{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T10:19:03Z","timestamp":1789294743173,"version":"build-2803163510"},"reference-count":64,"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\/iccv51701.2025.01474","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15885-15895","source":"Crossref","is-referenced-by-count":1,"title":["MUSE: Multi-Subject Unified Synthesis Via Explicit Layout Semantic Expansion"],"prefix":"10.1109","author":[{"given":"Fei","family":"Peng","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junqiang","family":"Wu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Li","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingting","family":"Gao","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiyuan","family":"Fu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref2","article-title":"ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref3","volume-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","author":"Bar-Tal","year":"2023"},{"issue":"3","key":"ref4","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref5","article-title":"Large scale gan training for high fidelity natural image synthesis","author":"Brock","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref6","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref8","article-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref11","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref13","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","author":"Feng","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref15","article-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0699"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref21","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref22","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00714"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref25","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref26","article-title":"Generating images with multimodal language models","volume":"36","author":"Yu Koh","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1312"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref33","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref34","article-title":"Kosmos-g: Generating images in context with multimodal large language models","author":"Pan","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"\u039b-eclipse: Multi-concept personalized text-to-image diffusion models by leveraging clip latent space","author":"Patel","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3472"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"2","key":"ref39","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.25"},{"key":"ref41","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"International conference on machine learning","author":"Reed"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00610"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00852"},{"key":"ref48","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref51","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref53","article-title":"Ms-diffusion: Multi-subject zero-shot image personalization with layout guidance","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref55","article-title":"Ifadapter: Instance feature control for grounded text-to-image generation","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_17"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref59","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"ref63","article-title":"Migc++: Advanced multi-instance generation controller for image synthesis","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"}],"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\/11444218.pdf?arnumber=11444218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:21Z","timestamp":1777613361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01474","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}