{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T15:57:55Z","timestamp":1778947075341,"version":"3.51.4"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585679","type":"print"},{"value":"9783030585686","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58568-6_12","type":"book-chapter","created":{"date-parts":[[2020,11,12]],"date-time":"2020-11-12T14:04:57Z","timestamp":1605189897000},"page":"194-210","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1040,"title":["Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D"],"prefix":"10.1007","author":[{"given":"Jonah","family":"Philion","sequence":"first","affiliation":[]},{"given":"Sanja","family":"Fidler","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,13]]},"reference":[{"key":"12_CR1","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. CoRR arXiv:abs\/1511.00561 (2015). http:\/\/arxiv.org\/abs\/1511.00561"},{"key":"12_CR2","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. CoRR arXiv:abs\/1903.11027 (2019). http:\/\/arxiv.org\/abs\/1903.11027"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Chang, M.F., et al.: Argoverse: 3D tracking and forecasting with rich maps. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00895"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., Urtasun, R.: Monocular 3D object detection for autonomous driving. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2147\u20132156 (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"12_CR5","unstructured":"Ghiasi, G., Lin, T., Le, Q.V.: DropBlock: a regularization method for convolutional networks. CoRR arXiv:abs\/1810.12890 (2018). http:\/\/arxiv.org\/abs\/1810.12890"},{"key":"12_CR6","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http:\/\/www.deeplearningbook.org"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. CoRR arXiv:abs\/1703.06870 (2017). http:\/\/arxiv.org\/abs\/1703.06870","DOI":"10.1109\/ICCV.2017.322"},{"key":"12_CR8","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR arXiv:abs\/1512.03385 (2015). http:\/\/arxiv.org\/abs\/1512.03385"},{"key":"12_CR9","unstructured":"Hendy, N., et al.: Fishing net: future inference of semantic heatmaps in grids (2020)"},{"key":"12_CR10","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR arXiv:abs\/1502.03167 (2015). http:\/\/arxiv.org\/abs\/1502.03167"},{"key":"12_CR11","unstructured":"Kayhan, O.S., Gemert, J.C.v.: On translation invariance in CNNS: convolutional layers can exploit absolute spatial location. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Kehl, W., Manhardt, F., Tombari, F., Ilic, S., Navab, N.: SSD-6D: making rgb-based 3D detection and 6d pose estimation great again. CoRR arXiv:abs\/1711.10006 (2017)","DOI":"10.1109\/ICCV.2017.169"},{"key":"12_CR13","unstructured":"Kesten, R., et al.: Lyft level 5 AV dataset 2019 (2019). https:\/\/level5.lyft.com\/dataset\/"},{"key":"12_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR arXiv:abs\/1412.6980 (2014)"},{"key":"12_CR15","unstructured":"Kirillov, A., He, K., Girshick, R.B., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. CoRR arXiv:abs\/1801.00868 (2018). http:\/\/arxiv.org\/abs\/1801.00868"},{"key":"12_CR16","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images (2009)"},{"key":"12_CR17","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097\u20131105. Curran Associates, Inc. (2012). http:\/\/papers.nips.cc\/paper\/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf"},{"key":"12_CR18","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. CoRR arXiv:abs\/1812.05784 (2018)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. In: Proceedings of the IEEE, pp. 2278\u20132324 (1998)","DOI":"10.1109\/5.726791"},{"key":"12_CR20","doi-asserted-by":"publisher","unstructured":"Lombardi, S., Simon, T., Saragih, J., Schwartz, G., Lehrmann, A., Sheikh, Y.: Neural volumes. ACM Trans. Graph. 38(4), 1\u201314 (2019). https:\/\/doi.org\/10.1145\/3306346.3323020","DOI":"10.1145\/3306346.3323020"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Mani, K., Daga, S., Garg, S., Shankar, N.S., Jatavallabhula, K.M., Krishna, K.M.: MonoLayout: amodal scene layout from a single image. arXiv:abs\/2002.08394 (2020)","DOI":"10.1109\/WACV45572.2020.9093519"},{"key":"12_CR22","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML (2010)"},{"key":"12_CR23","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Philion, J.: Fastdraw: addressing the long tail of lane detection by adapting a sequential prediction network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01185"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Philion, J., Kar, A., Fidler, S.: Learning to evaluate perception models using planner-centric metrics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01407"},{"key":"12_CR26","unstructured":"Poirson, P., Ammirato, P., Fu, C., Liu, W., Kosecka, J., Berg, A.C.: Fast single shot detection and pose estimation. CoRR arXiv:abs\/1609.05590 (2016)"},{"key":"12_CR27","doi-asserted-by":"publisher","first-page":"8851","DOI":"10.1609\/aaai.v33i01.33018851","volume":"33","author":"Z Qin","year":"2019","unstructured":"Qin, Z., Wang, J., Lu, Y.: MonoGRNet: a geometric reasoning network for monocular 3D object localization. Proc. AAAI Conf. Artif. Intell. 33, 8851\u20138858 (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33018851","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"12_CR28","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) (2020)","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"12_CR29","unstructured":"Roddick, T., Kendall, A., Cipolla, R.: Orthographic feature transform for monocular 3D object detection. CoRR arXiv:abs\/1811.08188 (2018)"},{"key":"12_CR30","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge (2014)"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bul\u00f2, S.R., Porzi, L., L\u00f3pez-Antequera, M., Kontschieder, P.: Disentangling monocular 3D object detection. CoRR arXiv:abs\/1905.12365 (2019)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Srinivasan, P.P., Mildenhall, B., Tancik, M., Barron, J.T., Tucker, R., Snavely, N.: Lighthouse: predicting lighting volumes for spatially-coherent illumination (2020)","DOI":"10.1109\/CVPR42600.2020.00810"},{"key":"12_CR33","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"12_CR34","unstructured":"Su, H., et al.: SplatNet: sparse lattice networks for point cloud processing. CoRR arXiv:abs\/1802.08275 (2018). http:\/\/arxiv.org\/abs\/1802.08275"},{"key":"12_CR35","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: Waymo open dataset (2019)"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Takikawa, T., Acuna, D., Jampani, V., Fidler, S.: Gated-SCNN: gated shape CNNs for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00533"},{"key":"12_CR37","unstructured":"Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. CoRR arXiv:abs\/1905.11946 (2019). http:\/\/arxiv.org\/abs\/1905.11946"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Tucker, R., Snavely, N.: Single-view view synthesis with multiplane images (2020)","DOI":"10.1109\/CVPR42600.2020.00063"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W., Garg, D., Hariharan, B., Campbell, M., Weinberger, K.Q.: Pseudo-LiDAR from visual depth estimation: bridging the gap in 3D object detection for autonomous driving. CoRR arXiv:abs\/1812.07179 (2018)","DOI":"10.1109\/CVPR.2019.00864"},{"key":"12_CR40","unstructured":"You, Y., et al.: Pseudo-LiDAR++: accurate depth for 3D object detection in autonomous driving. CoRR arXiv:abs\/1906.06310 (2019)"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Zeng, W., et al.: End-to-end interpretable neural motion planner. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8652\u20138661 (2019)","DOI":"10.1109\/CVPR.2019.00886"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58568-6_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:18:33Z","timestamp":1731370713000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58568-6_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585679","9783030585686"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"13 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}