{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:01:17Z","timestamp":1791910877688,"version":"4.3.4"},"publisher-location":"Cham","reference-count":101,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376237","type":"print"},{"value":"9783032376244","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37624-4_12","type":"book-chapter","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:53:27Z","timestamp":1789538007000},"page":"187-208","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["OmniNWM: Omniscient Driving Navigation World Models"],"prefix":"10.1007","author":[{"given":"Bohan","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dalong","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baorui","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhujin","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenqiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianda","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueming","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"12_CR1","unstructured":"Bahmani, S., et all.: VD3D: taming large video diffusion transformers for 3D camera control. arXiv preprint arXiv:2407.12781 (2024)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Bai, J., et\u00a0al.: Recammaster: camera-controlled generative rendering from a single video. arXiv preprint arXiv:2503.11647 (2025)","DOI":"10.1109\/ICCV51701.2025.01376"},{"key":"12_CR3","unstructured":"Bai, J., et al.: Qwen-VL: a versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"12_CR4","unstructured":"Bengio, S., Vinyals, O., Jaitly, N., Shazeer, N.: Scheduled sampling for sequence prediction with recurrent neural networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: A multimodal dataset for autonomous driving. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Cao, A.Q., de\u00a0Charette, R.: Monoscene: monocular 3D semantic scene completion. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"12_CR7","unstructured":"Chen, A., et al.: Geodrive: 3D geometry-informed driving world model with precise action control. arXiv preprint arXiv:2505.22421 (2025)"},{"key":"12_CR8","first-page":"24081","volume":"37","author":"B Chen","year":"2025","unstructured":"Chen, B., Mart\u00ed Mons\u00f3, D., Du, Y., Simchowitz, M., Tedrake, R., Sitzmann, V.: Diffusion forcing: next-token prediction meets full-sequence diffusion. Adv. Neural. Inf. Process. Syst. 37, 24081\u201324125 (2025)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Chen, R., et al.: Unimlvg: unified framework for multi-view long video generation with comprehensive control capabilities for autonomous driving (2025). https:\/\/arxiv.org\/abs\/2412.04842","DOI":"10.1109\/ICCV51701.2025.02361"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Chen, X., Lin, K.Y., Qian, C., Zeng, G., Li, H.: 3D sketch-aware semantic scene completion via semi-supervised structure prior. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00425"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Y., Zhang, Z.: DrivingGPT: unifying driving world modeling and planning with multi-modal autoregressive transformers. arXiv preprint arXiv:2412.18607 (2024)","DOI":"10.1109\/ICCV51701.2025.02496"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Chi, H., et\u00a0al.: Impromptu VLA: open weights and open data for driving vision-language-action models. arXiv preprint arXiv:2505.23757 (2025)","DOI":"10.52202\/085713-2557"},{"issue":"2","key":"12_CR13","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1145\/1461928.1461951","volume":"52","author":"C Daskalakis","year":"2009","unstructured":"Daskalakis, C., Goldberg, P.W., Papadimitriou, C.H.: The complexity of computing a Nash equilibrium. Commun. ACM 52(2), 89\u201397 (2009)","journal-title":"Commun. ACM"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Gao, R., Chen, K., Xiao, B., Hong, L., Li, Z., Xu, Q.: Magicdrive-V2: high-resolution long video generation for autonomous driving with adaptive control. arXiv preprint arXiv:2411.13807 (2024)","DOI":"10.1109\/ICCV51701.2025.02612"},{"key":"12_CR15","unstructured":"Gao, R., Chen, K., Xiao, B., Hong, L., Li, Z., Xu, Q.: Magicdrivedit: high-resolution long video generation for autonomous driving with adaptive control. arXiv e-prints, arXiv\u20132411 (2024)"},{"key":"12_CR16","unstructured":"Gao, R., et al.: Magicdrive: street view generation with diverse 3D geometry control. In: ICLR (2024)"},{"key":"12_CR17","first-page":"91560","volume":"37","author":"S Gao","year":"2025","unstructured":"Gao, S., et al.: Vista: a generalizable driving world model with high fidelity and versatile controllability. Adv. Neural. Inf. Process. Syst. 37, 91560\u201391596 (2025)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Ge, J., et al.: Unraveling the effects of synthetic data on end-to-end autonomous driving. arXiv preprint arXiv:2503.18108 (2025)","DOI":"10.1109\/ICCV51701.2025.02680"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Guo, J., et\u00a0al.: Dist-4d: disentangled spatiotemporal diffusion with metric depth for 4D driving scene generation. arXiv preprint arXiv:2503.15208 (2025)","DOI":"10.1109\/ICCV51701.2025.02528"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Guo, X., et\u00a0al.: Genesis: multimodal driving scene generation with spatio-temporal and cross-modal consistency. arXiv preprint arXiv:2506.07497 (2025)","DOI":"10.52202\/085713-2021"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Hassan, M., et al.: Gem: a generalizable ego-vision multimodal world model for fine-grained ego-motion, object dynamics, and scene composition control. In: CVPR, pp. 22404\u201322415 (2025)","DOI":"10.1109\/CVPR52734.2025.02087"},{"key":"12_CR22","unstructured":"He, H., et al.: Cameractrl: enabling camera control for text-to-video generation. arXiv preprint arXiv:2404.02101 (2024)"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"He, H., et al.: Cameractrl ii: dynamic scene exploration via camera-controlled video diffusion models. arXiv preprint arXiv:2503.10592 (2025)","DOI":"10.1109\/ICCV51701.2025.01246"},{"key":"12_CR24","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: NeurIPS (2017)"},{"issue":"12","key":"12_CR25","doi-asserted-by":"publisher","first-page":"3999","DOI":"10.1073\/pnas.0308738101","volume":"101","author":"CA Holt","year":"2004","unstructured":"Holt, C.A., Roth, A.E.: The Nash equilibrium: a perspective. Proc. Natl. Acad. Sci. 101(12), 3999\u20134002 (2004)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"12_CR26","unstructured":"Hou, C., Wei, G., Zeng, Y., Chen, Z.: Training-free camera control for video generation. arXiv preprint arXiv:2406.10126 (2024)"},{"key":"12_CR27","unstructured":"Hu, T., et\u00a0al.: Vision-language-action models for autonomous driving: past, present, and future. arXiv preprint arXiv:2512.16760 (2025)"},{"key":"12_CR28","unstructured":"Hu, X., et al.: DrivingWorld: constructing world model for autonomous driving via video GPT. arXiv preprint arXiv:2412.19505 (2024)"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Huang, X., Li, Z., He, G., Zhou, M., Shechtman, E.: Self forcing: bridging the train-test gap in autoregressive video diffusion. arXiv preprint arXiv:2506.08009 (2025)","DOI":"10.52202\/085713-5576"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zheng, W., Zhang, Y., Zhou, J., Lu, J.: Tri-perspective view for vision-based 3D semantic occupancy prediction. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Jiang, H., et al.: Rayzer: a self-supervised large view synthesis model. arXiv preprint arXiv:2505.00702 (2025)","DOI":"10.1109\/ICCV51701.2025.00468"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Jin, B., et al.: Posepilot: steering camera pose for generative world models with self-supervised depth (2025). https:\/\/arxiv.org\/abs\/2505.01729","DOI":"10.1109\/IROS60139.2025.11247293"},{"key":"12_CR33","unstructured":"Jin, H., et al.: LVSM: a large view synthesis model with minimal 3D inductive bias. arXiv preprint arXiv:2410.17242 (2024)"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Kim, S.W., Philion, J., Torralba, A., Fidler, S.: DriveGAN: towards a controllable high-quality neural simulation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00576"},{"key":"12_CR35","unstructured":"Kong, L., et al.: 3D and 4D world modeling: a survey. arXiv preprint arXiv:2509.07996 (2025)"},{"key":"12_CR36","unstructured":"Kong, W., et\u00a0al.: HunyuanVideo: a systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"12_CR37","doi-asserted-by":"publisher","first-page":"16240","DOI":"10.52202\/079017-0518","volume":"37","author":"Z Kuang","year":"2024","unstructured":"Kuang, Z., et al.: Collaborative video diffusion: consistent multi-video generation with camera control. Adv. Neural. Inf. Process. Syst. 37, 16240\u201316271 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR38","doi-asserted-by":"publisher","first-page":"24223","DOI":"10.52202\/075280-1053","volume":"36","author":"K Lee","year":"2023","unstructured":"Lee, K., Kim, S., Choi, J.: Refining diffusion planner for reliable behavior synthesis by automatic detection of infeasible plans. Adv. Neural. Inf. Process. Syst. 36, 24223\u201324246 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Li, B., Deng, J., Sun, Y., Wang, X., Jin, X., Zeng, W.: Hierarchical context alignment with disentangled geometric and temporal modeling for semantic occupancy prediction. IEEE Trans. Pattern Anal. Mach. Intell. (2026)","DOI":"10.1109\/TPAMI.2025.3650478"},{"key":"12_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/978-3-031-73235-5_8","volume-title":"Computer Vision \u2013 ECCV 2024","author":"B Li","year":"2024","unstructured":"Li, B., et al.: Hierarchical temporal context learning for camera-based semantic scene completion. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15062, pp. 131\u2013148. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73235-5_8"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Li, B., et\u00a0al.: Uniscene: unified occupancy-centric driving scene generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 11971\u201311981 (2025)","DOI":"10.1109\/CVPR52734.2025.01118"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Li, B., et\u00a0al.: Occscene: semantic occupancy-based cross-task mutual learning for 3D scene generation. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3602511"},{"key":"12_CR43","unstructured":"Li, B., et\u00a0al.: Scaling up occupancy-centric driving scene generation: dataset and method. arXiv preprint arXiv:2510.22973 (2025)"},{"key":"12_CR44","unstructured":"Li, B., et al.: Bridging stereo geometry and BEV representation with reliable mutual interaction for semantic scene completion. In: IJCAI (2024)"},{"key":"12_CR45","unstructured":"Li, B., et al.: From articulated kinematics to routed visual control for action-conditioned surgical video generation. arXiv preprint arXiv:2605.08712 (2026)"},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Li, J., Han, K., Wang, P., Liu, Y., Yuan, X.: Anisotropic convolutional networks for 3D semantic scene completion. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00341"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Li, R., Yi, B., Liu, J., Gao, H., Ma, Y., Kanazawa, A.: Cameras as relative positional encoding. arXiv preprint arXiv:2507.10496 (2025)","DOI":"10.52202\/085713-0540"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Li, S., Kachana, P., Chidananda, P., Nair, S., Furukawa, Y., Brown, M.: RIG3R: rig-aware conditioning for learned 3D reconstruction. arXiv preprint arXiv:2506.02265 (2025)","DOI":"10.52202\/085713-0815"},{"key":"12_CR49","unstructured":"Liang, A., et\u00a0al.: Worldlens: full-spectrum evaluations of driving world models in real world. arXiv preprint arXiv:2512.10958 (2025)"},{"key":"12_CR50","unstructured":"Liang, D., et al.: Unifuture: a 4D driving world model for future generation and perception. In: IEEE International Conference on Robotics and Automation (2026)"},{"key":"12_CR51","unstructured":"Liu, X., et al.: Wanderland: geometrically grounded simulation for open-world embodied AI. arXiv preprint arXiv:2511.20620 (2025)"},{"key":"12_CR52","doi-asserted-by":"crossref","unstructured":"Long, X., Liu, L., Li, W., Theobalt, C., Wang, W.: Multi-view depth estimation using epipolar spatio-temporal networks. In: CVPR, pp. 8258\u20138267 (2021)","DOI":"10.1109\/CVPR46437.2021.00816"},{"key":"12_CR53","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"12_CR54","doi-asserted-by":"crossref","unstructured":"Lu, J., Huang, Z., Zhang, J., Yang, Z., Zhang, L.: Wovogen: world volume-aware diffusion for controllable multi-camera driving scene generation. arXiv preprint arXiv:2312.02934 (2023)","DOI":"10.1007\/978-3-031-72989-8_19"},{"key":"12_CR55","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Infinicube: unbounded and controllable dynamic 3D driving scene generation with world-guided video models (2025). https:\/\/arxiv.org\/abs\/2412.03934","DOI":"10.1109\/ICCV51701.2025.02532"},{"key":"12_CR56","doi-asserted-by":"crossref","unstructured":"Mao, J., et al.: Dreamdrive: generative 4D scene modeling from street view images. arXiv preprint arXiv:2501.00601 (2024)","DOI":"10.1109\/ICRA55743.2025.11127463"},{"key":"12_CR57","doi-asserted-by":"crossref","unstructured":"Mousakhan, A., Mittal, S., Galesso, S., Farid, K., Brox, T.: Orbis: overcoming challenges of long-horizon prediction in driving world models. arXiv preprint arXiv:2507.13162 (2025)","DOI":"10.52202\/085713-0167"},{"key":"12_CR58","doi-asserted-by":"crossref","unstructured":"Ni, C., et\u00a0al.: Recondreamer: crafting world models for driving scene reconstruction via online restoration. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 1559\u20131569 (2025)","DOI":"10.1109\/CVPR52734.2025.00153"},{"key":"12_CR59","doi-asserted-by":"crossref","unstructured":"Roldao, L., de\u00a0Charette, R., Verroust-Blondet, A.: LMSCnet: lightweight multiscale 3D semantic completion. In: 3DV (2020)","DOI":"10.1109\/3DV50981.2020.00021"},{"key":"12_CR60","doi-asserted-by":"crossref","unstructured":"Schneider, J.P., Bisht, P.S., Chugunov, I., Kolb, A., Moeller, M., Heide, F.: Neural atlas graphs for dynamic scene decomposition and editing. arXiv preprint arXiv:2509.16336 (2025)","DOI":"10.52202\/085713-0485"},{"key":"12_CR61","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"12_CR62","doi-asserted-by":"crossref","unstructured":"Song, R., et al.: Coda-4dgs: dynamic gaussian splatting with context and deformation awareness for autonomous driving. arXiv preprint arXiv:2503.06744 (2025)","DOI":"10.1109\/ICCV51701.2025.02602"},{"issue":"9","key":"12_CR63","doi-asserted-by":"publisher","first-page":"14088","DOI":"10.1109\/TITS.2021.3136353","volume":"23","author":"J Sun","year":"2021","unstructured":"Sun, J., Zhang, H., Zhou, H., Yu, R., Tian, Y.: Scenario-based test automation for highly automated vehicles: a review and paving the way for systematic safety assurance. IEEE Trans. Intell. Transp. Syst. 23(9), 14088\u201314103 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"12_CR64","doi-asserted-by":"crossref","unstructured":"Swerdlow, A., Xu, R., Zhou, B.: Street-view image generation from a bird\u2019s-eye view layout. IEEE Robot. Autom. Lett. (2024)","DOI":"10.1109\/LRA.2024.3368234"},{"key":"12_CR65","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: ICML (2019)"},{"key":"12_CR66","doi-asserted-by":"crossref","unstructured":"Tang, P., et al.: Sparseocc: rethinking sparse latent representation for vision-based semantic occupancy prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15035\u201315044 (2024)","DOI":"10.1109\/CVPR52733.2024.01424"},{"key":"12_CR67","unstructured":"Team, R., et al.: Advancing open-source world models. arXiv preprint arXiv:2601.20540 (2026)"},{"key":"12_CR68","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"12_CR69","doi-asserted-by":"crossref","unstructured":"Wang, G., et al.: OCCgen: generative multi-modal 3d occupancy prediction for autonomous driving. arXiv preprint arXiv:2404.15014 (2024)","DOI":"10.1007\/978-3-031-72661-3_6"},{"key":"12_CR70","unstructured":"Wang, L., et al.: Stag-1: towards realistic 4D driving simulation with video generation model. arXiv preprint arXiv:2412.05280 (2024)"},{"key":"12_CR71","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-3-031-73195-2_4","volume-title":"Computer Vision \u2013 ECCV 2024","author":"X Wang","year":"2024","unstructured":"Wang, X., Zhu, Z., Huang, G., Chen, X., Lu, J.: DriveDreamer: towards real-world-driven world models for autonomous driving. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15106, pp. 55\u201372. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73195-2_4"},{"key":"12_CR72","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Openoccupancy: a large scale benchmark for surrounding semantic occupancy perception. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"12_CR73","doi-asserted-by":"crossref","unstructured":"Wang, Y., He, J., Fan, L., Li, H., Chen, Y., Zhang, Z.: Driving into the future: multiview visual forecasting and planning with world model for autonomous driving. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"12_CR74","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: MotionCtrl: a unified and flexible motion controller for video generation. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657518"},{"key":"12_CR75","unstructured":"Wei, Y., et al.: Surrounddepth: entangling surrounding views for self-supervised multi-camera depth estimation. In: Conference on Robot Learning, pp. 539\u2013549. PMLR (2023)"},{"key":"12_CR76","doi-asserted-by":"crossref","unstructured":"Wen, Y., et al.: Panacea: panoramic and controllable video generation for autonomous driving. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"12_CR77","doi-asserted-by":"crossref","unstructured":"Xiao, B., Feng, C., Huang, Z., Zhong, Y., Ma, L.: Robotron-sim: improving real-world driving via simulated hard-case. arXiv preprint arXiv:2508.04642 (2025)","DOI":"10.1109\/ICCV51701.2025.02542"},{"key":"12_CR78","unstructured":"Xu, D., et al.: Camco: camera-controllable 3d-consistent image-to-video generation. arXiv preprint arXiv:2406.02509 (2024)"},{"key":"12_CR79","doi-asserted-by":"crossref","unstructured":"Xu, J., Deng, K., Fan, Z., Wang, S., Xie, J., Yang, J.: Ad-GS: object-aware b-spline gaussian splatting for self-supervised autonomous driving. arXiv preprint arXiv:2507.12137 (2025)","DOI":"10.1109\/ICCV51701.2025.02297"},{"key":"12_CR80","doi-asserted-by":"crossref","unstructured":"Yan, X., et al.: Sparse single sweep lidar point cloud segmentation via learning contextual shape priors from scene completion. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i4.16419"},{"key":"12_CR81","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Diffusion-es: gradient-free planning with diffusion for autonomous and instruction-guided driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15342\u201315353 (2024)","DOI":"10.1109\/CVPR52733.2024.01453"},{"key":"12_CR82","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: ReSim: reliable world simulation for autonomous driving. arXiv preprint arXiv:2506.09981 (2025)","DOI":"10.52202\/085713-5591"},{"key":"12_CR83","unstructured":"Yang, K., Ma, E., Peng, J., Guo, Q., Lin, D., Yu, K.: BEVControl: accurately controlling street-view elements with multi-perspective consistency via BEV sketch layout. arXiv preprint arXiv:2308.01661 (2023)"},{"key":"12_CR84","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: Direct-a-video: customized video generation with user-directed camera movement and object motion. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201312 (2024)","DOI":"10.1145\/3641519.3657481"},{"key":"12_CR85","doi-asserted-by":"crossref","unstructured":"Yang, X., et al.: DriveArena: a closed-loop generative simulation platform for autonomous driving. arXiv preprint arXiv:2408.00415 (2024)","DOI":"10.1109\/ICCV51701.2025.02500"},{"key":"12_CR86","doi-asserted-by":"crossref","unstructured":"Yang, X., et al.: DriveArena: a closed-loop generative simulation platform for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 26933\u201326943 (2025)","DOI":"10.1109\/ICCV51701.2025.02500"},{"key":"12_CR87","doi-asserted-by":"crossref","unstructured":"Yang, Y., Liang, A., Mei, J., Ma, Y., Liu, Y., Lee, G.H.: X-scene: large-scale driving scene generation with high fidelity and flexible controllability. arXiv preprint arXiv:2506.13558 (2025)","DOI":"10.52202\/085713-3487"},{"key":"12_CR88","doi-asserted-by":"crossref","unstructured":"Yang, Z., Pan, Z., Yang, Y., Zhu, X., Zhang, L.: Driving view synthesis on free-form trajectories with generative prior (2025). https:\/\/arxiv.org\/abs\/2412.01717","DOI":"10.1109\/ICCV51701.2025.02607"},{"key":"12_CR89","doi-asserted-by":"crossref","unstructured":"Yang, Z., Guo, X., Ding, C., Wang, C., Wu, W., Zhang, Y.: InstaDrive: instance-aware driving world models for realistic and consistent video generation. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.02357"},{"key":"12_CR90","doi-asserted-by":"crossref","unstructured":"Ye, X., Yaman, B., Cheng, S., Tao, F., Mallik, A., Ren, L.: BEVDiffuser: plug-and-play diffusion model for BEV denoising with ground-truth guidance. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 1495\u20131504 (2025)","DOI":"10.1109\/CVPR52734.2025.00147"},{"key":"12_CR91","doi-asserted-by":"crossref","unstructured":"Zeng, S., et al.: FuturesightDrive: thinking visually with spatio-temporal cot for autonomous driving. arXiv preprint arXiv:2505.17685 (2025)","DOI":"10.52202\/085713-2257"},{"key":"12_CR92","unstructured":"Zhang, J.Y., Lin, A., Kumar, M., Yang, T.H., Ramanan, D., Tulsiani, S.: Cameras as rays: Pose estimation via ray diffusion. arXiv preprint arXiv:2402.14817 (2024)"},{"key":"12_CR93","doi-asserted-by":"crossref","unstructured":"Zhang, K., et\u00a0al.: Epona: autoregressive diffusion world model for autonomous driving. arXiv preprint arXiv:2506.24113 (2025)","DOI":"10.1109\/ICCV51701.2025.02527"},{"key":"12_CR94","doi-asserted-by":"crossref","unstructured":"Zhao, G., et al.: Recondreamer++: harmonizing generative and reconstructive models for driving scene representation. arXiv preprint arXiv:2503.18438 (2025)","DOI":"10.1109\/ICCV51701.2025.02480"},{"key":"12_CR95","doi-asserted-by":"crossref","unstructured":"Zhao, G., et al.: DriveDreamer-2: LLM-enhanced world models for diverse driving video generation. arXiv preprint arXiv:2403.06845 (2024)","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"12_CR96","doi-asserted-by":"crossref","unstructured":"Zheng, W., Chen, W., Huang, Y., Zhang, B., Duan, Y., Lu, J.: OCCWorld: learning a 3D occupancy world model for autonomous driving. arXiv preprint arXiv:2311.16038 (2023)","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"12_CR97","doi-asserted-by":"crossref","unstructured":"Zheng, W., Song, R., Guo, X., Chen, L.: Genad: generative end-to-end autonomous driving. arXiv preprint arXiv:2402.11502 (2024)","DOI":"10.1007\/978-3-031-73650-6_6"},{"key":"12_CR98","unstructured":"Zheng, Y., et\u00a0al.: Diffusion-based planning for autonomous driving with flexible guidance. arXiv preprint arXiv:2501.15564 (2025)"},{"key":"12_CR99","unstructured":"Zhou, H., et al.: HugSim: a real-time, photo-realistic and closed-loop simulator for autonomous driving. arXiv preprint arXiv:2412.01718 (2024)"},{"key":"12_CR100","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: Hermes: a unified self-driving world model for simultaneous 3D scene understanding and generation. arXiv preprint arXiv:2501.14729 (2025)","DOI":"10.1109\/ICCV51701.2025.02582"},{"key":"12_CR101","series-title":"ecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/978-3-031-72952-2_16","volume-title":"Computer Vision \u2013 ECCV 2024","author":"Y Zou","year":"2024","unstructured":"Zou, Y., Ding, Y., Qiu, X., Wang, H., Zhang, H.: M$$^{2}$$Depth: self-supervised two-frame multi-camera metric depth estimation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15104, pp. 269\u2013285. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72952-2_16"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37624-4_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:54:03Z","timestamp":1789538043000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37624-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032376237","9783032376244"],"references-count":101,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37624-4_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"17 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}