{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:19:52Z","timestamp":1777889992556,"version":"3.51.4"},"reference-count":54,"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":["2024YFB3908503"],"award-info":[{"award-number":["2024YFB3908503"]}],"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":["62322608"],"award-info":[{"award-number":["62322608"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.01606","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":1,"title":["DreamFuse: Adaptive Image Fusion with Diffusion Transformer"],"prefix":"10.1109","author":[{"given":"Junjia","family":"Huang","sequence":"first","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengxiang","family":"Yan","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Wu","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yitong","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"30286","article-title":"Cohen. Subject-driven text-to-image generation via apprenticeship learning","volume":"36","author":"Chen","year":"2023","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2669"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01871"},{"key":"ref5","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2023","journal-title":"ICLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref7","article-title":"Affordance-aware object insertion via mask-aware dual diffusion","author":"He","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","first-page":"123","article-title":"Wildvidfit: Video virtual tryon in the wild via image-based controlled diffusion models","volume-title":"ECCV","author":"He","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.70675\/802872a7z8092z4556za1fdz2c7af45f0e72"},{"key":"ref10","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00321"},{"key":"ref12","article-title":"In-context lora for diffusion transformers","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref15","article-title":"Labs","author":"Forest","year":"2024","journal-title":"Flux: Inference repository"},{"key":"ref16","article-title":"Aligning diffusion models by optimizing human utility","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Improving video generation with human feedback","author":"Liu","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref19","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"ref21","article-title":"High-resolution image harmonization with adaptive-interval color transformation","author":"Meng","year":"2024","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02036"},{"key":"ref23","article-title":"Prodigy: An expeditiously adaptive parameter-free learner","author":"Mishchenko","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28246"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref26","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref29","first-page":"2527825294","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref32","first-page":"3","article-title":"Ominicontrol: Minimal and universal control for diffusion transformer","author":"Tan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref33","article-title":"Motioncom: Automatic and motion-aware image composition with 11 m and video diffusion prior","author":"Tao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_27"},{"key":"ref35","article-title":"Mige: A unified framework for multimodal instruction-based image generation and editing","author":"Tian","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02115"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00574"},{"key":"ref39","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680848"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_7"},{"key":"ref42","article-title":"Objectmate: A recurrence prior for object insertion and subject-driven generation","author":"Winter","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","first-page":"15903","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2023","journal-title":"NeurIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i13.38107"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref46","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref47","article-title":"Controlcom: Controllable image composition using diffusion model","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680610"},{"key":"ref49","article-title":"Unifl: Improve stable diffusion via unified feedback learning","author":"Zhang","year":"2025","journal-title":"NeurIPS"},{"key":"ref50","article-title":"Scaling in-the-wild training for diffusion-based illumination harmonization and editing by imposing consistent light transport","author":"Zhang","year":"2025","journal-title":"ICLR"},{"key":"ref51","article-title":"Diffusion model as a noise-aware latent reward model for step-level preference optimization","author":"Zhang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"ref53","author":"Zhong","year":"2025","journal-title":"Mod-adapter: Tuning-free and versatile multi-concept personalization via modulation adapter"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681355"}],"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\/11443639.pdf?arnumber=11443639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:24:17Z","timestamp":1777613057000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443639\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01606","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}