{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:08Z","timestamp":1777890128170,"version":"3.51.4"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01495","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16112-16121","source":"Crossref","is-referenced-by-count":0,"title":["TextMaster: A Unified Framework for Realistic Text Editing via Glyph-Style Dual-Control"],"prefix":"10.1109","author":[{"given":"Zhenyu","family":"Yan","sequence":"first","affiliation":[{"name":"Taobao & Tmall Group of Alibaba"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aoqiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhan","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxiang","family":"Shang","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhu","family":"Hangcheng","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Flux.1","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2753"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_23"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0410"},{"key":"ref5","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"In Advances in Neural Information Processing Systems","author":"Dhariwal","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref7","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"In Forty-first international conference on machine learning","author":"Esser","year":"2024"},{"key":"ref8","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2023","journal-title":"In ICLR"},{"key":"ref9","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"In NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1916"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"CoRR","author":"Hu","year":"2023"},{"key":"ref13","article-title":"Composer: Creative and controllable image synthesis with composable conditions","volume-title":"arXiv preprint","author":"Huang","year":"2023"},{"key":"ref14","author":"Huang","year":"2024","journal-title":"In-context lora for diffusion transformers"},{"key":"ref15","article-title":"Improving diffusion models for scene text editing with dual encoders","author":"Ji","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref17","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014","journal-title":"In ICLR"},{"key":"ref18","author":"Li","year":"2022","journal-title":"Pp-ocrv3: More attempts for the improvement of ultra lightweight ocr system"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_21"},{"key":"ref21","article-title":"Glyph-byt5-v2: A strong aesthetic baseline for accurate multilingual visual text rendering","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Glyphdraw: Learning to draw chinese characters in image synthesis models coherently","volume-title":"arXiv preprint","author":"Ma","year":"2023"},{"key":"ref23","article-title":"Glyphdraw2: Automatic generation of complex glyph posters with diffusion models and large language models","author":"Ma","year":"2024","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref25","volume-title":"Dall\u2022e3","year":"2023"},{"key":"ref26","author":"Oquab","year":"2024","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref27","article-title":"Sdxl: Improving latent diffusion mod-els for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02155"},{"key":"ref32","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv preprint"},{"key":"ref33","author":"Santoso","year":"2023","journal-title":"On manipulating scene text in the wild with diffusion models"},{"key":"ref34","author":"Schuhmann","year":"2021","journal-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01716"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/wacv51458.2022.00323"},{"key":"ref37","article-title":"Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Anytext2: Visual text generation and editing with customizable attributes","author":"Tuo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Anytext: Multilingual visual text generation and editing","author":"Tuo","year":"2024","journal-title":"ICLR"},{"key":"ref40","author":"Wang","year":"2024","journal-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation"},{"key":"ref41","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02659"},{"key":"ref43","article-title":"Glyphcontrol: Glyph conditional control for visual text generation","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Glyphcontrol: Glyph conditional control for visual text generation","volume":"36","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00800"},{"key":"ref47","author":"Zeng","year":"2024","journal-title":"Textctrl: Diffusion-based scene text editing with prior guidance control"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref49","author":"Zhou","year":"2024","journal-title":"Storydiffusion: Consistent selfattention for long-range image and video generation"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445114.pdf?arnumber=11445114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:29Z","timestamp":1777613489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445114\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01495","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}