{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:44Z","timestamp":1777890164209,"version":"3.51.4"},"reference-count":72,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471287"],"award-info":[{"award-number":["62471287"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0160201"],"award-info":[{"award-number":["2022ZD0160201"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.01237","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13315-13325","source":"Crossref","is-referenced-by-count":1,"title":["Light-a-Video: Training-Free Video Relighting via Progressive Light Fusion"],"prefix":"10.1109","author":[{"given":"Yujie","family":"Zhou","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiazi","family":"Bu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengyang","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Wu","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qidong","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinsong","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyi","family":"Dong","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Zang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Cao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anyi","family":"Rao","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Niu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2377712"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01213"},{"key":"ref5","article-title":"Hiflow: Training-free high-resolution image generation with flow-aligned guidance","author":"Bu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00595"},{"key":"ref7","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_27"},{"key":"ref10","article-title":"Flatten: optical flowguided attention for consistent text-to-video editing","author":"Cong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344855"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_6"},{"key":"ref13","article-title":"Relightvid: Temporal-consistent diffusion model for video relighting","author":"Fang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"I2v-adapter: A general image-to-video adapter for video diffusion models","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01448"},{"key":"ref21","article-title":"Videocontrolnet: A motion-guided video-to-video translation framework by using diffusion model with controlnet","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Neural gaffer: Relighting any object via diffusion","author":"Jin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00622"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02371"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32456"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00894"},{"key":"ref28","article-title":"Anyv2v: A tuning-free framework for any video-tovideo editing tasks","author":"Ku","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Motionclone: Training-free motion cloning for controllable video generation","author":"Ling","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"ref32","article-title":"Follow-your-click: Opendomain regional image animation via short prompts","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"arXiv preprint","author":"Meng","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00517"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459872"},{"key":"ref38","article-title":"pixabay","volume-title":"pixabay","year":"2025"},{"key":"ref39","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref41","article-title":"On the out-of-distribution generalization of self-supervised learning","volume-title":"International conference on machine learning","author":"Qiang","year":"2025"},{"key":"ref42","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":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00617"},{"key":"ref44","article-title":"Semantic image inversion and editing using rectified stochastic differential equations","author":"Rout","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022","journal-title":"arXiv preprint"},{"key":"ref46","volume-title":"pytorch-fid: FID Score for PyTorch","author":"Seitzer","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00659"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00242"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601137"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3095816"},{"key":"ref51","article-title":"Learning invariant causal mechanism from vision-language models","volume-title":"International conference on machine learning","author":"Song","year":"2025"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323008"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref55","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Cove: Unleashing the diffusion feature correspondence for consistent video editing","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Zero-shot video editing using off-the-shelf image diffusion models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01992"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00831"},{"key":"ref64","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657396"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271-9"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00084"},{"key":"ref68","article-title":"Scaling in-the-wild training for diffusion-based illumination harmonization and editing by imposing consistent light transport","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhang","year":"2025"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00740"},{"key":"ref70","article-title":"Lumisculpt: A consistency lighting control network for video generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00729"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00420"}],"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\/11444224.pdf?arnumber=11444224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:16Z","timestamp":1777613356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444224\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01237","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}