{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T08:02:21Z","timestamp":1770192141948,"version":"3.49.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036005"],"award-info":[{"award-number":["62036005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"GPU Cluster Built by MCC Laboratory of Information Science and Technology Institution, University of Science and Technology of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3654412","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T21:01:47Z","timestamp":1769202107000},"page":"1111-1126","source":"Crossref","is-referenced-by-count":0,"title":["LaCon: Late-Constraint Controllable Visual Generation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1751-6206","authenticated-orcid":false,"given":"Chang","family":"Liu","sequence":"first","affiliation":[{"name":"MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3102-0932","authenticated-orcid":false,"given":"Rui","family":"Li","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6467-7112","authenticated-orcid":false,"given":"Kaidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8884-0853","authenticated-orcid":false,"given":"Yunwei","family":"Lan","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}]},{"given":"Xin","family":"Luo","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9100-2906","authenticated-orcid":false,"given":"Dong","family":"Liu","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","author":"Ho"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref3","article-title":"I2 VGen-XL: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv:2311.04145"},{"key":"ref4","article-title":"HunyuanVideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv:2412.03603"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref9","first-page":"11127","article-title":"Uni-ControlNet: All-in-one control to text-to-image diffusion models","volume-title":"Proc. NeurIPS","author":"Zhao"},{"key":"ref10","first-page":"8542","article-title":"In-context learning unlocked for diffusion models","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_20"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3553024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3541877"},{"key":"ref14","article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"Proc. ICLR","author":"Baranchuk"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3551648"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3402620"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933590"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2890017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2924589"},{"key":"ref25","article-title":"Denoising diffusion implicit models","volume-title":"Proc. ICLR","author":"Song"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32469"},{"key":"ref28","article-title":"LTX-video: Realtime video latent diffusion","author":"HaCohen","year":"2024","journal-title":"arXiv:2501.00103"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3639307"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00183"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_36"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2866698"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3021789"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055062"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3026728"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref39","article-title":"Control-A-video: Controllable text-to-video generation with diffusion models","author":"Chen","year":"2023","journal-title":"arXiv:2305.13840"},{"key":"ref40","article-title":"Ctrl-adapter: An efficient and versatile framework for adapting diverse controls to any diffusion model","volume-title":"Proc. ICLR","author":"Lin"},{"key":"ref41","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref42","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591560"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"ref46","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. ICLR","author":"Meng"},{"key":"ref47","article-title":"OminiControl: Minimal and universal control for diffusion transformer","author":"Tan","year":"2024","journal-title":"arXiv:2411.15098"},{"key":"ref48","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv:2401.14159"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007074"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"ref53","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. NIPS","author":"Heusel"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611969"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3179744"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01415"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3290479"},{"key":"ref59","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref61","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. ICLR","author":"Podell"},{"key":"ref62","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"Proc. ICLR","author":"Karras"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref64","article-title":"Token merging: Your ViT but faster","volume-title":"Proc. ICLR","author":"Bolya"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00536"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0917-8_2"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11360571.pdf?arnumber=11360571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T20:57:13Z","timestamp":1770152233000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11360571\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3654412","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}