{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:55:57Z","timestamp":1771955757786,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585884","type":"print"},{"value":"9783030585891","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\/978-3-030-58589-1_31","type":"book-chapter","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T06:18:04Z","timestamp":1605075484000},"page":"514-529","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Monocular Differentiable Rendering for Self-supervised 3D Object Detection"],"prefix":"10.1007","author":[{"given":"Deniz","family":"Beker","sequence":"first","affiliation":[]},{"given":"Hiroharu","family":"Kato","sequence":"additional","affiliation":[]},{"given":"Mihai Adrian","family":"Morariu","sequence":"additional","affiliation":[]},{"given":"Takahiro","family":"Ando","sequence":"additional","affiliation":[]},{"given":"Toru","family":"Matsuoka","sequence":"additional","affiliation":[]},{"given":"Wadim","family":"Kehl","sequence":"additional","affiliation":[]},{"given":"Adrien","family":"Gaidon","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,12]]},"reference":[{"key":"31_CR1","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. In: CoRR (2015)"},{"key":"31_CR2","unstructured":"Chen, W., et al.: Learning to predict 3D objects with an interpolation-based differentiable renderer. In: NeurIPS (2019)"},{"key":"31_CR3","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: CVPR (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"31_CR4","unstructured":"Chen, X., et al.: 3D object proposals for accurate object class detection. In: NIPS (2015)"},{"key":"31_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/978-3-319-45886-1_18","volume-title":"Pattern Recognition","author":"F Engelmann","year":"2016","unstructured":"Engelmann, F., St\u00fcckler, J., Leibe, B.: Joint object pose estimation and shape reconstruction in urban street scenes using 3D shape priors. In: Rosenhahn, B., Andres, B. (eds.) GCPR 2016. LNCS, vol. 9796, pp. 219\u2013230. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-45886-1_18"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Engelmann, F., St\u00fcckler, J., Leibe, B.: SAMP: shape and motion priors for 4D vehicle reconstruction. In: WACV (2017)","DOI":"10.1109\/WACV.2017.51"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for Autonomous Driving? The KITTI vision benchmark suite. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambrus, R., Pillai, S., Raventos, A., Gaidon, A.: PackNet-SfM: 3D packing for self-supervised monocular depth estimation. In: CoRR (2019)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"31_CR11","unstructured":"Ushiku, Y., Kato, H., Harada, T.: Neural 3D mesh renderer. In: CVPR (2018)"},{"key":"31_CR12","unstructured":"Insafutdinov, E., Dosovitskiy, A.: Unsupervised learning of shape and pose with differentiable point clouds. In: NIPS (2018)"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Kato, H., Harada, T.: Learning view priors for single-view 3D reconstruction. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01001"},{"key":"31_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Kulkarni, N., Gupta, A., Tulsiani, S.: Canonical surface mapping via geometric cycle consistency. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00229"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Kundu, A., Li, Y., Rehg, J.M.: 3D-RCNN: instance-level 3D object reconstruction via render-and-compare. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00375"},{"issue":"6","key":"31_CR17","first-page":"222:1","volume":"37","author":"T-M Li","year":"2018","unstructured":"Li, T.-M., Aittala, M., Durand, F., Lehtinen, J.: Differentiable Monte Carlo ray tracing through edge sampling. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 37(6), 222:1\u2013222:11 (2018)","journal-title":"ACM Trans. Graph. (Proc. SIGGRAPH Asia)"},{"key":"31_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Liu, S., Li, T., Chen, W., Li, H.: Soft rasterizer: a differentiable renderer for image-based 3D reasoning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00780"},{"key":"31_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/978-3-319-10584-0_11","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MM Loper","year":"2014","unstructured":"Loper, M.M., Black, M.J.: OpenDR: an approximate differentiable renderer. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 154\u2013169. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_11"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Ma, X., Wang, Z., Li, H., Ouyang, W., Zhang, P.: Accurate monocular 3D object detection via color-embedded 3D reconstruction for autonomous driving. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00695"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Mahjourian, R., Wicke, M., Angelova, A.: Unsupervised learning of depth and egomotion from monocular video using 3D geometric constraints. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00594"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Manhardt, F., Kehl, W., Gaidon, A.: ROI-10D: monocular lifting of 2D detection to 6D pose and metric shape. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00217"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Choi, H.M., Kang, H., Hyun, Y.: Multi-view reprojection architecture for orientation estimation. In: ICCVW (2019)","DOI":"10.1109\/ICCVW.2019.00289"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Kosecka, J.: 3D bounding box estimation using deep learning and geometry. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.597"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Pillai, S., Ambru\u015f, R., Gaidon, A.: SuperDepth: self-supervised, super-resolved monocular depth estimation. In: ICRA (2019)","DOI":"10.1109\/ICRA.2019.8793621"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bulo, S.R., Porzi, L., L\u00f3pez-Antequera, M., Kontschieder, P.: Disentangling monocular 3D object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bul\u00f2, S.R., Porzi, L., Ricci, E., Kontschieder,P.: Single-stage monocular 3D object detection with virtual cameras. In: CoRR (2019)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Stutz, D., Geiger, A.: Learning 3D shape completion under weak supervision. In: IJCV (2018)","DOI":"10.1007\/s11263-018-1126-y"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Efros, A.A., Malik, J.: Multi-view consistency as supervisory signal for learning shape and pose prediction. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00306"},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Wang, R., Yang, N., Stueckler, J., Cremers, D.: DirectShape: photometric alignment of shape priors for visual vehicle pose and shape estimation. In: ICRA (2020)","DOI":"10.1109\/ICRA40945.2020.9197095"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W.-L., 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. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00864"},{"key":"31_CR33","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.-Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"31_CR34","doi-asserted-by":"crossref","unstructured":"Xu, B., Chen, Z.: Multi-level fusion based 3D object detection from monocular images. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00249"},{"key":"31_CR35","unstructured":"You, Y., et al.: Pseudo-LiDAR++: accurate depth for 3D object detection in autonomous driving. In: ICLR (2020)"},{"key":"31_CR36","doi-asserted-by":"crossref","unstructured":"Zakharov, S., Kehl, W., Bhargava, A., Gaidon, A.: Autolabeling 3D objects with differentiable rendering of SDF shape priors. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01224"},{"key":"31_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"31_CR38","doi-asserted-by":"crossref","unstructured":"Zuffi, S., Kanazawa, A., Berger-Wolf, T., Black, M.J.: Three-D safari: learning to estimate zebra pose, shape, and texture from images \u201cin the wild\u201d. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00546"}],"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\/978-3-030-58589-1_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:23:21Z","timestamp":1731284601000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58589-1_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585884","9783030585891"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58589-1_31","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":"12 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.","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)"}}]}}