{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T01:55:46Z","timestamp":1785549346618,"version":"3.56.0"},"reference-count":93,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01261","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13580-13591","source":"Crossref","is-referenced-by-count":5,"title":["Controllable Weather Synthesis and Removal with Video Diffusion Models"],"prefix":"10.1109","author":[{"given":"Chih-Hao","family":"Lin","sequence":"first","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zian","family":"Wang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruofan","family":"Liang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanja","family":"Fidler","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shenlong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois,Urbana-Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zan","family":"Gojcic","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Pexels.com"},{"key":"ref2","article-title":"Cosmos world foundation model platform for physical ai","author":"Agarwal","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref4","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref7","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref9","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2598681"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095605"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_45"},{"key":"ref15","article-title":"Flatten: optical flow-guided attention for consistent text-tovideo editing","author":"Cong","year":"2024","journal-title":"ICLR"},{"key":"ref16","article-title":"Using simulated data to generate images of climate change","volume-title":"ICLR Workshop","author":"Cosne"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01506"},{"key":"ref18","article-title":"Diffusion models beat GANs on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Epic Games","year":"2019","journal-title":"Unreal engine"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1242073.1242231"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00641"},{"key":"ref23","article-title":"Let it snow! animating static gaussian scenes with dynamic weather effects","author":"Fiebelman","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141985"},{"key":"ref26","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2024","journal-title":"ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392431"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01111"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917518"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01808"},{"key":"ref31","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho"},{"key":"ref33","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00076"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref36","article-title":"Vbench++: Comprehensive and versatile benchmark suite for video generative models","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref37","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"NeurIPS","author":"Karras"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01462"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref41","article-title":"Anyv2v: A tuning-free framework for any video-to-video editing tasks","author":"Ku","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.511"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00324"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00299"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00945"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00784"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02428"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00741"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2806202"},{"key":"ref51","article-title":"Sdedit: Image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref53","article-title":"Dreamix: Video diffusion models are general video editors","author":"Molad","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref55","volume-title":"Chatgpt: A conversational ai model","year":"2025"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3238179"},{"key":"ref57","article-title":"One-step image translation with text-to-image models","author":"Parmar","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref58","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00263"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00903"},{"key":"ref62","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref63","volume-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00927"},{"key":"ref65","article-title":"Visualizing the consequences of climate change using cycle-consistent adversarial networks","author":"Schmidt","year":"2019","journal-title":"ICLR"},{"key":"ref66","article-title":"Climategan: Raising climate change awareness by generating images of floods","author":"Schmidt","year":"2022","journal-title":"ICLR"},{"key":"ref67","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume-title":"NeurIPS","author":"Schuhmann"},{"key":"ref68","first-page":"1215","article-title":"Edit-a-video: Single video editing with object-aware consistency","volume-title":"Asian Conference on Machine Learning","author":"Shin"},{"key":"ref69","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International Conference on Machine Learning","author":"Sohl-Dickstein"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461948"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/0010-4655(94)00170-7"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_7"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01366-3"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00239"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917269"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917367"},{"key":"ref80","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01041"},{"key":"ref82","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00701","article-title":"Tune-a-video: Oneshot tuning of image diffusion models for text-to-video generation","volume-title":"ICCV","author":"Wu"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02098"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680916"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183612"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00831"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.183"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01214"},{"key":"ref89","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01163"},{"key":"ref91","article-title":"Controlvideo: Training-free controllable text-to-video generation","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3501855"}],"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\/11443650.pdf?arnumber=11443650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:10:53Z","timestamp":1777529453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":93,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01261","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}