{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:48:50Z","timestamp":1777654130922,"version":"3.51.4"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project of China","doi-asserted-by":"publisher","award":["2023ZD0121300"],"award-info":[{"award-number":["2023ZD0121300"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472399"],"award-info":[{"award-number":["62472399"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032006"],"award-info":[{"award-number":["62032006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62021001"],"award-info":[{"award-number":["62021001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tcsvt.2025.3601553","type":"journal-article","created":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:04:57Z","timestamp":1755911097000},"page":"2247-2258","source":"Crossref","is-referenced-by-count":6,"title":["Panacea+: Panoramic and Controllable Video Generation for Autonomous Driving"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9492-362X","authenticated-orcid":false,"given":"Yuqing","family":"Wen","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"given":"Yucheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Megvii Technology, Beijing, China"}]},{"given":"Yingfei","family":"Liu","sequence":"additional","affiliation":[{"name":"Megvii Technology, Beijing, China"}]},{"given":"Binyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, Hubei, China"}]},{"given":"Fan","family":"Jia","sequence":"additional","affiliation":[{"name":"Megvii Technology, Beijing, China"}]},{"given":"Yanhui","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Mach Drive, Wuhu, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6517-4293","authenticated-orcid":false,"given":"Tiancai","family":"Wang","sequence":"additional","affiliation":[{"name":"Megvii Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3638-5566","authenticated-orcid":false,"given":"Xiaoyan","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2138-4608","authenticated-orcid":false,"given":"Xiangyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Megvii Technology, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01719"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_32"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01674"},{"key":"ref9","article-title":"BEVControl: Accurately controlling street-view elements with multi-perspective consistency via BEV sketch layout","author":"Yang","year":"2023","journal-title":"arXiv:2308.01661"},{"key":"ref10","article-title":"Street-view image generation from a bird\u2019s-eye view layout","author":"Swerdlow","year":"2023","journal-title":"arXiv:2301.04634"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref12","article-title":"LayoutDiffuse: Adapting foundational diffusion models for layout-to-image generation","author":"Cheng","year":"2023","journal-title":"arXiv:2302.08908"},{"key":"ref13","article-title":"MagicDrive: Street view generation with diverse 3D geometry control","author":"Gao","year":"2023","journal-title":"arXiv:2310.02601"},{"key":"ref14","article-title":"DriveDreamer: Towards real-world-driven world models for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv:2309.09777"},{"key":"ref15","article-title":"WoVoGen: World volume-aware diffusion for controllable multi-camera driving scene generation","author":"Lu","year":"2023","journal-title":"arXiv:2312.02934"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3601553"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref20","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2023","journal-title":"arXiv:2301.00493"},{"key":"ref21","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2014","journal-title":"arXiv:1406.2661"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3347971"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3136857"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867934"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.251"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2970919"},{"key":"ref27","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"Proc. ICLR","author":"Hong"},{"key":"ref28","article-title":"GODIVA: Generating open-domain videos from nAtural descriptions","author":"Wu","year":"2021","journal-title":"arXiv: 2104.14806"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369757"},{"key":"ref31","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nichol"},{"key":"ref32","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref33","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NeurIPS","author":"Saharia"},{"key":"ref34","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref35","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3409184"},{"key":"ref38","article-title":"MVDiffusion: Enabling holistic multi-view image generation with correspondence-aware diffusion","author":"Tang","year":"2023","journal-title":"arXiv:2307.01097"},{"key":"ref39","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref40","article-title":"Tune-A-Video: One-shot tuning of image diffusion models for text-to-video generation","author":"Wu","year":"2022","journal-title":"arXiv:2212.11565"},{"key":"ref41","article-title":"MagicVideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","journal-title":"arXiv:2211.11018"},{"key":"ref42","article-title":"LAMP: Learn a motion pattern for few-shot-based video generation","author":"Wu","year":"2023","journal-title":"arXiv:2310.10769"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref44","article-title":"ModelScope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv:2308.06571"},{"key":"ref45","article-title":"VideoGen: A reference-guided latent diffusion approach for high definition text-to-video generation","author":"Li","year":"2023","journal-title":"arXiv:2309.00398"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref47","first-page":"1","article-title":"Make-A-Video: Text-to-video generation without text-video data","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Singer"},{"key":"ref48","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv:2311.15127"},{"key":"ref49","volume-title":"Sora: Creating Video From Text","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3268849"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202810"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3396870"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00500"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref59","article-title":"Time will tell: New outlooks and a baseline for temporal multi-view 3D object detection","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Park"},{"key":"ref60","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. CoRL","author":"Wang"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32376"},{"key":"ref63","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref64","article-title":"Denoising diffusion implicit models","volume-title":"Proc. ICLR","author":"Song"},{"key":"ref65","article-title":"T2D: Spatiotemporal feature learning based on triple 2D decomposition","author":"Zhao","year":"2023"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2993901"},{"key":"ref70","article-title":"MicroCinema: A divide-and-conquer approach for text-to-video generation","author":"Wang","year":"2023","journal-title":"arXiv:2311.18829"},{"key":"ref71","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01339"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00889"},{"key":"ref74","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":"ref75","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv:1812.01717"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01403"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref78","article-title":"DreamForge: Motion-aware autoregressive video generation for multi-view driving scenes","author":"Mei","year":"2024","journal-title":"arXiv:2409.04003"},{"key":"ref79","article-title":"Physical informed driving world model","author":"Yang","year":"2024","journal-title":"arXiv:2412.08410"},{"key":"ref80","article-title":"Exploiting diffusion prior for real-world image super-resolution","author":"Wang","year":"2023","journal-title":"arXiv:2305.07015"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3401451"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109420"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11392768\/11134493.pdf?arnumber=11134493","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:02:55Z","timestamp":1770930175000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11134493\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":82,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3601553","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}