{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:04:22Z","timestamp":1789376662866,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":74,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372345","type":"print"},{"value":"9783032372352","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\/978-3-032-37235-2_29","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:15:49Z","timestamp":1789373749000},"page":"499-520","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Doe-2: 3D Representation World Model for\u00a0Unified Driving Scene Forecasting"],"prefix":"10.1007","author":[{"given":"Dong","family":"Zhuo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhao","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sicheng","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanhui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siming","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"29_CR1","unstructured":"Arai, H., Ishihara, K., Takahashi, T., Yamaguchi, Y.: ACT-bench: towards action controllable world models for autonomous driving. arXiv preprint arXiv:2412.05337 (2024)"},{"key":"29_CR2","unstructured":"Baldassarre, F., et al.: Back to the features: DINO as a foundation for video world models. arXiv preprint arXiv:2507.19468 (2025)"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"29_CR4","unstructured":"Chen, A., et al.: GeoDrive: 3D geometry-informed driving world model with precise action control. arXiv preprint arXiv:2505.22421 (2025)"},{"key":"29_CR5","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":"29_CR6","doi-asserted-by":"crossref","unstructured":"Dang, C., et al.: SparseWorld: a flexible, adaptive, and efficient 4D occupancy world model powered by sparse and dynamic queries. arXiv preprint arXiv:2510.17482 (2025)","DOI":"10.1609\/aaai.v40i5.37347"},{"key":"29_CR7","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":"29_CR8","unstructured":"Gao, R., et al.: MagicDrive: street view generation with diverse 3D geometry control. arXiv preprint arXiv:2310.02601 (2023)"},{"key":"29_CR9","doi-asserted-by":"publisher","first-page":"91560","DOI":"10.52202\/079017-2906","volume":"37","author":"S Gao","year":"2024","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 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR10","unstructured":"Gao, Y., Chen, C., Chen, T., Gu, J.: One layer is enough: adapting pretrained visual encoders for image generation. arXiv preprint arXiv:2512.07829 (2025)"},{"key":"29_CR11","unstructured":"Gu, S., et al.: DOME: taming diffusion model into high-fidelity controllable occupancy world model. arXiv preprint arXiv:2410.10429 (2024)"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Guo, J., et\u00a0al.: DiST-4D: disentangled spatiotemporal diffusion with metric depth for 4D driving scene generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 27231\u201327241 (2025)","DOI":"10.1109\/ICCV51701.2025.02528"},{"key":"29_CR13","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":"29_CR14","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22404\u201322415 (2025)","DOI":"10.1109\/CVPR52734.2025.02087"},{"key":"29_CR15","unstructured":"Hu, A., et al.: GAIA-1: a generative world model for autonomous driving. arXiv preprint arXiv:2309.17080 (2023)"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Hu, P., Huang, A., Dolan, J., Held, D., Ramanan, D.: Safe local motion planning with self-supervised freespace forecasting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12732\u201312741 (2021)","DOI":"10.1109\/CVPR46437.2021.01254"},{"key":"29_CR17","doi-asserted-by":"publisher","unstructured":"Hu, S., Chen, L., Wu, P., Li, H., Yan, J., Tao, D.: ST-P3: end-to-end vision-based autonomous driving via spatial-temporal feature learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13698, pp. 533\u2013549. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_31","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"29_CR18","unstructured":"Hu, X., et al.: DrivingWorld: constructing world model for autonomous driving via video GPT. arXiv preprint arXiv:2412.19505 (2024)"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Hu, Y., et\u00a0al.: Planning-oriented autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17853\u201317862 (2023)","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"29_CR20","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9223\u20139232 (2023)","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, B., et al.: VAD: vectorized scene representation for efficient autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8340\u20138350 (2023)","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"29_CR22","doi-asserted-by":"publisher","unstructured":"Khurana, T., Hu, P., Dave, A., Ziglar, J., Held, D., Ramanan, D.: Differentiable Raycasting for self-supervised occupancy forecasting. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13698, pp. 353\u2013369. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_21","DOI":"10.1007\/978-3-031-19839-7_21"},{"key":"29_CR23","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":"29_CR24","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":"29_CR25","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":"29_CR26","unstructured":"Li, B., et\u00a0al.: OmniNWM: Omniscient driving navigation world models. arXiv preprint arXiv:2510.18313 (2025)"},{"key":"29_CR27","doi-asserted-by":"publisher","first-page":"56424","DOI":"10.52202\/079017-1797","volume":"37","author":"T Li","year":"2024","unstructured":"Li, T., Tian, Y., Li, H., Deng, M., He, K.: Autoregressive image generation without vector quantization. Adv. Neural. Inf. Process. Syst. 37, 56424\u201356445 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR28","unstructured":"Li, X., Li, P., Zheng, Y., Sun, W., Wang, Y., Chen, Y.: Semi-supervised vision-centric 3D occupancy world model for autonomous driving. arXiv preprint arXiv:2502.07309 (2025)"},{"key":"29_CR29","unstructured":"Li, Y., Fan, L., He, J., Wang, Y., Chen, Y., Zhang, Z., Tan, T.: Enhancing end-to-end autonomous driving with latent world model. arXiv preprint arXiv:2406.08481 (2024)"},{"key":"29_CR30","unstructured":"Li, Y., et\u00a0al.: DriveVLA-W0: world models amplify data scaling law in autonomous driving. arXiv preprint arXiv:2510.12796 (2025)"},{"key":"29_CR31","unstructured":"Li, Z., et al.: FB-OCC: 3D occupancy prediction based on forward-backward view transformation. arXiv preprint arXiv:2307.01492 (2023)"},{"key":"29_CR32","unstructured":"Liang, D., et al.: UniFuture: a 4D driving world model for future generation and perception. In: IEEE International Conference on Robotics and Automation. IEEE (2026)"},{"key":"29_CR33","doi-asserted-by":"crossref","unstructured":"Liao, B., et\u00a0al.: DiffusionDrive: truncated diffusion model for end-to-end autonomous driving. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 12037\u201312047 (2025)","DOI":"10.1109\/CVPR52734.2025.01124"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Liao, Z., Wei, P., Chen, S., Wang, H., Ren, Z.: STCOcc: sparse spatial-temporal cascade renovation for 3D occupancy and scene flow prediction. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 1516\u20131526 (2025)","DOI":"10.1109\/CVPR52734.2025.00149"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Liao, Z., Wei, P., Zhang, R., Chen, S., Wang, H., Ren, Z.: I2-World: intra-inter tokenization for efficient dynamic 4D scene forecasting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 25810\u201325819 (2025)","DOI":"10.1109\/ICCV51701.2025.02394"},{"key":"29_CR36","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow. arXiv preprint arXiv:2209.03003 (2022)"},{"key":"29_CR37","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"29_CR38","unstructured":"Lu, H., et al.: UniUGP: unifying understanding, generation, and planing for end-to-end autonomous driving. arXiv preprint arXiv:2512.09864 (2025)"},{"key":"29_CR39","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":"29_CR40","doi-asserted-by":"crossref","unstructured":"Min, C., et\u00a0al.: DriveWorld: 4D pre-trained scene understanding via world models for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15522\u201315533 (2024)","DOI":"10.1109\/CVPR52733.2024.01470"},{"key":"29_CR41","doi-asserted-by":"crossref","unstructured":"Ratliff, N.D., Bagnell, J.A., Zinkevich, M.A.: Maximum margin planning. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 729\u2013736 (2006)","DOI":"10.1145\/1143844.1143936"},{"key":"29_CR42","doi-asserted-by":"crossref","unstructured":"Shi, Y., et al.: COME: adding scene-centric forecasting control to occupancy world model. arXiv preprint arXiv:2506.13260 (2025)","DOI":"10.52202\/085713-0004"},{"key":"29_CR43","unstructured":"Sim\u00e9oni, O., et\u00a0al.: DINOv3. arXiv preprint arXiv:2508.10104 (2025)"},{"key":"29_CR44","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":"29_CR45","doi-asserted-by":"publisher","first-page":"64318","DOI":"10.52202\/075280-2809","volume":"36","author":"X Tian","year":"2023","unstructured":"Tian, X., et al.: Occ3D: a large-scale 3D occupancy prediction benchmark for autonomous driving. Adv. Neural. Inf. Process. Syst. 36, 64318\u201364330 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR46","unstructured":"Tong, W., et\u00a0al.: Scene as occupancy. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8406\u20138415 (2023)"},{"key":"29_CR47","doi-asserted-by":"crossref","unstructured":"Wang, S., et al.: OmniDrive: a holistic vision-language dataset for autonomous driving with counterfactual reasoning. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 22442\u201322452 (2025)","DOI":"10.1109\/CVPR52734.2025.02090"},{"key":"29_CR48","doi-asserted-by":"publisher","unstructured":"Wang, X., Zhu, Z., Huang, G., Chen, X., Zhu, J., Lu, J.: DriveDreamer: towards real-world-drive world models for autonomous driving. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision, ECCV 2024. LNCS, vol. 15106, pp. 55\u201372. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73195-2_4","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"29_CR49","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14749\u201314759 (2024)","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"29_CR50","unstructured":"Wei, J., Yuan, S., Li, P., Hu, Q., Gan, Z., Ding, W.: OccLLaMA: an occupancy-language-action generative world model for autonomous driving. arXiv preprint arXiv:2409.03272 (2024)"},{"key":"29_CR51","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":"29_CR52","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhao, L., Zheng, W., Zhu, Z., Zhou, J., Lu, J.: SurroundOcc: multi-camera 3d occupancy prediction for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21729\u201321740 (2023)","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"29_CR53","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":"29_CR54","unstructured":"Xu, H., Peng, P., Tan, G., Chang, Y., Zhao, Y., Tian, Y.: Delta-triplane transformers as occupancy world models. arXiv preprint arXiv:2503.07338 (2025)"},{"key":"29_CR55","doi-asserted-by":"crossref","unstructured":"Xu, T., Lu, H., Yan, X., Cai, Y., Liu, B., Chen, Y.: Occ-LLM: enhancing autonomous driving with occupancy-based large language models. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 8434\u20138441. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11127665"},{"key":"29_CR56","doi-asserted-by":"crossref","unstructured":"Yan, T., et al.: DrivingSphere: building a high-fidelity 4D world for closed-loop simulation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 27531\u201327541 (2025)","DOI":"10.1109\/CVPR52734.2025.02564"},{"key":"29_CR57","doi-asserted-by":"crossref","unstructured":"Yan, Z., et\u00a0al.: RenderWorld: world model with self-supervised 3D label. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 6063\u20136070. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11127609"},{"key":"29_CR58","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":"29_CR59","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":"29_CR60","doi-asserted-by":"crossref","unstructured":"Zeng, W., et al.: End-to-end interpretable neural motion planner. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8660\u20138669 (2019)","DOI":"10.1109\/CVPR.2019.00886"},{"key":"29_CR61","unstructured":"Zhang, H., et al.: An efficient occupancy world model via decoupled dynamic flow and image-assisted training. arXiv preprint arXiv:2412.13772 (2024)"},{"key":"29_CR62","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":"29_CR63","unstructured":"Zhang, Y., et al.: BEVworld: a multimodal world model for autonomous driving via unified BEV latent space (2024)"},{"key":"29_CR64","doi-asserted-by":"crossref","unstructured":"Zhao, G., et\u00a0al.: DriveDreamer4D: world models are effective data machines for 4D driving scene representation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 12015\u201312026 (2025)","DOI":"10.1109\/CVPR52734.2025.01122"},{"key":"29_CR65","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":"29_CR66","unstructured":"Zheng, B., Ma, N., Tong, S., Xie, S.: Diffusion transformers with representation autoencoders. arXiv preprint arXiv:2510.11690 (2025)"},{"key":"29_CR67","doi-asserted-by":"publisher","unstructured":"Zheng, W., Chen, W., Huang, Y., Zhang, B., Duan, Y., Lu, J.: OccWorld: learning a 3D occupancy world model for autonomous driving. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision, ECCV 2024. LNCS, vol. 15071, pp. 55\u201372. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72624-8_4","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"29_CR68","doi-asserted-by":"publisher","unstructured":"Zheng, W., Song, R., Guo, X., Zhang, C., Chen, L.: GenAD: generative end-to-end autonomous driving. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision, ECCV 2024. LNCS, vol. 15123, pp. 87\u2013104. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73650-6_6","DOI":"10.1007\/978-3-031-73650-6_6"},{"key":"29_CR69","unstructured":"Zheng, W., Xia, Z., Huang, Y., Zuo, S., Zhou, J., Lu, J.: Doe-1: closed-loop autonomous driving with large world model. arXiv preprint arXiv:2412.09627 (2024)"},{"key":"29_CR70","doi-asserted-by":"crossref","unstructured":"Zhou, H., et al.: HUGSIM: a real-time, photo-realistic and closed-loop simulator for autonomous driving. IEEE TPAMI (2025)","DOI":"10.1109\/TPAMI.2025.3647952"},{"key":"29_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: HERMES++: toward a unified driving world model for 3D scene understanding and generation. arXiv preprint arXiv:2604.28196 (2026)","DOI":"10.1109\/ICCV51701.2025.02582"},{"key":"29_CR72","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: HERMES: a unified self-driving world model for simultaneous 3D scene understanding and generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 27817\u201327827 (2025)","DOI":"10.1109\/ICCV51701.2025.02582"},{"key":"29_CR73","unstructured":"Zhuo, D., et al.: DriveTok: 3D driving scene tokenization for unified multi-view reconstruction and understanding. arXiv preprint arXiv:2603.19219 (2026)"},{"key":"29_CR74","doi-asserted-by":"publisher","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.) Computer Vision, ECCV 2024. LNCS, vol. 15104, pp. 269\u2013285. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72952-2_16","DOI":"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\/978-3-032-37235-2_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:16:28Z","timestamp":1789373788000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37235-2_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372345","9783032372352"],"references-count":74,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37235-2_29","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":"15 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"}}]}}