{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:36:22Z","timestamp":1757608582061,"version":"3.44.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["NSFC 62088102"],"award-info":[{"award-number":["NSFC 62088102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128068","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"13312-13319","source":"Crossref","is-referenced-by-count":0,"title":["Dualdiff: Dual-Branch Diffusion Model for Autonomous Driving with Semantic Fusion"],"prefix":"10.1109","author":[{"given":"Haoteng","family":"Li","sequence":"first","affiliation":[{"name":"National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Yang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zezhong","family":"Qian","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gongpeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,Anhui,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqi","family":"Huang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,Anhui,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huazheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longjun","family":"Liu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trpro.2018.10.103"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.tranpol.2017.09.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SAMI60510.2024.10432820"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref7","article-title":"Drivingdiffusion: Layout-guided multiview driving scene video generation with latent diffusion model","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref10","article-title":"MagicDrive: Street view generation with diverse 3d geometry control","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Gao","year":"2024"},{"key":"ref11","article-title":"Perldiff: Controllable street view synthesis using perspectivelayout diffusion models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Bevcontrol: Accurately controlling street-view elements with multi-perspective consistency via bev sketch layout","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3368234"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00637"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611480"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref19","first-page":"11127","article-title":"Uni-controlnet: All-in-one control to text-to-image diffusion models","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zhao","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00891"},{"key":"ref21","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Animate-astory: Storytelling with retrieval-augmented video generation","author":"He","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28620"},{"key":"ref24","article-title":"Maptr: Structured modeling and learning for online vectorized hd map construction","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Liao","year":"2023"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"ref29","article-title":"Simgen: Simulator-conditioned driving scene generation","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Unleashing generalization of end-to-end autonomous driving with controllable long video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref32","article-title":"Occ3d: A large-scale 3d occupancy prediction benchmark for autonomous driving","author":"Tian","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref38","first-page":"49842","article-title":"Unipc: A unified predictor-corrector framework for fast sampling of diffusion models","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zhao","year":"2023"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128068.pdf?arnumber=11128068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:06:39Z","timestamp":1756879599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128068","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}