{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:08:51Z","timestamp":1780636131229,"version":"3.54.1"},"reference-count":60,"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":["62332016"],"award-info":[{"award-number":["62332016"]}],"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\/iccv51701.2025.02357","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"25410-25420","source":"Crossref","is-referenced-by-count":1,"title":["InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation"],"prefix":"10.1109","author":[{"given":"Zhuoran","family":"Yang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Guo","sequence":"additional","affiliation":[{"name":"SenseAuto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenjing","family":"Ding","sequence":"additional","affiliation":[{"name":"SenseAuto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chiyu","family":"Wang","sequence":"additional","affiliation":[{"name":"SenseAuto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wu","sequence":"additional","affiliation":[{"name":"SenseAuto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"An","year":"2023","journal-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref3","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","author":"Cabon","year":"2020","journal-title":"Virtual kitti 2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref8","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proceedings of the 1st Annual Conference on Robot Learning","author":"Dosovitskiy","year":"2017"},{"key":"ref9","author":"Gao","year":"2024","journal-title":"Ca2-vdm: Efficient autoregressive video diffusion model with causal generation and cache sharing"},{"key":"ref10","author":"Gao","year":"2024","journal-title":"Magicdrivedit: High-resolution long video generation for autonomous driving with adaptive control"},{"key":"ref11","author":"Gao","year":"2024","journal-title":"Magicdrive: Street view generation with diverse 3d geometry control"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.01.115"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01956"},{"key":"ref14","author":"Guo","year":"2024","journal-title":"Infinity-drive: Breaking time limits in driving world models"},{"key":"ref15","author":"Guo","year":"2023","journal-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_23"},{"key":"ref17","author":"HaCohen","year":"2024","journal-title":"Ltx-video: Realtime video latent diffusion"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02087"},{"key":"ref19","author":"He","year":"2022","journal-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths"},{"key":"ref20","first-page":"6629","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017"},{"key":"ref21","author":"Ho","year":"2022","journal-title":"Imagen video: High definition video generation with diffusion models"},{"key":"ref22","first-page":"8633","volume":"35","author":"Ho","year":"2022","journal-title":"Video diffusion models"},{"key":"ref23","first-page":"8153","volume-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","author":"Hu","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref25","author":"Jia","year":"2023","journal-title":"Adriver-i: A general world model for autonomous driving"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01359"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref30","author":"Oquab","year":"2024","journal-title":"Dinov2: Learning robust visual features without supervision"},{"issue":"140","key":"ref31","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3009957"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.241"},{"key":"ref35","author":"Singer","year":"2022","journal-title":"Make-a-video: Text-to-video generation without text-video data"},{"key":"ref36","author":"Swerdlow","year":"2023","journal-title":"Streetview image generation from a bird\u2019s-eye view layout"},{"key":"ref37","author":"Tang","year":"2023","journal-title":"Mvdiffusion: Enabling holistic multiview image generation with correspondence-aware diffusion"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01609"},{"key":"ref40","author":"Unterthiner","year":"2018","journal-title":"Towards accurate generative models of video: A new metric challenges"},{"key":"ref41","author":"Wang","year":"2023","journal-title":"Modelscope text-to-video technical report"},{"key":"ref42","author":"Wang","year":"2024","journal-title":"Qihoo-t2x: An efficient proxy-tokenized diffusion transformer for text-to-any-task"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref44","author":"Wang","year":"2023","journal-title":"Videofactory: Swap attention in spatiotemporal diffusions for text-to-video generation"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref46","first-page":"1","author":"Wang","year":"2024","journal-title":"Lavie: High-quality video generation with cascaded latent diffusion models"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref48","author":"Wu","year":"2024","journal-title":"Drivescape: To-wards high-resolution controllable multi-view driving video generation"},{"key":"ref49","author":"Xi","year":"2025","journal-title":"Sparse videogen: Accelerating video diffusion transformers with spatial-temporal sparsity"},{"key":"ref50","author":"Yang","year":"2023","journal-title":"Bevcontrol: Accurately controlling streetview elements with multi-perspective consistency via bev sketch layout"},{"key":"ref51","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02346-1"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00400"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73650-6_6"},{"key":"ref57","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref58","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref59","author":"Zhou","year":"2023","journal-title":"Magicvideo: Efficient video generation with latent diffusion models"},{"key":"ref60","author":"Zhou","year":"2024","journal-title":"Allegro: Open the black box of commercial-level video generation model"}],"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\/11445809.pdf?arnumber=11445809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:02Z","timestamp":1777530002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445809\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02357","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}