{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:09:32Z","timestamp":1769634572206,"version":"3.49.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031736353","type":"print"},{"value":"9783031736360","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T00:00:00Z","timestamp":1730764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T00:00:00Z","timestamp":1730764800000},"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\/978-3-031-73636-0_7","type":"book-chapter","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T15:02:39Z","timestamp":1730732559000},"page":"110-126","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["LetsMap: Unsupervised Representation Learning for\u00a0Label-Efficient Semantic BEV Mapping"],"prefix":"10.1007","author":[{"given":"Nikhil","family":"Gosala","sequence":"first","affiliation":[]},{"given":"K\u00fcrsat","family":"Petek","sequence":"additional","affiliation":[]},{"given":"B.","family":"Ravi Kiran","sequence":"additional","affiliation":[]},{"given":"Senthil","family":"Yogamani","sequence":"additional","affiliation":[]},{"given":"Paulo","family":"Drews-Jr","sequence":"additional","affiliation":[]},{"given":"Wolfram","family":"Burgard","sequence":"additional","affiliation":[]},{"given":"Abhinav","family":"Valada","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,5]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Bustos, A.P., Chin, T.J., Eriksson, A., Reid, I.: Visual SLAM: why bundle adjust? In: International Conference on Robotics & Automation, pp. 2385\u20132391 (2019)","DOI":"10.1109\/ICRA.2019.8793749"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"7_CR3","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: Proceedings of the Conference on Neural Information Processing Systems (NIPS) (2020)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"7_CR5","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, vol.\u00a0119, pp. 1597\u20131607 (2020)"},{"issue":"8","key":"7_CR6","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1109\/TPAMI.2009.161","volume":"32","author":"Y Furukawa","year":"2009","unstructured":"Furukawa, Y., Ponce, J.: Accurate, dense, and robust multiview stereopsis. IEEE Trans. Pattern Anal. Mach. Intell. 32(8), 1362\u20131376 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Gao, S., Wang, Q., Sun, Y.: S2G2: semi-supervised semantic bird-eye-view grid-map generation using a monocular camera for autonomous driving. IEEE Robot. Autom. Lett. (2022)","DOI":"10.1109\/LRA.2022.3208377"},{"key":"7_CR8","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: International Conference on Learning Representations (2018)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Gosala, N., Petek, K., Drews-Jr, P.L.J., Burgard, W., Valada, A.: SkyEye: self-supervised bird\u2019s-eye-view semantic mapping using monocular frontal view images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 14901\u201314910 (2023)","DOI":"10.1109\/CVPR52729.2023.01431"},{"issue":"2","key":"7_CR10","doi-asserted-by":"publisher","first-page":"1968","DOI":"10.1109\/LRA.2022.3142418","volume":"7","author":"N Gosala","year":"2022","unstructured":"Gosala, N., Valada, A.: Bird\u2019s-eye-view panoptic segmentation using monocular frontal view images. IEEE Robot. Autom. Lett. 7(2), 1968\u20131975 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Fang, Z., Li, J., Ambrus, R., Fragkiadaki, K.: Simple-BEV: what really matters for multi-sensor BEV perception? In: International Conference\u00a0on Robotics & Automation, pp. 2759\u20132765 (2023)","DOI":"10.1109\/ICRA48891.2023.10160831"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: IEEE Conference\u00a0on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: IEEE Conference\u00a0on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Hindel, J., Gosala, N., Bregler, K., Valada, A.: INoD: injected noise discriminator for self-supervised representation learning in agricultural fields. IEEE Robot. Autom. Lett. (2023)","DOI":"10.1109\/LRA.2023.3301269"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Hurtado, J.V., Valada, A.: Semantic scene segmentation for robotics. In: Deep Learning for Robot Perception and Cognition, pp. 279\u2013311. Elsevier (2022)","DOI":"10.1016\/B978-0-32-385787-1.00017-8"},{"key":"7_CR16","doi-asserted-by":"publisher","first-page":"100338","DOI":"10.1016\/j.cosrev.2020.100338","volume":"39","author":"AK Ingale","year":"2021","unstructured":"Ingale, A.K., et al.: Real-time 3D reconstruction techniques applied in dynamic scenes: a systematic literature review. Comput. Sci. Rev. 39, 100338 (2021)","journal-title":"Comput. Sci. Rev."},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Irshad, M.Z., et al.: NeO 360: neural fields for sparse view synthesis of outdoor scenes. In: International Conference\u00a0on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00843"},{"key":"7_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/978-3-031-20086-1_12","volume-title":"Computer Vision \u2013 ECCV 2022","author":"N Kulkarni","year":"2022","unstructured":"Kulkarni, N., Johnson, J., Fouhey, D.F.: Directed ray distance functions for 3D scene reconstruction. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13662, pp. 201\u2013219. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_12"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Lang, C., Braun, A., Schillingmann, L., Haug, K., Valada, A.: Self-supervised representation learning from temporal ordering of automated driving sequences. IEEE Robot. Autom. Lett. (2024)","DOI":"10.1109\/LRA.2024.3354552"},{"key":"7_CR20","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\u00a0on Robotics & Automation, pp. 4628\u20134634 (2022)","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Liao, Y., Xie, J., Geiger, A.: KITTI-360: a novel dataset and benchmarks for urban scene understanding in 2D and 3D. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: BEVFusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation, pp. 2774\u20132781 (2023)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"issue":"2","key":"7_CR23","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1109\/LRA.2019.2891028","volume":"4","author":"C Lu","year":"2019","unstructured":"Lu, C., van de Molengraft, M.J.G., Dubbelman, G.: Monocular semantic occupancy grid mapping with convolutional variational encoder-decoder networks. IEEE Robot. Autom. Lett. 4(2), 445\u2013452 (2019)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"3","key":"7_CR24","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/BF00201978","volume":"64","author":"HA Mallot","year":"1991","unstructured":"Mallot, H.A., B\u00fclthoff, H.H., Little, J., Bohrer, S.: Inverse perspective mapping simplifies optical flow computation and obstacle detection. Biol. Cybern. 64(3), 177\u2013185 (1991)","journal-title":"Biol. Cybern."},{"key":"7_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-58452-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Mildenhall","year":"2020","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405\u2013421. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24"},{"key":"7_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46466-4_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Noroozi","year":"2016","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_5"},{"key":"7_CR27","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"issue":"3","key":"7_CR28","doi-asserted-by":"publisher","first-page":"4867","DOI":"10.1109\/LRA.2020.3004325","volume":"5","author":"B Pan","year":"2020","unstructured":"Pan, B., Sun, J., Leung, H.Y.T., Andonian, A., Zhou, B.: Cross-view semantic segmentation for sensing surroundings. IEEE Robot. Autom. Lett. 5(3), 4867\u20134873 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"7_CR29","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":"7_CR30","doi-asserted-by":"crossref","unstructured":"Roddick, T., Cipolla, R.: Predicting semantic map representations from images using pyramid occupancy networks. In: IEEE Conference\u00a0on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Saha, A., Mendez, O., Russell, C., Bowden, R.: Translating images into maps. In: International Conference on Robotics & Automation, pp. 9200\u20139206 (2022)","DOI":"10.1109\/ICRA46639.2022.9811901"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Schramm, J., V\u00f6disch, N., Petek, K., Kiran, B.R., Yogamani, S., Burgard, W., Valada, A.: BEVCar: camera-radar fusion for BEV map and object segmentation. arXiv preprint arXiv:2403.11761 (2024)","DOI":"10.1109\/IROS58592.2024.10802147"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: IEEE Conference\u00a0on Computer Vision and Pattern Recognition, pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"7_CR34","unstructured":"Tian, K., Jiang, Y., Diao, Q., Lin, C., Wang, L., Yuan, Z.: Designing BERT for convolutional networks: Sparse and hierarchical masked modeling. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"V\u00f6disch, N., Cattaneo, D., Burgard, W., Valada, A.: Continual SLAM: beyond lifelong simultaneous localization and mapping through continual learning. arXiv preprint arXiv:2203.01578 (2022)","DOI":"10.1007\/978-3-031-25555-7_3"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Wimbauer, F., Yang, N., Rupprecht, C., Cremers, D.: Behind the scenes: density fields for single view reconstruction, pp. 9076\u20139086 (2023)","DOI":"10.1109\/CVPR52729.2023.00876"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Yang, C., et al.: BEVFormer v2: adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision. In: IEEE Conference\u00a0on Computer Vision and Pattern Recognition, pp. 17830\u201317839 (2023)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A.: PixelNeRF: neural radiance fields from one or few images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4578\u20134587 (2021)","DOI":"10.1109\/CVPR46437.2021.00455"}],"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\/978-3-031-73636-0_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T10:52:59Z","timestamp":1765018379000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73636-0_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,5]]},"ISBN":["9783031736353","9783031736360"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73636-0_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,5]]},"assertion":[{"value":"5 November 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"}}]}}