{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:48Z","timestamp":1777890108192,"version":"3.51.4"},"reference-count":55,"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\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20240484681"],"award-info":[{"award-number":["20240484681"]}],"id":[{"id":"10.13039\/501100005090","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\/iccv51701.2025.01587","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17087-17096","source":"Crossref","is-referenced-by-count":0,"title":["Aligning Global Semantics and Local Textures in Generative Video Enhancement*"],"prefix":"10.1109","author":[{"given":"Zhikai","family":"Chen","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuchen","family":"Long","sequence":"additional","affiliation":[{"name":"HiDream.ai Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaofan","family":"Qiu","sequence":"additional","affiliation":[{"name":"HiDream.ai Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Yao","sequence":"additional","affiliation":[{"name":"HiDream.ai Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Rochester,Rochester,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Mei","sequence":"additional","affiliation":[{"name":"HiDream.ai Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.304"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3756870"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_19"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00491"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00587"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32205"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3381814"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00882"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref13","article-title":"Diffusion Models Beat GANs on Image Synthesis","volume-title":"NeurIPS","author":"Dhariwal","year":"2021"},{"key":"ref14","author":"He","year":"2024","journal-title":"VEnhancer: Generative Space-Time Enhancement for Video Generation"},{"key":"ref15","article-title":"Prompt-to-Prompt Image Editing with Cross-Attention Control","author":"Hertz","year":"2023","journal-title":"ICLR"},{"key":"ref16","article-title":"Classifier-Free Diffusion Guidance","volume-title":"NeurIPS Workshop","author":"Ho","year":"2021"},{"key":"ref17","article-title":"Denoising Diffusion Probabilistic Models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref18","author":"Ho","year":"2022","journal-title":"Imagen Video: High Definition Video Generation with Diffusion Models"},{"key":"ref19","article-title":"Video Diffusion Models","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_38"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_20"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2024.3372454"},{"key":"ref25","article-title":"Recurrent Video Restoration Transformer with Guided Deformable Attention","author":"Liang","year":"2022","journal-title":"NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00319"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_28"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01779-w"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_27"},{"key":"ref30","article-title":"Glide: Towards Photorealistic Image Generation and Editing with Text-guided Diffusion Models","author":"Quinn Nichol","year":"2022","journal-title":"ICML"},{"key":"ref31","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2024"},{"key":"ref32","article-title":"Learning Transferable Visual Models From Natural Language Supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","article-title":"Rethinking Alignment in Video Super-Resolution Transformers","author":"Shi","year":"2022","journal-title":"NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00845"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref41","article-title":"Feature Representation Matters: End-toEnd Learning for Reference-based Image Super-resolution","author":"Xie","year":"2020","journal-title":"ECCV"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00632"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-018-01144-2","article-title":"Video Enhancement with TaskOriented Flow","author":"Xue","year":"2019","journal-title":"IJCV"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_4"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00320"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00439"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2279315"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref50","volume-title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","author":"Zhang","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00817"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00828"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02603"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_6"},{"key":"ref55","article-title":"Upscale-A- Video: TemporalConsistent Diffusion Model for Real-World Video SuperResolution","author":"Zhou","year":"2024","journal-title":"CVPR"}],"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\/11445031.pdf?arnumber=11445031","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:56Z","timestamp":1777613456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445031\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01587","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}