{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T21:02:17Z","timestamp":1780434137304,"version":"3.54.1"},"reference-count":49,"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\/iros60139.2025.11247293","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"8051-8058","source":"Crossref","is-referenced-by-count":0,"title":["PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth"],"prefix":"10.1109","author":[{"given":"Bu","family":"Jin","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weize","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for AI Industry Research (AIR)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baihan","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for AI Industry Research (AIR)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenxin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for AI Industry Research (AIR)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junpeng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan-ang","family":"Gao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for AI Industry Research (AIR)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Sun","sequence":"additional","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Zhan","sequence":"additional","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengtong","family":"Hu","sequence":"additional","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Jia","sequence":"additional","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for AI Industry Research (AIR)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01443"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3447450"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160552"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611261"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160470"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_21"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01118"},{"key":"ref9","article-title":"Hint-ad: Holistically aligned interpretability in end-to-end autonomous driving","author":"Ding","year":"2024"},{"key":"ref10","first-page":"20 703","article-title":"Model-based imitation learning for urban driving","volume":"35","author":"Hu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref13","article-title":"Bevcontrol: Accurately controlling street-view elements with multi-perspective consistency via bev sketch layout","author":"Yang","year":"2023"},{"key":"ref14","article-title":"Magicdrive: Street view generation with diverse 3d geometry control","author":"Gao","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32376"},{"key":"ref17","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref20","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024"},{"key":"ref21","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00594"},{"key":"ref24","article-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video","volume":"32","author":"Bian","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01484-6"},{"key":"ref27","article-title":"A survey of world models for autonomous driving","author":"Feng","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref29","article-title":"Dome: Taming diffusion model into high-fidelity controllable occupancy world model","author":"Gu","year":"2024"},{"key":"ref30","article-title":"World4drive: End-to-end autonomous driving via intention-aware physical latent world model","author":"Zheng","year":"2025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00784"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00340"},{"key":"ref34","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref36","article-title":"World-dreamer: Towards general world models for video generation via predicting masked tokens","author":"Wang","year":"2024"},{"key":"ref37","article-title":"Muvo: A multimodal world model with spatial representations for autonomous driving","author":"Bogdoll","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"ref39","first-page":"34 322","article-title":"Motionbooth: Motion-aware customized text-to-video generation","volume":"37","author":"Wu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","article-title":"Training-free camera control for video generation","author":"Hou","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00065"},{"key":"ref42","article-title":"Cami2v: Camera-controlled image-to-video diffusion model","author":"Zheng","year":"2024"},{"key":"ref43","article-title":"I2vcontrol-camera: Precise video camera control with adjustable motion strength","author":"Feng","year":"2024"},{"key":"ref44","article-title":"Dive: Dit-based video generation with enhanced control","author":"Jiang","year":"2024"},{"key":"ref45","article-title":"Drivingworld: Constructingworld model for autonomous driving via video gpt","author":"Hu","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"},{"key":"ref49","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":"Advances in neural information processing systems"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247293.pdf?arnumber=11247293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T20:01:30Z","timestamp":1780430490000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247293","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}