{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:29:16Z","timestamp":1777656556042,"version":"3.51.4"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729881","type":"print"},{"value":"9783031729898","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72989-8_19","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:02:04Z","timestamp":1729875724000},"page":"329-345","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["WoVoGen: World Volume-Aware Diffusion for\u00a0Controllable Multi-camera Driving Scene Generation"],"prefix":"10.1007","author":[{"given":"Jiachen","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ze","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"19_CR1","unstructured":"Blattmann, A., et\u00a0al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint (2023)"},{"key":"19_CR2","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":"19_CR3","unstructured":"Chen, Y., Gu, C., Jiang, J., Zhu, X., Zhang, L.: Periodic vibration gaussian: dynamic urban scene reconstruction and real-time rendering. arXiv preprint (2023)"},{"key":"19_CR4","unstructured":"Contributors, S.: SpConv: spatially sparse convolution library (2022). https:\/\/github.com\/traveller59\/spconv"},{"key":"19_CR5","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis (2021)"},{"key":"19_CR6","unstructured":"Ding, M., et\u00a0al.: CogView: mastering text-to-image generation via transformers (2021)"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Fong, W.K., et al.: Panoptic nuScenes: a large-scale benchmark for LiDAR panoptic segmentation and tracking (2022)","DOI":"10.1109\/LRA.2022.3148457"},{"key":"19_CR9","unstructured":"Gao, R., et al.: MagicDrive: street view generation with diverse 3D geometry control. arXiv preprint (2023)"},{"key":"19_CR10","unstructured":"Guo, J., et al.: StreetSurf: extending multi-view implicit surface reconstruction to street views. arXiv preprint (2023)"},{"key":"19_CR11","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 (2017)"},{"key":"19_CR12","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models (2020)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"19_CR14","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: BEVDet: high-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint (2021)"},{"key":"19_CR15","unstructured":"Huang, L., Chen, D., Liu, Y., Shen, Y., Zhao, D., Zhou, J.: Composer: creative and controllable image synthesis with composable conditions. arXiv preprint (2023)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Kim, S.W., et al.: NeuralField-LDM: scene generation with hierarchical latent diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00821"},{"key":"19_CR17","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":"19_CR18","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, Y., Ye, X.: DrivingDiffusion: layout-guided multi-view driving scene video generation with latent diffusion model. arXiv preprint (2023)","DOI":"10.1007\/978-3-031-73229-4_27"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GLIGEN: open-set grounded text-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"19_CR20","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20077-9_1","volume-title":"ECCV 2022","author":"Z Li","year":"2022","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: Avidan, S., Brostow, G., Ciss\u2019e, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3D object. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"19_CR22","unstructured":"Liu, Y., et al.: SyncDreamer: generating multiview-consistent images from a single-view image. arXiv preprint (2023)"},{"key":"19_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-58568-6_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Philion","year":"2020","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 194\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12"},{"key":"19_CR24","unstructured":"Qian, G., et\u00a0al.: Magic123: one image to high-quality 3D object generation using both 2D and 3D diffusion priors. arXiv preprint (2023)"},{"key":"19_CR25","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"19_CR26","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint (2022)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"19_CR30","unstructured":"Shi, Y., Wang, P., Ye, J., Long, M., Li, K., Yang, X.: MVDream: multi-view diffusion for 3D generation. arXiv preprint (2023)"},{"key":"19_CR31","unstructured":"Singer, U., et\u00a0al.: Make-a-video: text-to-video generation without text-video data. arXiv preprint (2022)"},{"key":"19_CR32","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2023)"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Sun, J., Shen, Z., Wang, Y., Bao, H., Zhou, X.: LoFTR: detector-free local feature matching with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8922\u20138931 (2021)","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Swerdlow, A., Xu, R., Zhou, B.: Street-view image generation from a bird\u2019s-eye view layout. IEEE Rob. Autom. Lett. (2024)","DOI":"10.1109\/LRA.2024.3368234"},{"key":"19_CR35","unstructured":"Tian, X., Jiang, T., Yun, L., Wang, Y., Wang, Y., Zhao, H.: Occ3D: a large-scale 3D occupancy prediction benchmark for autonomous driving. arXiv preprint (2023)"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Tong, W., et\u00a0al.: Scene as occupancy. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"19_CR37","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 (2018)"},{"key":"19_CR38","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning (2017)"},{"key":"19_CR39","unstructured":"Vaswani, A., et al.: Attention is all you need (2017)"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhu, Z., Huang, G., Chen, X., Lu, J.: DriveDreamer: towards real-world-driven world models for autonomous driving. arXiv preprint (2023)","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"19_CR41","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. arXiv preprint (2023)","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., et al.: Tune-a-video: one-shot tuning of image diffusion models for text-to-video generation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Wu, Z., et\u00a0al.: MARS: an instance-aware, modular and realistic simulator for autonomous driving. arXiv preprint (2023)","DOI":"10.1007\/978-981-99-8850-1_1"},{"key":"19_CR44","unstructured":"Xie, Z., Zhang, J., Li, W., Zhang, F., Zhang, L.: S-NeRF: neural radiance fields for street views. In: ICLR (2023)"},{"key":"19_CR45","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 (2023)"},{"key":"19_CR46","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: UniSim: a neural closed-loop sensor simulator. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00140"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"19_CR48","doi-asserted-by":"crossref","unstructured":"Zheng, G., Zhou, X., Li, X., Qi, Z., Shan, Y., Li, X.: LayoutDiffusion: controllable diffusion model for layout-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"19_CR49","unstructured":"Zhou, D., Wang, W., Yan, H., Lv, W., Zhu, Y., Feng, J.: MagicVideo: efficient video generation with latent diffusion models. arXiv preprint (2022)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72989-8_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T08:31:50Z","timestamp":1732955510000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72989-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031729881","9783031729898"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72989-8_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}