{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:50:16Z","timestamp":1778082616431,"version":"3.51.4"},"reference-count":60,"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\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406135"],"award-info":[{"award-number":["62406135"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20241198"],"award-info":[{"award-number":["BK20241198"]}],"id":[{"id":"10.13039\/501100004608","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\/iccv51701.2025.01797","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19331-19341","source":"Crossref","is-referenced-by-count":1,"title":["RAGD: Regional-Aware Diffusion Model for Text-to-Image Generation"],"prefix":"10.1109","author":[{"given":"Zhennan","family":"Chen","sequence":"first","affiliation":[{"name":"Nanjing University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yajie","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haofan","family":"Wang","sequence":"additional","affiliation":[{"name":"InstantX Team,North Carolina,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibo","family":"Chen","sequence":"additional","affiliation":[{"name":"Liblib AI,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengkai","family":"Jiang","sequence":"additional","affiliation":[{"name":"HKUST,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Wang","sequence":"additional","affiliation":[{"name":"China Mobile,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Tai","sequence":"additional","affiliation":[{"name":"Nanjing University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","author":"Bar-Tal","year":"2023"},{"key":"ref2","volume-title":"Black forest labs; frontier ai lab","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref4","article-title":"Pixart- $\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230302"},{"key":"ref6","article-title":"Textcrafter: Accurately rendering multiple texts in complex visual scenes","author":"Nikai","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref8","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref9","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00454"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref13","first-page":"36777","article-title":"Pulid: Pure and lightning id customization via contrastive alignment","volume":"37","author":"Guo","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref17","article-title":"Mixture of diffusers for scene composition and high resolution image generation","author":"Jim\u00e9nez","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Brushnet: A plug-and-play image inpainting model with decomposed dual-branch diffusion","author":"Xuan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01850"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"ref23","article-title":"Playground v3: Improving text-toimage alignment with deep-fusion large language models","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref24","volume-title":"Omost github","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref26","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"issue":"140","key":"ref27","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"issue":"2","key":"ref28","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Hyper-sd: Trajectory segmented consistency model for efficient image synthesis","author":"Ren","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref33","volume-title":"Myth wukong lora","year":"2024"},{"key":"ref34","volume-title":"Wool yarn lora","year":"2024"},{"key":"ref35","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref36","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref37","article-title":"Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","article-title":"Instantstyle-plus: Style transfer with content-preserving in text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref40","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref42","article-title":"Ms-diffusion: Multi-subject zero-shot image personalization with layout guidance","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","author":"Xie","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref45","article-title":"Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal 11 ms","volume-title":"Forty-first International Conference on Machine Learning","author":"Yang","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref47","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"issue":"3","key":"ref48","first-page":"5","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume":"2","author":"Jiahui","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref51","article-title":"Tar3d: Creating high-quality 3d assets via next-part prediction","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01847"},{"key":"ref53","article-title":"Ar-1-to-3: Single image to consistent 3d object generation via next-view prediction","author":"Zhang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00791"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106428"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03314-5"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3510752"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"ref59","article-title":"3dis: Depth-driven decoupled instance synthesis for text-to-image generation","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01552"}],"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\/11444650.pdf?arnumber=11444650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:06Z","timestamp":1777611246000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01797","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}