{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:20:27Z","timestamp":1783574427060,"version":"3.55.0"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031728891","type":"print"},{"value":"9783031728907","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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\/978-3-031-72890-7_2","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:46:45Z","timestamp":1733514405000},"page":"19-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Mask2Map: Vectorized HD Map Construction Using Bird\u2019s Eye View Segmentation Masks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1151-4056","authenticated-orcid":false,"given":"Sehwan","family":"Choi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0704-3619","authenticated-orcid":false,"given":"Jungho","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9537-6759","authenticated-orcid":false,"given":"Hongjae","family":"Shin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3733-0148","authenticated-orcid":false,"given":"Jun Won","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Antonello, M., Carraro, M., Pierobon, M., Menegatti, E.: Fast and robust detection of fallen people from a mobile robot. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4159\u20134166. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206276"},{"key":"2_CR2","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 (CVPR), pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"2_CR3","unstructured":"Caesar, H., et al.: nuplan: a closed-loop ml-based planning benchmark for autonomous vehicles. arXiv preprint arXiv:2106.11810 (2021)"},{"key":"2_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"2_CR6","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: Advances in Neural Information Processing Systems, pp. 17864\u201317875 (2021)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Choi, S., Kim, J., Yun, J., Choi, J.W.: R-pred: two-stage motion prediction via tube-query attention-based trajectory refinement. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 8525\u20138535 (2023)","DOI":"10.1109\/ICCV51070.2023.00783"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Da, F., Zhang, Y.: Path-aware graph attention for HD maps in motion prediction. In: International Conference on Robotics and Automation (ICRA), pp. 6430\u20136436. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812100"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Ding, W., Qiao, L., Qiu, X., Zhang, C.: PivotNet: vectorized pivot learning for end-to-end HD map construction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3672\u20133682 (2023)","DOI":"10.1109\/ICCV51070.2023.00340"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Gao, J., et al.: VectorNet: encoding HD maps and agent dynamics from vectorized representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11525\u201311533 (2020)","DOI":"10.1109\/CVPR42600.2020.01154"},{"issue":"2","key":"2_CR11","first-page":"943","volume":"3","author":"AM Hasan","year":"2009","unstructured":"Hasan, A.M., Samsudin, K., Ramli, A.R., Azmir, R., Ismaeel, S.: A review of navigation systems (integration and algorithms). Aust. J. Basic Appl. Sci. (AJBAS) 3(2), 943\u2013959 (2009)","journal-title":"Aust. J. Basic Appl. Sci. (AJBAS)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Kim, B., et al.: LaPred: lane-aware prediction of multi-modal future trajectories of dynamic agents. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14636\u201314645 (2021)","DOI":"10.1109\/CVPR46437.2021.01440"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: PointPillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: DN-DETR: Accelerate DETR training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Xu, H., Liu, S., Zhang, L., Ni, L.M., Shum, H.Y.: Mask DINO: towards a unified transformer-based framework for object detection and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3041\u20133050 (2023)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Li, Q., Wang, Y., Wang, Y., Zhao, H.: HDMapNet: an online HD map construction and evaluation framework. In: International Conference on Robotics and Automation (ICRA), pp. 4628\u20134634. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"2_CR18","doi-asserted-by":"publisher","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\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision (ECCV), pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Liang, M., et al.: Learning lane graph representations for motion forecasting. In: European Conference on Computer Vision (ECCV), pp. 541\u2013556 (2020)","DOI":"10.1007\/978-3-030-58536-5_32"},{"key":"2_CR20","unstructured":"Liao, B., et al.: MapTR: structured modeling and learning for online vectorized HD map construction. In: The Eleventh International Conference on Learning Representations (ICLR) (2023)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Liao, B., et al.: MapTRv2: an end-to-end framework for online vectorized HD map construction. arXiv preprint arXiv:2308.05736 (2023)","DOI":"10.1007\/s11263-024-02235-z"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"2_CR23","unstructured":"Liu, S., et al.: DAB-DETR: dynamic anchor boxes are better queries for DETR. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"2_CR24","unstructured":"Liu, Y., Yuan, T., Wang, Y., Wang, Y., Zhao, H.: VectorMapNet: end-to-end vectorized HD map learning. In: International Conference on Machine Learning (ICML), pp. 22352\u201322369. PMLR (2023)"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: PETRv2: a unified framework for 3D perception from multi-camera images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3262\u20133272 (2023)","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional DETR for fast training convergence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Peng, L., Chen, Z., Fu, Z., Liang, P., Cheng, E.: BEVSegFormer: bird\u2019s eye view semantic segmentation from arbitrary camera rigs. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 5935\u20135943 (2023)","DOI":"10.1109\/WACV56688.2023.00588"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: European Conference on Computer Vision (ECCV), pp. 194\u2013210 (2020)","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"2_CR29","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++ deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS), pp. 5105\u20135114 (2017)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Qiao, L., Ding, W., Qiu, X., Zhang, C.: End-to-end vectorized HD-map construction with piecewise bezier curve. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13218\u201313228 (2023)","DOI":"10.1109\/CVPR52729.2023.01270"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Reiher, L., Lampe, B., Eckstein, L.: A sim2real deep learning approach for the transformation of images from multiple vehicle-mounted cameras to a semantically segmented image in bird\u2019s eye view. In: 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), pp.\u00a01\u20137. IEEE (2020)","DOI":"10.1109\/ITSC45102.2020.9294462"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Roddick, T., Cipolla, R.: Predicting semantic map representations from images using pyramid occupancy networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11138\u201311147 (2020)","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Shan, T., Englot, B.: Lego-loam: lightweight and ground-optimized lidar odometry and mapping on variable terrain. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4758\u20134765. IEEE (2018)","DOI":"10.1109\/IROS.2018.8594299"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Shan, T., Englot, B., Meyers, D., Wang, W., Ratti, C., Rus, D.: Lio-sam: tightly-coupled lidar inertial odometry via smoothing and mapping. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5135\u20135142. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341176"},{"key":"2_CR35","unstructured":"Shin, J., Rameau, F., Jeong, H., Kum, D.: Instagram: instance-level graph modeling for vectorized HD map learning. arXiv preprint arXiv:2301.04470 (2023)"},{"key":"2_CR36","unstructured":"Wilson, B., et\u00a0al.: Argoverse 2: next generation datasets for self-driving perception and forecasting. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (NeurIPS) (2021)"},{"key":"2_CR37","unstructured":"Xu, R., Tu, Z., Xiang, H., Shao, W., Zhou, B., Ma, J.: CoBEVT: cooperative bird\u2019s eye view semantic segmentation with sparse transformers. In: Conference on Robot Learning (CoRL), pp. 989\u20131000. PMLR (2023)"},{"key":"2_CR38","unstructured":"Xu, Z., Wong, K.K., Zhao, H.: Insightmapper: a closer look at inner-instance information for vectorized high-definition mapping. arXiv preprint arXiv:2308.08543 (2023)"},{"issue":"10","key":"2_CR39","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: SECOND: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)","journal-title":"Sensors"},{"key":"2_CR40","unstructured":"Zhang, G., et\u00a0al.: Online map vectorization for autonomous driving: a rasterization perspective. In: Advances in Neural Information Processing Systems, pp. 31865\u201331877 (2023)"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: MP-former: mask-piloted transformer for image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18074\u201318083 (2023)","DOI":"10.1109\/CVPR52729.2023.01733"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, J., Singh, S.: LOAM: lidar odometry and mapping in real-time. In: Robotics: Science and Systems (RSS), vol.\u00a02, pp.\u00a01\u20139. Berkeley, CA (2014)","DOI":"10.15607\/RSS.2014.X.007"},{"key":"2_CR43","unstructured":"Zhang, Y., et al.: BEVerse: unified perception and prediction in birds-eye-view for vision-centric autonomous driving. arXiv preprint arXiv:2205.09743 (2022)"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, B., Kr\u00e4henb\u00fchl, P.: Cross-view transformers for real-time map-view semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13760\u201313769 (2022)","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"2_CR45","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (ICLR) (2021)"}],"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\/978-3-031-72890-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:03:17Z","timestamp":1733515397000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72890-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9783031728891","9783031728907"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72890-7_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 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"}}]}}