{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T23:02:53Z","timestamp":1780095773013,"version":"3.54.0"},"reference-count":18,"publisher":"Walter de Gruyter GmbH","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In the rapidly developing digital media era of artificial intelligence, image editing technology has become the core support for digital content creation and information transmission. However, existing image editing technologies still face key challenges such as unstable generation quality, low interaction efficiency, and insufficient cross domain adaptability. To address these issues, a digital media image editing algorithm based on image generation and manual interaction is proposed, aiming to achieve the unity of high-quality image generation and precise control by integrating hybrid generation architecture and dynamic attention mechanism. Experiments show that the research algorithm achieves a Fr\u00e9chet Distance (FID) value of 21.3 in terms of generation quality, which is 44.8\u202f% and 53.9\u202f% higher than the control group\u2019s values of 38.8 and 46.2, respectively. In the cross domain editing task, when the intersection to union ratio index reaches 89\u202f%, the Dynamic Similarity Adjacency Matrix (DSAM) value of the research algorithm is 0.83, which is 21.4\u202f% and 18.7\u202f% higher than the control group method, respectively. In terms of system stability, the research algorithm has a misidentification rate of only 6.0\u202f% and a crash frequency of 1 after 5\u202fh of continuous operation, which is much better than the control group\u2019s 34.5\u202f% and 5 crashes. This proves that the research algorithm can effectively balance generation quality and computational efficiency, improve user interaction experience while maintaining structural consistency, and provide technical reference for professional level image editing.<\/jats:p>","DOI":"10.1515\/comp-2025-0056","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T22:18:22Z","timestamp":1780093102000},"source":"Crossref","is-referenced-by-count":0,"title":["Digital media image editing algorithm based on\u00a0image generation and\u00a0manual interaction"],"prefix":"10.1515","volume":"16","author":[{"given":"Fei","family":"Shen","sequence":"first","affiliation":[{"name":"College of Computing and Information Science , Fuzhou Institute of Technology , Fuzhou , 350506 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"374","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"2026052922314595840_j_comp-2025-0056_ref_001","doi-asserted-by":"crossref","unstructured":"M. Liu, Y. Wei, X. Wu, W. Zuo, and L. Zhang, \u201cSurvey on leveraging pre-trained generative adversarial networks for image editing and restoration,\u201d Sci. China Inf. Sci., vol.\u00a066, no.\u00a05, pp.\u00a0151101\u2013151102, 2023, https:\/\/doi.org\/10.1007\/s11432-022-3679-0.","DOI":"10.1007\/s11432-022-3679-0"},{"key":"2026052922314595840_j_comp-2025-0056_ref_002","doi-asserted-by":"crossref","unstructured":"S. Tyagi and D. Yadav, \u201cA detailed analysis of image and video forgery detection techniques,\u201d Vis. Comput., vol.\u00a039, no.\u00a03, pp.\u00a0813\u2013833, 2023, https:\/\/doi.org\/10.1007\/s00371-021-02347-4.","DOI":"10.1007\/s00371-021-02347-4"},{"key":"2026052922314595840_j_comp-2025-0056_ref_003","doi-asserted-by":"crossref","unstructured":"Y. Yu et al.., \u201cTechniques and challenges of image segmentation: A review,\u201d Electron, vol.\u00a012, no.\u00a05, pp.\u00a01199\u20131120, 2023, https:\/\/doi.org\/10.3390\/electronics12051199.","DOI":"10.3390\/electronics12051199"},{"key":"2026052922314595840_j_comp-2025-0056_ref_004","doi-asserted-by":"crossref","unstructured":"J. Maur\u00edcio, I. Domingues, and J. Bernardino, \u201cComparing vision transformers and convolutional neural networks for image classification: A literature review,\u201d Appl. Sci., vol.\u00a013, no.\u00a09, pp.\u00a05521\u20135522, 2023, https:\/\/doi.org\/10.3390\/app13095521.","DOI":"10.3390\/app13095521"},{"key":"2026052922314595840_j_comp-2025-0056_ref_005","doi-asserted-by":"crossref","unstructured":"R. Archana and P. S. E. Jeevaraj, \u201cDeep learning models for digital image processing: A review,\u201d Artif. Intell. Rev., vol.\u00a057, no.\u00a01, pp.\u00a011\u201312, 2024, https:\/\/doi.org\/10.1007\/s10462-023-10631-z.","DOI":"10.1007\/s10462-023-10631-z"},{"key":"2026052922314595840_j_comp-2025-0056_ref_006","doi-asserted-by":"crossref","unstructured":"N. E. Khalifa, M. Loey, and S. Mirjalili, \u201cA comprehensive survey of recent trends in deep learning for digital images augmentation,\u201d Artif. Intell. Rev., vol.\u00a055, no.\u00a03, pp.\u00a02351\u20132377, 2022, https:\/\/doi.org\/10.1007\/s10462-021-10066-4.","DOI":"10.1007\/s10462-021-10066-4"},{"key":"2026052922314595840_j_comp-2025-0056_ref_007","doi-asserted-by":"crossref","unstructured":"M. Elasri, O. Elharrouss, S. Al-Maadeed, and H. Tairi, \u201cImage generation: A review,\u201d Neural Process. Lett., vol.\u00a054, no.\u00a05, pp.\u00a04609\u20134646, 2022, https:\/\/doi.org\/10.1007\/s11063-022-10777-x.","DOI":"10.1007\/s11063-022-10777-x"},{"key":"2026052922314595840_j_comp-2025-0056_ref_008","doi-asserted-by":"crossref","unstructured":"H. Chefer, Y. Alaluf, Y. Vinker, L. Wolf, and D. Cohen-Or, \u201cAttend-and-excite: Attention-based semantic guidance for text-to-image diffusion models,\u201d ACM Trans. Graph. (TOG), vol.\u00a042, no.\u00a04, pp.\u00a01\u201310, 2023, https:\/\/doi.org\/10.1145\/3592116.","DOI":"10.1145\/3592116"},{"key":"2026052922314595840_j_comp-2025-0056_ref_009","doi-asserted-by":"crossref","unstructured":"D. Roich, R. Mokady, A. H. Bermano, and D. Cohen-Or, \u201cPivotal tuning for latent-based editing of real images,\u201d ACM Trans. Graph. (TOG), vol.\u00a042, no.\u00a01, pp.\u00a01\u201313, 2022, https:\/\/doi.org\/10.1145\/3544777.","DOI":"10.1145\/3544777"},{"key":"2026052922314595840_j_comp-2025-0056_ref_010","doi-asserted-by":"crossref","unstructured":"J. Sun, X. Wang, Y. Shi, L. Wang, J. Wang, and Y. Liu, \u201cIde-3d: Interactive disentangled editing for high-resolution 3d-aware portrait synthesis,\u201d ACM Trans. Graph. (TOG), vol.\u00a041, no.\u00a06, pp.\u00a01\u201310, 2022, https:\/\/doi.org\/10.1145\/3550454.3555506.","DOI":"10.1145\/3550454.3555506"},{"key":"2026052922314595840_j_comp-2025-0056_ref_011","doi-asserted-by":"crossref","unstructured":"R. Gal, M. Arar, Y. Atzmon, A. H. Bermano, G. Chechik, and D. Cohen-Or, \u201cEncoder-based domain tuning for fast personalization of text-to-image models,\u201d ACM Trans. Graph. (TOG), vol.\u00a042, no.\u00a04, pp.\u00a01\u201313, 2023, https:\/\/doi.org\/10.1145\/3592133.","DOI":"10.1145\/3592133"},{"key":"2026052922314595840_j_comp-2025-0056_ref_012","doi-asserted-by":"crossref","unstructured":"Y. Zeng, J. Fu, H. Chao, and B. Guo, \u201cAggregated contextual transformations for high-resolution image inpainting,\u201d IEEE Trans. Vis. Comput. Graph., vol.\u00a029, no.\u00a07, pp.\u00a03266\u20133280, 2022, https:\/\/doi.org\/10.1109\/tvcg.2022.3156949.","DOI":"10.1109\/TVCG.2022.3156949"},{"key":"2026052922314595840_j_comp-2025-0056_ref_013","doi-asserted-by":"crossref","unstructured":"O. Avrahami, O. Fried, and D. Lischinski, \u201cBlended latent diffusion,\u201d ACM Trans. Graph. (TOG), vol.\u00a042, no.\u00a04, pp.\u00a01\u201311, 2023, https:\/\/doi.org\/10.1145\/3592450.","DOI":"10.1145\/3592450"},{"key":"2026052922314595840_j_comp-2025-0056_ref_014","doi-asserted-by":"crossref","unstructured":"R. Gal, O. Patashnik, H. Maron, A. H. Bermano, G. Chechik, and D. Cohen-Or, \u201cStylegan-nada: Clip-guided domain adaptation of image generators,\u201d ACM Trans. Graph. (TOG), vol.\u00a041, no.\u00a04, pp.\u00a01\u201313, 2022, https:\/\/doi.org\/10.1145\/3528223.3530164.","DOI":"10.1145\/3528223.3530164"},{"key":"2026052922314595840_j_comp-2025-0056_ref_015","doi-asserted-by":"crossref","unstructured":"Y. Jiang, S. Yang, H. Qiu, W. Wu, C. C. Loy, and Z. Liu, \u201cText2human: Text-driven controllable human image generation,\u201d ACM Trans. Graph. (TOG), vol.\u00a041, no.\u00a04, pp.\u00a01\u201311, 2022, https:\/\/doi.org\/10.1145\/3528223.3530104.","DOI":"10.1145\/3528223.3530104"},{"key":"2026052922314595840_j_comp-2025-0056_ref_016","doi-asserted-by":"crossref","unstructured":"H. F. Shahzad, F. Rustam, E. S. Flores, J. Luis Vidal Mazon, I. de la Torre Diez, and I. Ashraf, \u201cA review of image processing techniques for deepfakes,\u201d Sensors, vol.\u00a022, no.\u00a012, pp.\u00a04556\u20134557, 2022, https:\/\/doi.org\/10.3390\/s22124556.","DOI":"10.3390\/s22124556"},{"key":"2026052922314595840_j_comp-2025-0056_ref_017","doi-asserted-by":"crossref","unstructured":"Z. Xing et al.., \u201cA survey on video diffusion models,\u201d ACM Comput. Surv., vol.\u00a057, no.\u00a02, pp.\u00a01\u201342, 2024, https:\/\/doi.org\/10.1145\/3696415.","DOI":"10.1145\/3696415"},{"key":"2026052922314595840_j_comp-2025-0056_ref_018","doi-asserted-by":"crossref","unstructured":"K. Man and J. Chahl, \u201cA review of synthetic image data and its use in computer vision,\u201d J. Imaging, vol.\u00a08, no.\u00a011, pp.\u00a0310\u2013311, 2022, https:\/\/doi.org\/10.3390\/jimaging8110310.","DOI":"10.3390\/jimaging8110310"}],"container-title":["Open Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/comp-2025-0056\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/comp-2025-0056\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T22:31:54Z","timestamp":1780093914000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/comp-2025-0056\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":18,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,6,1]]},"published-print":{"date-parts":[[2026,1,23]]}},"alternative-id":["10.1515\/comp-2025-0056"],"URL":"https:\/\/doi.org\/10.1515\/comp-2025-0056","relation":{},"ISSN":["2299-1093"],"issn-type":[{"value":"2299-1093","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,1]]},"article-number":"20250056"}}