{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:33:00Z","timestamp":1777887180380,"version":"3.51.4"},"reference-count":77,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0108003"],"award-info":[{"award-number":["2020AAA0108003"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["GG-2024-01-02"],"award-info":[{"award-number":["GG-2024-01-02"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62277011"],"award-info":[{"award-number":["62277011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.cviu.2026.104673","type":"journal-article","created":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T16:30:31Z","timestamp":1770481831000},"page":"104673","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["OSTE: Omni-Scene Text Editing with Latent Decoupling"],"prefix":"10.1016","volume":"265","author":[{"given":"Tonghua","family":"Su","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7252-4207","authenticated-orcid":false,"given":"Fuxiang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2270-3378","authenticated-orcid":false,"given":"Donglin","family":"Di","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongjie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7892-8242","authenticated-orcid":false,"given":"Songze","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangqian","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104673_b1","series-title":"ICCV","first-page":"4715","article-title":"What is wrong with scene text recognition model comparisons? dataset and model analysis","author":"Baek","year":"2019"},{"key":"10.1016\/j.cviu.2026.104673_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2021.103347","article-title":"Progressive editing with stacked generative adversarial network for multiple facial attribute editing","volume":"217","author":"Chan","year":"2022","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104673_b3","series-title":"NeurIPS","article-title":"TextDiffuser: Diffusion models as text painters","volume":"36","author":"Chen","year":"2024"},{"key":"10.1016\/j.cviu.2026.104673_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2023.103883","article-title":"MFMAM: Image inpainting via multi-scale feature module with attention module","volume":"238","author":"Chen","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104673_b5","series-title":"NeurIPS","article-title":"DiffUTE: Universal text editing diffusion model","author":"Chen","year":"2023"},{"key":"10.1016\/j.cviu.2026.104673_b6","series-title":"CVPR","first-page":"3671","article-title":"Navigating the GAN parameter space for semantic image editing","author":"Cherepkov","year":"2021"},{"key":"10.1016\/j.cviu.2026.104673_b7","series-title":"CVPR","first-page":"3671","article-title":"Navigating the GAN parameter space for semantic image editing","author":"Cherepkov","year":"2021"},{"key":"10.1016\/j.cviu.2026.104673_b8","series-title":"NeurIPS","first-page":"4479","article-title":"Fast Fourier convolution","volume":"33","author":"Chi","year":"2020"},{"key":"10.1016\/j.cviu.2026.104673_b9","series-title":"ICDAR","first-page":"1571","article-title":"ICDAR2019 robust reading challenge on arbitrary-shaped text-rrc-art","author":"Chng","year":"2019"},{"key":"10.1016\/j.cviu.2026.104673_b10","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2023.3261988","article-title":"Diffusion models in vision: A survey","author":"Croitoru","year":"2023","journal-title":"TPAMI"},{"key":"10.1016\/j.cviu.2026.104673_b11","series-title":"Nano Banana (Gemini 2.5 Flash image) \u2013 AI image generation & editing model","author":"DeepMind","year":"2025"},{"key":"10.1016\/j.cviu.2026.104673_b12","series-title":"ICCV","first-page":"12124","article-title":"DH-FaceVid-1K: A large-scale high-quality dataset for face video generation","author":"Di","year":"2025"},{"key":"10.1016\/j.cviu.2026.104673_b13","series-title":"ICLR","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.cviu.2026.104673_b14","series-title":"CVPR","first-page":"25518","article-title":"Manta: A large-scale multi-view and visual-text anomaly detection dataset for tiny objects","author":"Fan","year":"2025"},{"key":"10.1016\/j.cviu.2026.104673_b15","series-title":"Ditalker: A unified dit-based framework for high-quality and speaking styles controllable portrait animation","author":"Feng","year":"2025"},{"key":"10.1016\/j.cviu.2026.104673_b16","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104673_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2021.103205","article-title":"Image style disentangling for instance-level facial attribute transfer","volume":"207","author":"Guo","year":"2021","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104673_b18","series-title":"CVPR","article-title":"Synthetic data for text localisation in natural images","author":"Gupta","year":"2016"},{"key":"10.1016\/j.cviu.2026.104673_b19","series-title":"CVPR","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.cviu.2026.104673_b20","series-title":"NeurIPS","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017"},{"key":"10.1016\/j.cviu.2026.104673_b21","series-title":"Lecture 6e: RMSProp \u2014 Divide the learning rate by a running average of its recent magnitude","author":"Hinton","year":"2012"},{"key":"10.1016\/j.cviu.2026.104673_b22","series-title":"NeurIPS","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020"},{"key":"10.1016\/j.cviu.2026.104673_b23","series-title":"ICCV","first-page":"1501","article-title":"Arbitrary style transfer in real-time with adaptive instance normalization","author":"Huang","year":"2017"},{"key":"10.1016\/j.cviu.2026.104673_b24","series-title":"ICDAR","first-page":"1516","article-title":"ICDAR2019 competition on scanned receipt ocr and information extraction","author":"Huang","year":"2019"},{"issue":"4","key":"10.1016\/j.cviu.2026.104673_b25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073659","article-title":"Globally and locally consistent image completion","volume":"36","author":"Iizuka","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.cviu.2026.104673_b26","series-title":"CVPR","first-page":"1125","article-title":"Image-to-image translation with conditional adversarial networks","author":"Isola","year":"2017"},{"key":"10.1016\/j.cviu.2026.104673_b27","article-title":"Improving diffusion models for scene text editing with dual encoders","author":"Ji","year":"2024","journal-title":"TMLR"},{"key":"10.1016\/j.cviu.2026.104673_b28","series-title":"ECCV","first-page":"694","article-title":"Perceptual losses for real-time style transfer and super-resolution","author":"Johnson","year":"2016"},{"key":"10.1016\/j.cviu.2026.104673_b29","series-title":"ICDAR","first-page":"1156","article-title":"ICDAR 2015 competition on robust reading","author":"Karatzas","year":"2015"},{"key":"10.1016\/j.cviu.2026.104673_b30","series-title":"CVPR","first-page":"4401","article-title":"A style-based generator architecture for generative adversarial networks","author":"Karras","year":"2019"},{"issue":"5","key":"10.1016\/j.cviu.2026.104673_b31","first-page":"3152","article-title":"Text region conditional generative adversarial network for text concealment in the wild","volume":"32","author":"Keserwani","year":"2021","journal-title":"TCSVT"},{"issue":"7","key":"10.1016\/j.cviu.2026.104673_b32","doi-asserted-by":"crossref","first-page":"9122","DOI":"10.1109\/TPAMI.2023.3239736","article-title":"TextStyleBrush: Transfer of text aesthetics from a single example","volume":"45","author":"Krishnan","year":"2023","journal-title":"TPAMI"},{"key":"10.1016\/j.cviu.2026.104673_b33","series-title":"ECCV","first-page":"457","article-title":"The surprisingly straightforward scene text removal method with gated attention and region of interest generation: A comprehensive prominent model analysis","author":"Lee","year":"2022"},{"key":"10.1016\/j.cviu.2026.104673_b34","series-title":"RewriteNet: Realistic scene text image generation via editing text in real-world image","author":"Lee","year":"2021"},{"key":"10.1016\/j.cviu.2026.104673_b35","series-title":"NeurIPS","first-page":"16331","article-title":"EditGAN: High-precision semantic image editing","author":"Ling","year":"2021"},{"key":"10.1016\/j.cviu.2026.104673_b36","article-title":"Progressive reverse attention network for image inpainting detection and localization","author":"Liu","year":"2025","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104673_b37","first-page":"8760","article-title":"EraseNet: End-to-end text removal in the wild","volume":"29","author":"Liu","year":"2020","journal-title":"TIP"},{"issue":"5","key":"10.1016\/j.cviu.2026.104673_b38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11432-022-3679-0","article-title":"Survey on leveraging pre-trained generative adversarial networks for image editing and restoration","volume":"66","author":"Liu","year":"2023","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.cviu.2026.104673_b39","series-title":"Adams bashforth moulton solver for inversion and editing in rectified flow","author":"Ma","year":"2025"},{"issue":"11","key":"10.1016\/j.cviu.2026.104673_b40","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van\u00a0der Maaten","year":"2008","journal-title":"JMLR"},{"key":"10.1016\/j.cviu.2026.104673_b41","series-title":"ICLR","article-title":"Spectral normalization for generative adversarial networks","author":"Miyato","year":"2019"},{"key":"10.1016\/j.cviu.2026.104673_b42","series-title":"ICDAR","first-page":"1582","article-title":"ICDAR2019 robust reading challenge on multi-lingual scene text detection and recognition\u2014RRC-MLT-2019","author":"Nayef","year":"2019"},{"key":"10.1016\/j.cviu.2026.104673_b43","series-title":"ICML","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","author":"Nichol","year":"2021"},{"key":"10.1016\/j.cviu.2026.104673_b44","series-title":"GPT-image-1.5 API","author":"OpenAI","year":"2025"},{"key":"10.1016\/j.cviu.2026.104673_b45","series-title":"CVPR","first-page":"2536","article-title":"Context encoders: Feature learning by inpainting","author":"Pathak","year":"2016"},{"key":"10.1016\/j.cviu.2026.104673_b46","series-title":"AAAI","first-page":"2119","article-title":"Exploring stroke-level modifications for scene text editing","volume":"37","author":"Qu","year":"2023"},{"key":"10.1016\/j.cviu.2026.104673_b47","series-title":"AAAI","first-page":"2119","article-title":"Exploring stroke-level modifications for scene text editing","volume":"37","author":"Qu","year":"2023"},{"key":"10.1016\/j.cviu.2026.104673_b48","series-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"10.1016\/j.cviu.2026.104673_b49","series-title":"CVPR","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.cviu.2026.104673_b50","series-title":"CVPR","first-page":"13228","article-title":"STEFANN: scene text editor using font adaptive neural network","author":"Roy","year":"2020"},{"key":"10.1016\/j.cviu.2026.104673_b51","series-title":"ACM SIGGRAPH","first-page":"1","article-title":"Palette: Image-to-image diffusion models","author":"Saharia","year":"2022"},{"key":"10.1016\/j.cviu.2026.104673_b52","series-title":"NeurIPS","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022"},{"key":"10.1016\/j.cviu.2026.104673_b53","series-title":"WACV","first-page":"5202","article-title":"On manipulating scene text in the wild with diffusion models","author":"Santoso","year":"2024"},{"key":"10.1016\/j.cviu.2026.104673_b54","series-title":"CVPR","first-page":"9243","article-title":"Interpreting the latent space of GANs for semantic face editing","author":"Shen","year":"2020"},{"key":"10.1016\/j.cviu.2026.104673_b55","series-title":"CVPR","first-page":"1532","article-title":"Closed-form factorization of latent semantics in GANs","author":"Shen","year":"2021"},{"key":"10.1016\/j.cviu.2026.104673_b56","series-title":"ICCV","first-page":"1076","article-title":"De-rendering stylized texts","author":"Shimoda","year":"2021"},{"key":"10.1016\/j.cviu.2026.104673_b57","series-title":"Type-r: Automatically retouching typos for text-to-image generation","author":"Shimoda","year":"2024"},{"key":"10.1016\/j.cviu.2026.104673_b58","series-title":"ICLR","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015"},{"key":"10.1016\/j.cviu.2026.104673_b59","series-title":"ICML","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015"},{"key":"10.1016\/j.cviu.2026.104673_b60","series-title":"ACM MM","first-page":"5020","article-title":"Llapa: A vision-language model framework for counterfactual-aware procedural planning","author":"Sun","year":"2025"},{"key":"10.1016\/j.cviu.2026.104673_b61","series-title":"ICDAR","first-page":"1557","article-title":"ICDAR2019 competition on large-scale street view text with partial labeling-RRC-LSVT","author":"Sun","year":"2019"},{"key":"10.1016\/j.cviu.2026.104673_b62","series-title":"WACV","first-page":"2149","article-title":"Resolution-robust large mask inpainting with Fourier convolutions","author":"Suvorov","year":"2022"},{"key":"10.1016\/j.cviu.2026.104673_b63","series-title":"ICLR","article-title":"AnyText: Multilingual visual text generation and editing","author":"Tuo","year":"2024"},{"key":"10.1016\/j.cviu.2026.104673_b64","series-title":"ICPR","article-title":"Show me the world in my language: Establishing the first baseline for scene-text to scene-text translation","author":"Vaidya","year":"2024"},{"key":"10.1016\/j.cviu.2026.104673_b65","series-title":"Coco-text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016"},{"key":"10.1016\/j.cviu.2026.104673_b66","series-title":"ECCV","first-page":"170","article-title":"StyleGAN2 distillation for feed-forward image manipulation","author":"Viazovetskyi","year":"2020"},{"key":"10.1016\/j.cviu.2026.104673_b67","series-title":"CVPR","first-page":"2747","article-title":"Bringing old photos back to life","author":"Wan","year":"2020"},{"key":"10.1016\/j.cviu.2026.104673_b68","series-title":"ACM MM","first-page":"1500","article-title":"Editing text in the wild","author":"Wu","year":"2019"},{"key":"10.1016\/j.cviu.2026.104673_b69","series-title":"CVPR","first-page":"14700","article-title":"SwapText: Image based texts transfer in scenes","author":"Yang","year":"2020"},{"key":"10.1016\/j.cviu.2026.104673_b70","series-title":"ICME","article-title":"Global-local aware scene text editing","author":"Yang","year":"2025"},{"key":"10.1016\/j.cviu.2026.104673_b71","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.neucom.2021.02.045","article-title":"Mask-guided GAN for robust text editing in the scene","volume":"441","author":"Yu","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.cviu.2026.104673_b72","series-title":"ACM MM","first-page":"5030","article-title":"SAGE: A visual language model for anomaly detection via fact enhancement and entropy-aware alignment","author":"Zang","year":"2025"},{"key":"10.1016\/j.cviu.2026.104673_b73","series-title":"CVPR","first-page":"586","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang","year":"2018"},{"key":"10.1016\/j.cviu.2026.104673_b74","series-title":"AAAI","first-page":"801","article-title":"Ensnet: Ensconce text in the wild","volume":"33","author":"Zhang","year":"2019"},{"key":"10.1016\/j.cviu.2026.104673_b75","series-title":"CVPR","first-page":"28358","article-title":"Choose what you need: Disentangled representation learning for scene text recognition removal and editing","author":"Zhang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104673_b76","series-title":"ICDAR","first-page":"1577","article-title":"ICDAR2019 robust reading challenge on reading chinese text on signboard","author":"Zhang","year":"2019"},{"key":"10.1016\/j.cviu.2026.104673_b77","series-title":"CVPR","first-page":"9762","article-title":"Interpretable image classification via non-parametric part prototype learning","author":"Zhu","year":"2025"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226000408?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226000408?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:03:41Z","timestamp":1777608221000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226000408"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":77,"alternative-id":["S1077314226000408"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104673","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"OSTE: Omni-Scene Text Editing with Latent Decoupling","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104673","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104673"}}