appl: J Spec issues Mobility Syst Users Data Comput 2019; 24: 63\u201369.","journal-title":"Mobile Networks Appl: J Spec issues Mobility Syst Users Data Comput"},{"key":"e_1_3_2_17_2","first-page":"100","article-title":"Optimized selection method of cycle consistent loss coefficient of cycligan in image generation with different texture complexity","volume":"046","author":"Xu Q","year":"2019","unstructured":"Xu Q, Shangping Z, Kaizhi C, et\u00a0al. Optimized selection method of cycle consistent loss coefficient of cycligan in image generation with different texture complexity. Comput Sci 2019; 046: 100\u2013106.","journal-title":"Comput Sci"},{"key":"e_1_3_2_18_2","first-page":"45","article-title":"Multi-label movie genre detection from a movie poster using knowledge transfer learning","volume":"5","author":"Kaushil K","year":"2019","unstructured":"Kaushil K, Patel Y, Shah M. Multi-label movie genre detection from a movie poster using knowledge transfer learning. Augment Hum Res 2019; 5: 45\u201350.","journal-title":"Augment Hum Res"},{"key":"e_1_3_2_19_2","first-page":"24","article-title":"Digital movies tracking using scene-based watermarking system","volume":"62","author":"Dolley S","year":"2019","unstructured":"Dolley S, Sharma M. Digital movies tracking using scene-based watermarking system. Radioelectron Commun Syst 2019; 62: 24\u201328.","journal-title":"Radioelectron Commun Syst"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12517-021-07742-8"},{"key":"e_1_3_2_21_2","first-page":"27","article-title":"Artificial intelligence (AI) \u2013 a revolutionary new driving force for film and television creation","volume":"000","author":"Ma P","year":"2019","unstructured":"Ma P. Artificial intelligence (AI) \u2013 a revolutionary new driving force for film and television creation. Mod Film Technol 2019; 000: 27\u201330.","journal-title":"Mod Film Technol"},{"key":"e_1_3_2_22_2","first-page":"70","article-title":"NLME: a nonlinear motion estimation-based compression method for animated mesh sequence","volume":"36","author":"Mohammadalip H","year":"2020","unstructured":"Mohammadalip H, Ebrahimnezhad H. NLME: a nonlinear motion estimation-based compression method for animated mesh sequence. Visual Comput 2020; 36: 70\u201375.","journal-title":"Visual Comput"},{"key":"e_1_3_2_23_2","first-page":"83","article-title":"Design and research of game trading platform based on AI technology","volume":"000","author":"He Q","year":"2020","unstructured":"He Q, Yongwei W, Chengbin L, et\u00a0al. Design and research of game trading platform based on AI technology. Inf Commun 2020; 000: 83\u201384, 86.","journal-title":"Inf Commun"},{"key":"e_1_3_2_24_2","first-page":"40","article-title":"Awesome, China \u2013 the 70th anniversary of the founding of the people's Republic of China","volume":"000","author":"Ma Y","year":"2019","unstructured":"Ma Y and directed by Yu Z. Awesome, China \u2013 the 70th anniversary of the founding of the people's Republic of China. Primary Sch Stud Reading World 2019; 000: 40\u201340.","journal-title":"Primary Sch Stud Reading World"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12891-019-2457-8"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00436-5"},{"key":"e_1_3_2_27_2","first-page":"1","article-title":"Audio visual expression of classic films \u2013 taking the road angel as an example","volume":"003","author":"Ma W","year":"2020","unstructured":"Ma W. Audio visual expression of classic films \u2013 taking the road angel as an example. Young Writer 2020; 003: 1\u20133.","journal-title":"Young Writer"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSSC.2019.2951654"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.nanoen.2023.108354"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.carbon.2023.03.067"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3061062"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.3389\/frsip.2021.812193"}],"container-title":["Intelligent Decision Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18724981241297464","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/18724981241297464","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18724981241297464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:21:02Z","timestamp":1777454462000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/18724981241297464"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,18]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1177\/18724981241297464"],"URL":"https:\/\/doi.org\/10.1177\/18724981241297464","relation":{},"ISSN":["1872-4981","1875-8843"],"issn-type":[{"value":"1872-4981","type":"print"},{"value":"1875-8843","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,18]]}}}