{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:17:52Z","timestamp":1783455472651,"version":"3.55.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2024YFB3908503"],"award-info":[{"award-number":["2024YFB3908503"]}]},{"name":"National Key R&D Program of China","award":["2024YFB3908500"],"award-info":[{"award-number":["2024YFB3908500"]}]},{"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"}]},{"name":"Major Key Project of PCL","award":["PCL2025A17"],"award-info":[{"award-number":["PCL2025A17"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3680535","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T19:59:33Z","timestamp":1775591973000},"page":"9502-9518","source":"Crossref","is-referenced-by-count":0,"title":["DreamFuse: Toward Realistic and Seamless Image Fusion Across Diverse Scenarios"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2914-6232","authenticated-orcid":false,"given":"Junjia","family":"Huang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengxiang","family":"Yan","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wu","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yitong","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5860-5941","authenticated-orcid":false,"given":"Xinglong","family":"Wu","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1318"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01386"},{"key":"ref4","article-title":"Mod-adapter: Tuning-free and versatile multi-concept personalization via modulation adapter","author":"Zhong","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref6","article-title":"Scaling in-the-wild training for diffusion-based illumination harmonization and editing by imposing consistent light transport","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_27"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00574"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01511"},{"key":"ref11","article-title":"Affordance-aware object insertion via mask-aware dual diffusion","author":"He","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02036"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02115"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680848"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref20","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gal"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3658205"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3730843"},{"key":"ref24","article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"ref26","article-title":"InstantID: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_8"},{"key":"ref28","article-title":"In-context lora for diffusion transformers","author":"Huang","year":"2024"},{"key":"ref29","article-title":"XVerse: Consistent multi-subject control of identity and semantic attributes via DiT modulation","author":"Chen","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28246"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681355"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0441"},{"key":"ref33","article-title":"MotionCom: Automatic and motion-aware image composition with LLM and video diffusion prior","author":"Tao","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02457"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3613169"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00207"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i11.37866"},{"key":"ref39","article-title":"OmniGen2: Exploration to advanced multimodal generation","author":"Wu","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i13.38107"},{"key":"ref42","first-page":"67355","article-title":"UniFL: Improve stable diffusion via unified feedback learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680610"},{"key":"ref44","article-title":"Improving video generation with human feedback","author":"Liu","year":"2025"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0785"},{"key":"ref47","article-title":"Diffusion model as a noise-aware latent reward model for step-level preference optimization","author":"Zhang","year":"2025"},{"key":"ref48","article-title":"Seed1. 5-VL technical report","author":"Guo","year":"2025"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24894\/sprengglossarium_m06267"},{"key":"ref50","article-title":"Flux: Inference repository","author":"Labs","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00321"},{"key":"ref53","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref54","article-title":"Seededit: Align image re-generation to image editing","author":"Shi","year":"2024"},{"key":"ref55","article-title":"FLUX. 1 kontext: Flow matching for in-context image generation and editing in latent space","author":"Batifol","year":"2025"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.663"},{"key":"ref57","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"issue":"2","key":"ref59","first-page":"95","article-title":"A benchmark of facial recognition pipelines and co-usability performances of modules","volume":"17","author":"Serengil","year":"2024","journal-title":"J. Inf. Technol."},{"key":"ref60","first-page":"19790","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Edstedt"},{"key":"ref61","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref62","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022"},{"key":"ref63","article-title":"Prodigy: An expeditiously adaptive parameter-free learner","author":"Mishchenko","year":"2023"},{"key":"ref64","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref65","article-title":"Controlcom: Controllable image composition using diffusion model","author":"Zhang","year":"2023"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2669"},{"key":"ref67","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Esser"},{"key":"ref68","article-title":"Qwen-image technical report","author":"Wu","year":"2025"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01609"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref71","article-title":"CogVLM2: Visual language models for image and video understanding","author":"Hong","year":"2024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1097\/00005053-195707000-00032"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01819"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11475881.pdf?arnumber=11475881","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:45:19Z","timestamp":1783453519000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11475881\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":73,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3680535","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}