{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T17:53:49Z","timestamp":1774720429877,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFE0203100"],"award-info":[{"award-number":["2024YFE0203100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["No.62476293"],"award-info":[{"award-number":["No.62476293"]}]},{"name":"Shenzhen Science and Technology Program","award":["No.GJHZ20220913142600001"],"award-info":[{"award-number":["No.GJHZ20220913142600001"]}]},{"name":"Nansha Key R&D Program","award":["No.2022ZD014"],"award-info":[{"award-number":["No.2022ZD014"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754772","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:27:39Z","timestamp":1761377259000},"page":"9365-9374","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8526-220X","authenticated-orcid":false,"given":"Tao","family":"Tang","sequence":"first","affiliation":[{"name":"Shenzhen Campus of Sun Yat-Sen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5334-7024","authenticated-orcid":false,"given":"Enhui","family":"Ma","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1892-351X","authenticated-orcid":false,"given":"Xia","family":"Zhou","sequence":"additional","affiliation":[{"name":"Li Auto Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0231-6960","authenticated-orcid":false,"given":"Letian","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Toronto, Toronto, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3685-2566","authenticated-orcid":false,"given":"Tianyi","family":"Yan","sequence":"additional","affiliation":[{"name":"Li Auto Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3678-5761","authenticated-orcid":false,"given":"Xueyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Li Auto Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4208-5220","authenticated-orcid":false,"given":"Kun","family":"Zhan","sequence":"additional","affiliation":[{"name":"Li Auto Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2273-3892","authenticated-orcid":false,"given":"Peng","family":"Jia","sequence":"additional","affiliation":[{"name":"Li Auto Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2620-7128","authenticated-orcid":false,"given":"Xianpeng","family":"Lang","sequence":"additional","affiliation":[{"name":"Li Auto Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2046-3363","authenticated-orcid":false,"given":"Jia-Wang","family":"Bian","sequence":"additional","affiliation":[{"name":"ByteDance Seed, San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0186-3399","authenticated-orcid":false,"given":"Kaicheng","family":"Yu","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-Sen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_2_1","volume-title":"Video generation models as world simulators","author":"Brooks Tim","year":"2024","unstructured":"Tim Brooks, Bill Peebles, Connor Holmes, Will DePue, Yufei Guo, Li Jing, David Schnurr, Joe Taylor, Troy Luhman, Eric Luhman, et al. Video generation models as world simulators. 2024. URL https:\/\/openai. com\/research\/video-generationmodels-as-world-simulators, 3:1, 2024."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968535"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"e_1_3_2_1_6_1","volume-title":"Pixart-\u03b4: Fast and controllable image generation with latent consistency models. arXiv preprint arXiv:2401.05252","author":"Chen Junsong","year":"2024","unstructured":"Junsong Chen, Yue Wu, Simian Luo, Enze Xie, Sayak Paul, Ping Luo, Hang Zhao, and Zhenguo Li. Pixart-\u03b4: Fast and controllable image generation with latent consistency models. arXiv preprint arXiv:2401.05252, 2024."},{"key":"e_1_3_2_1_7_1","volume-title":"Lidar-gs: Real-time lidar re-simulation using gaussian splatting. arXiv preprint arXiv:2410.05111","author":"Chen Qifeng","year":"2024","unstructured":"Qifeng Chen, Sheng Yang, Sicong Du, Tao Tang, Peng Chen, and Yuchi Huo. Lidar-gs: Real-time lidar re-simulation using gaussian splatting. arXiv preprint arXiv:2410.05111, 2024."},{"key":"e_1_3_2_1_8_1","volume-title":"Unimlvg: Unified framework for multi-view long video generation with comprehensive control capabilities for autonomous driving. arXiv preprint arXiv:2412.04842","author":"Chen Rui","year":"2024","unstructured":"Rui Chen, Zehuan Wu, Yichen Liu, Yuxin Guo, Jingcheng Ni, Haifeng Xia, and Siyu Xia. Unimlvg: Unified framework for multi-view long video generation with comprehensive control capabilities for autonomous driving. arXiv preprint arXiv:2412.04842, 2024."},{"key":"e_1_3_2_1_9_1","volume-title":"Magicdrive: Street view generation with diverse 3d geometry control. arXiv preprint arXiv:2310.02601","author":"Gao Ruiyuan","year":"2023","unstructured":"Ruiyuan Gao, Kai Chen, Enze Xie, Lanqing Hong, Zhenguo Li, Dit-Yan Yeung, and Qiang Xu. Magicdrive: Street view generation with diverse 3d geometry control. arXiv preprint arXiv:2310.02601, 2023."},{"key":"e_1_3_2_1_10_1","volume-title":"Magicdrive3d: Controllable 3d generation for any-view rendering in street scenes. arXiv preprint arXiv:2405.14475","author":"Gao Ruiyuan","year":"2024","unstructured":"Ruiyuan Gao, Kai Chen, Zhihao Li, Lanqing Hong, Zhenguo Li, and Qiang Xu. Magicdrive3d: Controllable 3d generation for any-view rendering in street scenes. arXiv preprint arXiv:2405.14475, 2024."},{"key":"e_1_3_2_1_11_1","volume-title":"Magicdrivedit: High-resolution long video generation for autonomous driving with adaptive control. arXiv preprint arXiv:2411.13807","author":"Gao Ruiyuan","year":"2024","unstructured":"Ruiyuan Gao, Kai Chen, Bo Xiao, Lanqing Hong, Zhenguo Li, and Qiang Xu. Magicdrivedit: High-resolution long video generation for autonomous driving with adaptive control. arXiv preprint arXiv:2411.13807, 2024."},{"key":"e_1_3_2_1_12_1","volume-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability. arXiv preprint arXiv:2405.17398","author":"Gao Shenyuan","year":"2024","unstructured":"Shenyuan Gao, Jiazhi Yang, Li Chen, Kashyap Chitta, Yihang Qiu, Andreas Geiger, Jun Zhang, and Hongyang Li. Vista: A generalizable driving world model with high fidelity and versatile controllability. arXiv preprint arXiv:2405.17398, 2024."},{"key":"e_1_3_2_1_13_1","volume-title":"Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598, 2022."},{"key":"e_1_3_2_1_14_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840--6851","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840--6851, 2020."},{"key":"e_1_3_2_1_15_1","volume-title":"Rangeldm: Fast realistic lidar point cloud generation. arXiv preprint arXiv:2403.10094","author":"Hu Qianjiang","year":"2024","unstructured":"Qianjiang Hu, Zhimin Zhang, and Wei Hu. Rangeldm: Fast realistic lidar point cloud generation. arXiv preprint arXiv:2403.10094, 2024."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01672"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01885"},{"key":"e_1_3_2_1_19_1","volume-title":"Adriver-i: A general world model for autonomous driving. arXiv preprint arXiv:2311.13549","author":"Jia Fan","year":"2023","unstructured":"Fan Jia, Weixin Mao, Yingfei Liu, Yucheng Zhao, Yuqing Wen, Chi Zhang, Xiangyu Zhang, and Tiancai Wang. Adriver-i: A general world model for autonomous driving. arXiv preprint arXiv:2311.13549, 2023."},{"key":"e_1_3_2_1_20_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013."},{"key":"e_1_3_2_1_21_1","volume-title":"et al. Uniscene: Unified occupancycentric driving scene generation. arXiv preprint arXiv:2412.05435","author":"Li Bohan","year":"2024","unstructured":"Bohan Li, Jiazhe Guo, Hongsi Liu, Yingshuang Zou, Yikang Ding, Xiwu Chen, Hu Zhu, Feiyang Tan, Chi Zhang, Tiancai Wang, et al. Uniscene: Unified occupancycentric driving scene generation. arXiv preprint arXiv:2412.05435, 2024."},{"key":"e_1_3_2_1_22_1","volume-title":"Syntheocc: Synthesize geometric-controlled street view images through 3d semantic mpis. arXiv preprint arXiv:2410.00337","author":"Li Leheng","year":"2024","unstructured":"Leheng Li, Weichao Qiu, Yingjie Cai, Xu Yan, Qing Lian, Bingbing Liu, and Ying-Cong Chen. Syntheocc: Synthesize geometric-controlled street view images through 3d semantic mpis. arXiv preprint arXiv:2410.00337, 2024."},{"key":"e_1_3_2_1_23_1","volume-title":"Advances in Neural Information Processing Systems","author":"Li Yanwei","year":"2022","unstructured":"Yanwei Li, Yilun Chen, Xiaojuan Qi, Zeming Li, Jian Sun, and Jiaya Jia. Unifying voxel-based representation with transformer for 3d object detection. In Advances in Neural Information Processing Systems, 2022."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"e_1_3_2_1_25_1","first-page":"10421","article-title":"A simple and robust lidarcamera fusion framework","volume":"35","author":"Liang Tingting","year":"2022","unstructured":"Tingting Liang, Hongwei Xie, Kaicheng Yu, Zhongyu Xia, Zhiwei Lin, Yongtao Wang, Tao Tang, Bing Wang, and Zhi Tang. Bevfusion: A simple and robust lidarcamera fusion framework. Advances in Neural Information Processing Systems, 35:10421--10434, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555376"},{"key":"e_1_3_2_1_27_1","volume-title":"Mvpbev: Multi-view perspective image generation from bev with test-time controllability and generalizability. arXiv preprint arXiv:2407.19468","author":"Liu Buyu","year":"2024","unstructured":"Buyu Liu, Kai Wang, Yansong Liu, Jun Bao, Tingting Han, and Jun Yu. Mvpbev: Multi-view perspective image generation from bev with test-time controllability and generalizability. arXiv preprint arXiv:2407.19468, 2024."},{"key":"e_1_3_2_1_28_1","volume-title":"ICLR","author":"Liu Xingchao","year":"2023","unstructured":"Xingchao Liu, Chengyue Gong, et al. Flow straight and fast: Learning to generate and transfer data with rectified flow. In ICLR, 2023."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"e_1_3_2_1_30_1","volume-title":"Seeing beyond views: Multi-view driving scene video generation with holistic attention. arXiv preprint arXiv:2412.03520","author":"Lu Hannan","year":"2024","unstructured":"Hannan Lu, Xiaohe Wu, Shudong Wang, Xiameng Qin, Xinyu Zhang, Junyu Han, Wangmeng Zuo, and Ji Tao. Seeing beyond views: Multi-view driving scene video generation with holistic attention. arXiv preprint arXiv:2412.03520, 2024."},{"key":"e_1_3_2_1_31_1","volume-title":"Wovogen: World volume-aware diffusion for controllable multi-camera driving scene generation. arXiv preprint arXiv:2312.02934","author":"Lu Jiachen","year":"2023","unstructured":"Jiachen Lu, Ze Huang, Jiahui Zhang, Zeyu Yang, and Li Zhang. Wovogen: World volume-aware diffusion for controllable multi-camera driving scene generation. arXiv preprint arXiv:2312.02934, 2023."},{"key":"e_1_3_2_1_32_1","volume-title":"et al. Infinicube: Unbounded and controllable dynamic 3d driving scene generation with world-guided video models. arXiv preprint arXiv:2412.03934","author":"Lu Yifan","year":"2024","unstructured":"Yifan Lu, Xuanchi Ren, Jiawei Yang, Tianchang Shen, Zhangjie Wu, Jun Gao, Yue Wang, Siheng Chen, Mike Chen, Sanja Fidler, et al. Infinicube: Unbounded and controllable dynamic 3d driving scene generation with world-guided video models. arXiv preprint arXiv:2412.03934, 2024."},{"key":"e_1_3_2_1_33_1","volume-title":"Unleashing generalization of end-to-end autonomous driving with controllable long video generation. arXiv preprint arXiv:2406.01349","author":"Ma Enhui","year":"2024","unstructured":"Enhui Ma, Lijun Zhou, Tao Tang, Zhan Zhang, Dong Han, Junpeng Jiang, Kun Zhan, Peng Jia, Xianpeng Lang, Haiyang Sun, et al. Unleashing generalization of end-to-end autonomous driving with controllable long video generation. arXiv preprint arXiv:2406.01349, 2024."},{"key":"e_1_3_2_1_34_1","volume-title":"Communications of the ACM","author":"Mildenhall Ben","year":"2021","unstructured":"Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. Nerf: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM, 2021."},{"key":"e_1_3_2_1_35_1","volume-title":"Lidar data synthesis with denoising diffusion probabilistic models. arXiv preprint arXiv:2309.09256","author":"Nakashima Kazuto","year":"2023","unstructured":"Kazuto Nakashima and Ryo Kurazume. Lidar data synthesis with denoising diffusion probabilistic models. arXiv preprint arXiv:2309.09256, 2023."},{"key":"e_1_3_2_1_36_1","first-page":"8162","volume-title":"ICML","author":"Nichol Alexander Quinn","year":"2021","unstructured":"Alexander Quinn Nichol and Prafulla Dhariwal. Improved denoising diffusion probabilistic models. In ICML, pages 8162--8171. PMLR, 2021."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_38_1","first-page":"194","volume-title":"Proceedings, Part XIV 16","author":"Philion Jonah","year":"2020","unstructured":"Jonah Philion and Sanja Fidler. Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XIV 16, pages 194--210. Springer, 2020."},{"key":"e_1_3_2_1_39_1","volume-title":"Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, 21(140):1--67","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, et al. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, 21(140):1--67, 2020."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01396"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_42_1","volume-title":"Street-view image generation from a bird's-eye view layout. arXiv preprint arXiv:2301.04634","author":"Swerdlow Alexander","year":"2023","unstructured":"Alexander Swerdlow, Runsheng Xu, and Bolei Zhou. Street-view image generation from a bird's-eye view layout. arXiv preprint arXiv:2301.04634, 2023."},{"key":"e_1_3_2_1_43_1","volume-title":"Lidarnerf: Novel lidar view synthesis via neural radiance fields. arXiv preprint arXiv:2304.10406","author":"Tao Tang","year":"2023","unstructured":"Tang Tao, Longfei Gao, Guangrun Wang, Yixing Lao, Peng Chen, Hengshuang Zhao, Dayang Hao, Xiaodan Liang, Mathieu Salzmann, and Kaicheng Yu. Lidarnerf: Novel lidar view synthesis via neural radiance fields. arXiv preprint arXiv:2304.10406, 2023."},{"key":"e_1_3_2_1_44_1","volume-title":"Neural discrete representation learning. Advances in neural information processing systems, 30","author":"Den Oord Aaron Van","year":"2017","unstructured":"Aaron Van Den Oord, Oriol Vinyals, et al. Neural discrete representation learning. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_3_2_1_45_1","unstructured":"Letian Wang Seung Wook Kim Jiawei Yang Cunjun Yu Boris Ivanovic Steven L Waslander Yue Wang Sanja Fidler Marco Pavone and Peter Karkus. Distillnerf: Perceiving 3d scenes from single-glance images by distilling neural fields and foundation model features. arXiv preprint arXiv:2406.12095 2024."},{"key":"e_1_3_2_1_46_1","volume-title":"Neus: Learning neural implicit surfaces by","author":"Wang Peng","year":"2021","unstructured":"Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, and Wenping Wang. Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction. arXiv preprint arXiv:2106.10689, 2021."},{"key":"e_1_3_2_1_47_1","volume-title":"Drivedreamer: Towards real-world-driven world models for autonomous driving. arXiv preprint arXiv:2309.09777","author":"Wang Xiaofeng","year":"2023","unstructured":"Xiaofeng Wang, Zheng Zhu, Guan Huang, Xinze Chen, and Jiwen Lu. Drivedreamer: Towards real-world-driven world models for autonomous driving. arXiv preprint arXiv:2309.09777, 2023."},{"key":"e_1_3_2_1_48_1","volume-title":"Driving into the future: Multiview visual forecasting and planning with world model for autonomous driving. arXiv preprint arXiv:2311.17918","author":"Wang Yuqi","year":"2023","unstructured":"Yuqi Wang, Jiawei He, Lue Fan, Hongxin Li, Yuntao Chen, and Zhaoxiang Zhang. Driving into the future: Multiview visual forecasting and planning with world model for autonomous driving. arXiv preprint arXiv:2311.17918, 2023."},{"key":"e_1_3_2_1_49_1","volume-title":"Panacea: Panoramic and controllable video generation for autonomous driving. arXiv preprint arXiv:2311.16813","author":"Wen Yuqing","year":"2023","unstructured":"Yuqing Wen, Yucheng Zhao, Yingfei Liu, Fan Jia, Yanhui Wang, Chong Luo, Chi Zhang, Tiancai Wang, Xiaoyan Sun, and Xiangyu Zhang. Panacea: Panoramic and controllable video generation for autonomous driving. arXiv preprint arXiv:2311.16813, 2023."},{"key":"e_1_3_2_1_50_1","volume-title":"Text2lidar: Textguided lidar point cloud generation via equirectangular transformer. arXiv preprint arXiv:2407.19628","author":"Wu Yang","year":"2024","unstructured":"Yang Wu, Kaihua Zhang, Jianjun Qian, Jin Xie, and Jian Yang. Text2lidar: Textguided lidar point cloud generation via equirectangular transformer. arXiv preprint arXiv:2407.19628, 2024."},{"key":"e_1_3_2_1_51_1","volume-title":"Glad: A streaming scene generator for autonomous driving. arXiv preprint arXiv:2503.00045","author":"Xie Bin","year":"2025","unstructured":"Bin Xie, Yingfei Liu, Tiancai Wang, Jiale Cao, and Xiangyu Zhang. Glad: A streaming scene generator for autonomous driving. arXiv preprint arXiv:2503.00045, 2025."},{"key":"e_1_3_2_1_52_1","volume-title":"M2bev: multi-camera joint 3d detection and segmentation with unified birds-eye view representation. arXiv preprint arXiv:2204.05088","author":"Xie Enze","year":"2022","unstructured":"Enze Xie, Zhiding Yu, Daquan Zhou, Jonah Philion, Anima Anandkumar, Sanja Fidler, Ping Luo, and Jose M Alvarez. M2bev: multi-camera joint 3d detection and segmentation with unified birds-eye view representation. arXiv preprint arXiv:2204.05088, 2022."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00110"},{"key":"e_1_3_2_1_54_1","volume-title":"Drivingsphere: Building a high-fidelity 4d world for closed-loop simulation. arXiv preprint arXiv:2411.11252","author":"Yan Tianyi","year":"2024","unstructured":"Tianyi Yan, Dongming Wu, Wencheng Han, Junpeng Jiang, Xia Zhou, Kun Zhan, Cheng-zhong Xu, and Jianbing Shen. Drivingsphere: Building a high-fidelity 4d world for closed-loop simulation. arXiv preprint arXiv:2411.11252, 2024."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01443"},{"key":"e_1_3_2_1_57_1","volume-title":"Bevcontrol: Accurately controlling street-view elements with multi-perspective consistency via bev sketch layout. arXiv preprint arXiv:2308.01661","author":"Yang Kairui","year":"2023","unstructured":"Kairui Yang, Enhui Ma, Jibin Peng, Qing Guo, Di Lin, and Kaicheng Yu. Bevcontrol: Accurately controlling street-view elements with multi-perspective consistency via bev sketch layout. arXiv preprint arXiv:2308.01661, 2023."},{"key":"e_1_3_2_1_58_1","first-page":"10371","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yang Lihe","year":"2024","unstructured":"Lihe Yang, Bingyi Kang, Zilong Huang, Xiaogang Xu, Jiashi Feng, and Hengshuang Zhao. Depth anything: Unleashing the power of large-scale unlabeled data. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pages 10371--10381, 2024."},{"key":"e_1_3_2_1_59_1","volume-title":"Mygo: Consistent and controllable multi-view driving video generation with camera control. arXiv preprint arXiv:2409.06189","author":"Yao Yining","year":"2024","unstructured":"Yining Yao, Xi Guo, Chenjing Ding, and Wei Wu. Mygo: Consistent and controllable multi-view driving video generation with camera control. arXiv preprint arXiv:2409.06189, 2024."},{"key":"e_1_3_2_1_60_1","volume-title":"et al. Fusionad: Multimodality fusion for prediction and planning tasks of autonomous driving. arXiv preprint arXiv:2308.01006","author":"Ye Tengju","year":"2023","unstructured":"Tengju Ye, Wei Jing, Chunyong Hu, Shikun Huang, Lingping Gao, Fangzhen Li, Jingke Wang, Ke Guo, Wencong Xiao, Weibo Mao, et al. Fusionad: Multimodality fusion for prediction and planning tasks of autonomous driving. arXiv preprint arXiv:2308.01006, 2023."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00537"},{"key":"e_1_3_2_1_64_1","volume-title":"Drivedreamer-2: Llm-enhanced world models for diverse driving video generation. arXiv preprint arXiv:2403.06845","author":"Zhao Guosheng","year":"2024","unstructured":"Guosheng Zhao, Xiaofeng Wang, Zheng Zhu, Xinze Chen, Guan Huang, Xiaoyi Bao, and Xingang Wang. Drivedreamer-2: Llm-enhanced world models for diverse driving video generation. arXiv preprint arXiv:2403.06845, 2024."},{"key":"e_1_3_2_1_65_1","volume-title":"Open-sora: Democratizing efficient video production for all. arXiv preprint arXiv:2412.20404","author":"Zheng Zangwei","year":"2024","unstructured":"Zangwei Zheng, Xiangyu Peng, Tianji Yang, Chenhui Shen, Shenggui Li, Hongxin Liu, Yukun Zhou, Tianyi Li, and Yang You. Open-sora: Democratizing efficient video production for all. arXiv preprint arXiv:2412.20404, 2024."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"e_1_3_2_1_67_1","volume-title":"Mudg: Taming multi-modal diffusion with gaussian splatting for urban scene reconstruction. arXiv preprint arXiv:2503.10604","author":"Zou Yingshuang","year":"2025","unstructured":"Yingshuang Zou, Yikang Ding, Chuanrui Zhang, Jiazhe Guo, Bohan Li, Xiaoyang Lyu, Feiyang Tan, Xiaojuan Qi, and Haoqian Wang. Mudg: Taming multi-modal diffusion with gaussian splatting for urban scene reconstruction. arXiv preprint arXiv:2503.10604, 2025."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_2"},{"key":"e_1_3_2_1_69_1","volume-title":"Lidardm: Generative lidar simulation in a generated world. arXiv preprint arXiv:2404.02903","author":"Zyrianov Vlas","year":"2024","unstructured":"Vlas Zyrianov, Henry Che, Zhijian Liu, and Shenlong Wang. Lidardm: Generative lidar simulation in a generated world. arXiv preprint arXiv:2404.02903, 2024."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754772","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:58:33Z","timestamp":1765342713000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754772"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":69,"alternative-id":["10.1145\/3746027.3754772","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754772","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}