{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:01:49Z","timestamp":1777888909894,"version":"3.51.4"},"reference-count":51,"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"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022YFB4701400\/4701402"],"award-info":[{"award-number":["2022YFB4701400\/4701402"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01704","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18335-18344","source":"Crossref","is-referenced-by-count":1,"title":["UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis"],"prefix":"10.1109","author":[{"given":"Yuanrui","family":"Wang","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Han","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yafei","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhipeng","family":"Jin","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiawei","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"SiNan","family":"Du","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Tao","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuanglong","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liu","family":"Lin","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Flux.1","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_23"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0410"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612489"},{"key":"ref5","article-title":"Whoever started the interference should end it: Guiding data-free model merging via task vectors","author":"Cheng","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref6","article-title":"Alore: Efficient visual adaptation via aggregating low rank experts","author":"Du","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref7","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref8","volume-title":"Layoutgpt: Compositional visual planning and generation with large language models","author":"Feng","year":"2023"},{"key":"ref9","article-title":"Wukong: 100 million large-scale chinese cross-modal pre-training dataset and A foundation framework","volume":"abs\/2202.06767","author":"Gu","year":"2022","journal-title":"CoRR"},{"key":"ref10","volume-title":"Enhancing logits distillation with plug&play kendall\u2019s $\\tau$ ranking loss","author":"Guan","year":"2025"},{"key":"ref11","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","author":"Hu","year":"2023","journal-title":"CoRR"},{"key":"ref12","article-title":"Composer: Creative and controllable image synthesis with composable conditions","volume":"abs\/2302.09778","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","volume-title":"Improving diffusion models for scene text editing with dual encoders","author":"Ji","year":"2023"},{"key":"ref14","article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma","year":"2014"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref16","volume-title":"Flux","year":"2024"},{"key":"ref17","volume-title":"Layoutprompter: Awaken the design ability of large language models","author":"Lin","year":"2023"},{"key":"ref18","volume-title":"Flow matching for generative modeling","author":"Lipman","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.900"},{"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 arXiv"},{"key":"ref22","volume-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"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","volume-title":"Chargen: High accurate characterlevel visual text generation model with multimodal encoder","author":"Ma","year":"2024"},{"key":"ref25","article-title":"Follow-your-creation: Empowering 4d creation through video inpainting","author":"Ma","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref26","article-title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models","volume":"abs\/2302.08453","author":"Mou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","volume-title":"Dall\u2022e3","year":"2023"},{"key":"ref28","volume-title":"Pp-ocrv4","year":"2023"},{"key":"ref29","volume-title":"Customtext: Customized textual image generation using diffusion models","author":"Paliwal","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref31","article-title":"LAION400 M: open dataset of clip-filtered 400 million image-text pairs","volume":"abs\/2111.02114","author":"Schuhmann","year":"2021","journal-title":"CoRR"},{"key":"ref32","volume-title":"Gsrender: Deduplicated occupancy prediction via weakly supervised 3d gaussian splatting","author":"Sun","year":"2024"},{"key":"ref33","volume-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref34","volume-title":"Llama 2: Open foundation and finetuned chat models","author":"Touvron","year":"2023"},{"key":"ref35","article-title":"Anytext: Multilingual visual text generation and editing","author":"Tuo","year":"2023","journal-title":"arXiv"},{"key":"ref36","volume-title":"Anytext2: Visual text generation and editing with customizable attributes","author":"Tuo","year":"2024"},{"key":"ref37","volume-title":"Rectified diffusion: Straightness is not your need in rectified flow","author":"Wang","year":"2024"},{"key":"ref38","volume-title":"Alphavae: Unified end-to-end rgba image reconstruction and generation with alpha-aware representation learning","author":"Wang","year":"2025"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01732"},{"key":"ref40","article-title":"Modeling multi-task model merging as adaptive projective gradient descent","author":"Wei","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01856"},{"key":"ref42","article-title":"Chartbench: A benchmark for complex visual reasoning in charts","author":"Xu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Glyphcontrol: Glyph conditional control for visual text generation","volume":"abs\/2305.18259","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3495831"},{"key":"ref46","volume-title":"Artist: Improving the generation of text-rich images with disentangled diffusion models and large language models","author":"Zhang","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28550"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00716"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_13"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"}],"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\/11445440.pdf?arnumber=11445440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:02:11Z","timestamp":1777611731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01704","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}