{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:46:09Z","timestamp":1765309569501,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China (NSFC)","award":["62376060"],"award-info":[{"award-number":["62376060"]}]},{"name":"NIO University Programme (NIO UP)"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754831","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"7386-7394","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MS-Road: Towards Spatiotemporal-Consistent Large-Scale Road Reconstruction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5273-3658","authenticated-orcid":false,"given":"Ze","family":"Huang","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4225-2110","authenticated-orcid":false,"given":"Zhongyang","family":"Xiao","sequence":"additional","affiliation":[{"name":"NIO, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4766-2722","authenticated-orcid":false,"given":"Mingliang","family":"Song","sequence":"additional","affiliation":[{"name":"NIO, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0252-3056","authenticated-orcid":false,"given":"Yu","family":"Fang","sequence":"additional","affiliation":[{"name":"NIO, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1913-4829","authenticated-orcid":false,"given":"Hongyuan","family":"Yuan","sequence":"additional","affiliation":[{"name":"NIO, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0393-8665","authenticated-orcid":false,"given":"Kevin Li","family":"Sun","sequence":"additional","affiliation":[{"name":"Bosch, XC, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1031-5420","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Building rome in a day. Commun. ACM","author":"Agarwal Sameer","year":"2011","unstructured":"Sameer Agarwal, Yasutaka Furukawa, Noah Snavely, Ian Simon, Brian Curless, Steven M Seitz, and Richard Szeliski. 2011. Building rome in a day. Commun. ACM (2011)."},{"key":"e_1_3_2_2_2_1","volume-title":"Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In ICCV.","author":"Barron Jonathan T","year":"2021","unstructured":"Jonathan T Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman, Ricardo Martin-Brualla, and Pratul P Srinivasan. 2021. Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In ICCV."},{"key":"e_1_3_2_2_3_1","volume-title":"Road surface reconstruction by stereo vision. PFG-Journal of Photogrammetry, Remote Sensing and Geoinformation Science","author":"Brunken Hauke","year":"2020","unstructured":"Hauke Brunken and Clemens G\u00fchmann. 2020. Road surface reconstruction by stereo vision. PFG-Journal of Photogrammetry, Remote Sensing and Geoinformation Science (2020)."},{"key":"e_1_3_2_2_4_1","unstructured":"Holger Caesar Varun Bankiti Alex H Lang Sourabh Vora Venice Erin Liong Qiang Xu Anush Krishnan Yu Pan Giancarlo Baldan and Oscar Beijbom. [n.d.]. nuscenes: A multimodal dataset for autonomous driving. In CVPR. 11621-11631."},{"key":"e_1_3_2_2_5_1","volume-title":"CSS: Overcoming Pose and Scene Challenges in Crowd-Sourced 3D Gaussian Splatting. arXiv preprint","author":"Chen Runze","year":"2024","unstructured":"Runze Chen, Mingyu Xiao, Haiyong Luo, Fang Zhao, Fan Wu, Hao Xiong, Qi Liu, and Meng Song. 2024. CSS: Overcoming Pose and Scene Challenges in Crowd-Sourced 3D Gaussian Splatting. arXiv preprint (2024)."},{"key":"e_1_3_2_2_6_1","unstructured":"Bowen Cheng Alexander G. Schwing and Alexander Kirillov. 2021. Per-Pixel Classification is Not All You Need for Semantic Segmentation. NeurIPS."},{"key":"e_1_3_2_2_7_1","unstructured":"Hainan Cui Xiang Gao Shuhan Shen and Zhanyi Hu. 2017. HSfM: Hybrid structure-from-motion. In CVPR."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2808770"},{"key":"e_1_3_2_2_9_1","volume-title":"Rethinking road surface 3-d reconstruction and pothole detection: From perspective transformation to disparity map segmentation","author":"Fan Rui","year":"2021","unstructured":"Rui Fan, Umar Ozgunalp, Yuan Wang, Ming Liu, and Ioannis Pitas. 2021. Rethinking road surface 3-d reconstruction and pothole detection: From perspective transformation to disparity map segmentation. IEEE Transactions on Cybernetics (2021)."},{"key":"e_1_3_2_2_10_1","volume-title":"RoGS: Large Scale Road Surface Reconstruction based on 2D Gaussian Splatting. arXiv preprint","author":"Feng Zhiheng","year":"2024","unstructured":"Zhiheng Feng, Wenhua Wu, and Hesheng Wang. 2024. RoGS: Large Scale Road Surface Reconstruction based on 2D Gaussian Splatting. arXiv preprint (2024)."},{"key":"e_1_3_2_2_11_1","unstructured":"Yang Fu Sifei Liu Amey Kulkarni Jan Kautz Alexei A Efros and Xiaolong Wang. 2024. Colmap-free 3d gaussian splatting. In CVPR."},{"key":"e_1_3_2_2_12_1","volume-title":"Vision meets robotics: The kitti dataset. The International Journal of Robotics Research","author":"Geiger Andreas","year":"2013","unstructured":"Andreas Geiger, Philip Lenz, Christoph Stiller, and Raquel Urtasun. 2013. Vision meets robotics: The kitti dataset. The International Journal of Robotics Research (2013)."},{"key":"e_1_3_2_2_13_1","volume-title":"Automatic reconstruction of road surface features by using terrestrial mobile lidar. Automation in Construction","author":"Guo Jenny","year":"2015","unstructured":"Jenny Guo, Meng-Ju Tsai, and Jen-Yu Han. 2015. Automatic reconstruction of road surface features by using terrestrial mobile lidar. Automation in Construction (2015)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Binbin Huang Zehao Yu Anpei Chen Andreas Geiger and Shenghua Gao. 2024. 2d gaussian splatting for geometrically accurate radiance fields. In ACM SIGGRAPH.","DOI":"10.1145\/3641519.3657428"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Justin Johnson Nikhila Ravi Jeremy Reizenstein David Novotny Shubham Tulsiani Christoph Lassner and Steve Branson. 2020. Accelerating 3d deep learning with pytorch3d. In SIGGRAPH Asia 2020 courses.","DOI":"10.1145\/3415263.3419160"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Angjoo Kanazawa Shubham Tulsiani Alexei A Efros and Jitendra Malik. 2018. Learning category-specific mesh reconstruction from image collections. In ECCV.","DOI":"10.1007\/978-3-030-01267-0_23"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023. 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. (2023).","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_2_18_1","volume-title":"Wildgaussians: 3d gaussian splatting in the wild. arXiv preprint","author":"Kulhanek Jonas","year":"2024","unstructured":"Jonas Kulhanek, Songyou Peng, Zuzana Kukelova, Marc Pollefeys, and Torsten Sattler. 2024. Wildgaussians: 3d gaussian splatting in the wild. arXiv preprint (2024)."},{"key":"e_1_3_2_2_19_1","volume-title":"Jonathan T Barron, Alexey Dosovitskiy, and Daniel Duckworth.","author":"Martin-Brualla Ricardo","year":"2021","unstructured":"Ricardo Martin-Brualla, Noha Radwan, Mehdi SM Sajjadi, Jonathan T Barron, Alexey Dosovitskiy, and Daniel Duckworth. 2021. Nerf in the wild: Neural radiance fields for unconstrained photo collections. In CVPR."},{"key":"e_1_3_2_2_20_1","volume-title":"Rome: Towards large scale road surface reconstruction via mesh representation","author":"Mei Ruohong","year":"2024","unstructured":"Ruohong Mei, Wei Sui, Jiaxin Zhang, Xue Qin, Gang Wang, Tao Peng, Tao Chen, and Cong Yang. 2024. Rome: Towards large scale road surface reconstruction via mesh representation. IEEE Transactions on Intelligent Vehicles (2024)."},{"key":"e_1_3_2_2_21_1","volume-title":"Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM","author":"Mildenhall Ben","year":"2021","unstructured":"Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM (2021)."},{"key":"e_1_3_2_2_22_1","volume-title":"Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras","author":"Mur-Artal Raul","year":"2017","unstructured":"Raul Mur-Artal and Juan D Tard\u00f3s. 2017. Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras. IEEE transactions on robotics (2017)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Junyi Pan Xiaoguang Han Weikai Chen Jiapeng Tang and Kui Jia. 2019. Deep mesh reconstruction from single rgb images via topology modification networks. In ICCV.","DOI":"10.1109\/ICCV.2019.01006"},{"key":"e_1_3_2_2_24_1","volume-title":"Crowd-Sourced NeRF: Collecting Data From Production Vehicles for 3D Street View Reconstruction","author":"Qin Tong","year":"2024","unstructured":"Tong Qin, Changze Li, Haoyang Ye, Shaowei Wan, Minzhen Li, Hongwei Liu, and Ming Yang. 2024. Crowd-Sourced NeRF: Collecting Data From Production Vehicles for 3D Street View Reconstruction. IEEE Transactions on Intelligent Transportation Systems (2024)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916881"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Johannes L Schonberger and Jan-Michael Frahm. 2016. Structure-from-motion revisited. In CVPR.","DOI":"10.1109\/CVPR.2016.445"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Johannes L Sch\u00f6nberger Enliang Zheng Jan-Michael Frahm and Marc Pollefeys. 2016. Pixelwise view selection for unstructured multi-view stereo. In ECCV.","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"e_1_3_2_2_28_1","volume-title":"Block-nerf: Scalable large scene neural view synthesis. In CVPR.","author":"Tancik Matthew","year":"2022","unstructured":"Matthew Tancik, Vincent Casser, Xinchen Yan, Sabeek Pradhan, Ben Mildenhall, Pratul P Srinivasan, Jonathan T Barron, and Henrik Kretzschmar. 2022. Block-nerf: Scalable large scene neural view synthesis. In CVPR."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"Julien PC Valentin Sunando Sengupta Jonathan Warrell Ali Shahrokni and Philip HS Torr. 2013. Mesh based semantic modelling for indoor and outdoor scenes. In CVPR.","DOI":"10.1109\/CVPR.2013.269"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Peng Wang Yuan Liu Zhaoxi Chen Lingjie Liu Ziwei Liu Taku Komura Christian Theobalt and Wenping Wang. 2023. F2-nerf: Fast neural radiance field training with free camera trajectories. In CVPR.","DOI":"10.1109\/CVPR52729.2023.00404"},{"key":"e_1_3_2_2_31_1","volume-title":"NeRO: Neural Road Surface Reconstruction. arXiv preprint","author":"Wang Ruibo","year":"2024","unstructured":"Ruibo Wang, Song Zhang, Ping Huang, Donghai Zhang, and Haoyu Chen. 2024b. NeRO: Neural Road Surface Reconstruction. arXiv preprint (2024)."},{"key":"e_1_3_2_2_32_1","volume-title":"WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections. arXiv preprint","author":"Wang Yuze","year":"2024","unstructured":"Yuze Wang, Junyi Wang, and Yue Qi. 2024a. WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections. arXiv preprint (2024)."},{"key":"e_1_3_2_2_33_1","unstructured":"Changchang Wu. 2013. Towards linear-time incremental structure from motion. In 3DV."},{"key":"e_1_3_2_2_34_1","volume-title":"Emie-map: Large-scale road surface reconstruction based on explicit mesh and implicit encoding. In ECCV.","author":"Wu Wenhua","year":"2024","unstructured":"Wenhua Wu, Qi Wang, Guangming Wang, Junping Wang, Tiankun Zhao, Yang Liu, Dongchao Gao, Zhe Liu, and Hesheng Wang. 2024. Emie-map: Large-scale road surface reconstruction based on explicit mesh and implicit encoding. In ECCV."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Yifan Yang Shuhai Zhang Zixiong Huang Yubing Zhang and Mingkui Tan. 2023. Cross-ray neural radiance fields for novel-view synthesis from unconstrained image collections. In ICCV.","DOI":"10.1109\/ICCV51070.2023.01457"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Dongbin Zhang Chuming Wang Weitao Wang Peihao Li Minghan Qin and Haoqian Wang. 2024. Gaussian in the wild: 3d gaussian splatting for unconstrained image collections. In ECCV.","DOI":"10.1007\/978-3-031-73116-7_20"},{"key":"e_1_3_2_2_37_1","volume-title":"A road surface reconstruction dataset for autonomous driving. Scientific data","author":"Zhao Tong","year":"2024","unstructured":"Tong Zhao, Yichen Xie, Mingyu Ding, Lei Yang, Masayoshi Tomizuka, and Yintao Wei. 2024a. A road surface reconstruction dataset for autonomous driving. Scientific data (2024)."},{"key":"e_1_3_2_2_38_1","volume-title":"RoadBEV: Road Surface Reconstruction in Bird's Eye View. arXiv preprint","author":"Zhao Tong","year":"2024","unstructured":"Tong Zhao, Lei Yang, Yichen Xie, Mingyu Ding, Masayoshi Tomizuka, and Yintao Wei. 2024b. RoadBEV: Road Surface Reconstruction in Bird's Eye View. arXiv preprint (2024)."},{"key":"e_1_3_2_2_39_1","volume-title":"DP-MVS: Detail preserving multi-view surface reconstruction of large-scale scenes. Remote Sensing","author":"Zhou Liyang","year":"2021","unstructured":"Liyang Zhou, Zhuang Zhang, Hanqing Jiang, Han Sun, Hujun Bao, and Guofeng Zhang. 2021. DP-MVS: Detail preserving multi-view surface reconstruction of large-scale scenes. Remote Sensing (2021). n"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754831","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:42:25Z","timestamp":1765309345000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754831"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":39,"alternative-id":["10.1145\/3746027.3754831","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754831","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"}}]}}