{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T05:05:24Z","timestamp":1782536724098,"version":"3.54.5"},"reference-count":51,"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":["62476192 and 62206199"],"award-info":[{"award-number":["62476192 and 62206199"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.01340","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14443-14452","source":"Crossref","is-referenced-by-count":1,"title":["NoiseController: Towards Consistent Multi-View Video Generation via Noise Decomposition and Collaboration"],"prefix":"10.1109","author":[{"given":"Haotian","family":"Dong","sequence":"first","affiliation":[{"name":"Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Lin","sequence":"additional","affiliation":[{"name":"Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yipeng","family":"Wu","sequence":"additional","affiliation":[{"name":"Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Chen","sequence":"additional","affiliation":[{"name":"Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruonan","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kairui","family":"Yang","sequence":"additional","affiliation":[{"name":"Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Guo","sequence":"additional","affiliation":[{"name":"Nankai University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","article-title":"Magicdrivedit: High-resolution long video generation for autonomous driving with adaptive control","author":"Gao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"MagicDrive: Street view generation with diverse 3d geometry control","author":"Gao","year":"2024","journal-title":"ICLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref7","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32376"},{"key":"ref10","article-title":"The lottery ticket hypothesis in denoising: Towards semantic-driven initialization","author":"Wang","year":"2024","journal-title":"ECCV"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00349"},{"key":"ref12","article-title":"Tuning-free noise rectification for high fidelity image-to-video generation","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","first-page":"469","article-title":"Driving-diffusion: Layout-guided multi-view driving scene video generation with latent diffusion model","author":"Li","year":"2024","journal-title":"ECCV"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28148"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_19"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612191"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref21","article-title":"Freenoise: Tuning-free longer video diffusion via noise rescheduling","author":"Qiu","year":"2024","journal-title":"ICLR"},{"key":"ref22","article-title":"Freetraj: Tuning-free trajectory control in video diffusion models","author":"Qiu","year":"2025","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00852"},{"key":"ref26","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2023","journal-title":"ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3368234"},{"key":"ref28","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref30","first-page":"55","article-title":"Drivedreamer: Towards real-worlddriven world models for autonomous driving","author":"Wang","year":"2024","journal-title":"ECCV"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01632"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref35","first-page":"34322","article-title":"Motionbooth: Motion-aware customized text-to-video generation","volume":"37","author":"Wu","year":"2024","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_22"},{"key":"ref38","article-title":"Drivescape: Towards high-resolution controllable multi-view driving video generation","author":"Wu","year":"2025","journal-title":"CVPR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28450"},{"key":"ref40","article-title":"Bevcontrol: Accurately controlling streetview elements with multi-perspective consistency via bev sketch layout","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref41","article-title":"Trajectory-llm: A language-based data generator for trajectory prediction in autonomous driving","author":"Yang","year":"2025","journal-title":"ICLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref43","article-title":"Mygo: Consistent and controllable multi-view driving video generation with camera control","author":"Yao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3541936"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-025-03948-z"},{"key":"ref46","article-title":"Controlvideo: Training-free controllable text-to-video generation","author":"Zhang","year":"2024","journal-title":"ICLR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00828"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref51","first-page":"110315","article-title":"Storydiffusion: Consistent self-attention for long-range image and video generation","volume":"37","author":"Zhou","year":"2024","journal-title":"NeurIPS"}],"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\/11444860.pdf?arnumber=11444860","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:27:32Z","timestamp":1777530452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444860\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01340","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}