{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:11:24Z","timestamp":1784736684812,"version":"3.55.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585198","type":"print"},{"value":"9783030585204","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\/978-3-030-58520-4_34","type":"book-chapter","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T10:08:18Z","timestamp":1605694098000},"page":"574-591","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":358,"title":["CosyPose: Consistent Multi-view Multi-object 6D Pose Estimation"],"prefix":"10.1007","author":[{"given":"Yann","family":"Labb\u00e9","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justin","family":"Carpentier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathieu","family":"Aubry","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josef","family":"Sivic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,19]]},"reference":[{"key":"34_CR1","unstructured":"Roberts, L.G.: Machine perception of three-dimensional solids. Ph.D. thesis, Massachusetts Institute of Technology (1963)"},{"issue":"3","key":"34_CR2","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/0004-3702(87)90070-1","volume":"31","author":"DG Lowe","year":"1987","unstructured":"Lowe, D.G.: Three-dimensional object recognition from single two-dimensional images. Artif. Intell. 31(3), 355\u2013395 (1987)","journal-title":"Artif. Intell."},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Object recognition from local scale-invariant features. In: Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 1150\u20131157, September 1999","DOI":"10.1109\/ICCV.1999.790410"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Rad, M., Lepetit, V.: BB8: a scalable, accurate, robust to partial occlusion method for predicting the 3D poses of challenging objects without using depth. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3828\u20133836 (2017)","DOI":"10.1109\/ICCV.2017.413"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Peng, S., Liu, Y., Huang, Q., Zhou, X., Bao, H.: PVNet: pixel-wise voting network for 6DoF pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4561\u20134570 (2019)","DOI":"10.1109\/CVPR.2019.00469"},{"key":"34_CR6","unstructured":"Tremblay, J., To, T., Sundaralingam, B., Xiang, Y., Fox, D., Birchfield, S.: Deep object pose estimation for semantic robotic grasping of household objects. In: Conference on Robot Learning (CoRL) (2018)"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Park, K., Patten, T., Vincze, M.: Pix2Pose: pixel-wise coordinate regression of objects for 6D pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7668\u20137677 (2019)","DOI":"10.1109\/ICCV.2019.00776"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Zakharov, S., Shugurov, I., Ilic, S.: DPOD: 6D pose object detector and refiner. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1941\u20131950 (2019)","DOI":"10.1109\/ICCV.2019.00203"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., Guibas, L.J.: Normalized object coordinate space for category-level 6D object pose and size estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2642\u20132651 (2019)","DOI":"10.1109\/CVPR.2019.00275"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, G., Ji, X., Xiang, Y., Fox, D.: DeepIM: deep iterative matching for 6D pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 683\u2013698 (2018)","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: DenseFusion: 6D object pose estimation by iterative dense fusion. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3343\u20133352 (2019)","DOI":"10.1109\/CVPR.2019.00346"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., Marton, Z.C., Durner, M., Brucker, M., Triebel, R.: Implicit 3D orientation learning for 6D object detection from RGB images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 699\u2013715 (2018)","DOI":"10.1007\/978-3-030-01231-1_43"},{"key":"34_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/11744023_32","volume-title":"Computer Vision \u2013 ECCV 2006","author":"H Bay","year":"2006","unstructured":"Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404\u2013417. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744023_32"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Hinterstoisser, S., et al.: Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes. In: 2011 International Conference on Computer Vision, pp. 858\u2013865, November 2011","DOI":"10.1109\/ICCV.2011.6126326"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Collet, A., Srinivasa, S.S.: Efficient multi-view object recognition and full pose estimation. In: 2010 IEEE International Conference on Robotics and Automation, pp. 2050\u20132055, May 2010","DOI":"10.1109\/ROBOT.2010.5509615"},{"issue":"10","key":"34_CR16","doi-asserted-by":"publisher","first-page":"1284","DOI":"10.1177\/0278364911401765","volume":"30","author":"A Collet","year":"2011","unstructured":"Collet, A., Martinez, M., Srinivasa, S.S.: The moped framework: object recognition and pose estimation for manipulation. Int. J. Rob. Res. 30(10), 1284\u20131306 (2011)","journal-title":"Int. J. Rob. Res."},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 1, pp. 886\u2013893, June 2005","DOI":"10.1109\/CVPR.2005.177"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Schmidt, T., Narayanan, V., Fox, D.: PoseCNN: a convolutional neural network for 6D object pose estimation in cluttered scenes. In: Robotics: Science and Systems XIV (2018)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Hodan, T., Haluza, P., Obdr\u017e\u00e1lek, \u0160., Matas, J., Lourakis, M., Zabulis, X.: T-LESS: an RGB-D dataset for 6D pose estimation of Texture-Less objects. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 880\u2013888, March 2017","DOI":"10.1109\/WACV.2017.103"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Li, C., Bai, J., Hager, G.D.: A unified framework for multi-view multi-class object pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 254\u2013269 (2018)","DOI":"10.1007\/978-3-030-01270-0_16"},{"key":"34_CR21","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. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1521\u20131529 (2017)","DOI":"10.1109\/ICCV.2017.169"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Tekin, B., Sinha, S.N., Fua, P.: Real-time seamless single shot 6D object pose prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 292\u2013301 (2018)","DOI":"10.1109\/CVPR.2018.00038"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Pitteri, G., Ilic, S., Lepetit, V.: CorNet: generic 3D corners for 6D pose estimation of new objects without retraining. In: Proceedings of the IEEE International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00342"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Grossberg, M.D., Nayar, S.K.: A general imaging model and a method for finding its parameters. In: Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, vol. 2, pp. 108\u2013115. IEEE (2001)","DOI":"10.1109\/ICCV.2001.937611"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Pless, R.: Using many cameras as one. In: 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003 Proceedings, vol. 2, II-587, June 2003","DOI":"10.1109\/CVPR.2003.1211520"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Salas-Moreno, R.F., Newcombe, R.A., Strasdat, H., Kelly, P.H.J., Davison, A.J.: SLAM++: simultaneous localisation and mapping at the level of objects. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1352\u20131359, June 2013","DOI":"10.1109\/CVPR.2013.178"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Drost, B., Ulrich, M., Navab, N., Ilic, S.: Model globally, match locally: efficient and robust 3D object recognition. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 998\u20131005, June 2010","DOI":"10.1109\/CVPR.2010.5540108"},{"issue":"2","key":"34_CR28","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/BF01427149","volume":"13","author":"Z Zhang","year":"1994","unstructured":"Zhang, Z.: Iterative point matching for registration of free-form curves and surfaces. Int. J. Comput. Vis. 13(2), 119\u2013152 (1994)","journal-title":"Int. J. Comput. Vis."},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Doumanoglou, A., Kouskouridas, R., Malassiotis, S., Kim, T.K.: Recovering 6D object pose and predicting next-best-view in the crowd. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3583\u20133592 (2016)","DOI":"10.1109\/CVPR.2016.390"},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Bao, S.Y., Savarese, S.: Semantic structure from motion. In: CVPR 2011, pp. 2025\u20132032. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995462"},{"key":"34_CR31","doi-asserted-by":"crossref","unstructured":"Pillai, S., Leonard, J.: Monocular SLAM supported object recognition. In: Robotics: Science and Systems XI, Robotics: Science and Systems Foundation, July 2015","DOI":"10.15607\/RSS.2015.XI.034"},{"issue":"4","key":"34_CR32","doi-asserted-by":"publisher","first-page":"925","DOI":"10.1109\/TRO.2019.2909168","volume":"35","author":"S Yang","year":"2019","unstructured":"Yang, S., Scherer, S.: CubeSLAM: monocular 3-D object slam. IEEE Trans. Rob. 35(4), 925\u2013938 (2019)","journal-title":"IEEE Trans. Rob."},{"key":"34_CR33","doi-asserted-by":"crossref","unstructured":"Bachmann, R., Sp\u00f6rri, J., Fua, P., Rhodin, H.: Motion capture from pan-tilt cameras with unknown orientation. In: 2019 International Conference on 3D Vision (3DV), pp. 308\u2013317. IEEE (2019)","DOI":"10.1109\/3DV.2019.00042"},{"issue":"1","key":"34_CR34","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1006\/jvci.1994.1002","volume":"5","author":"R Szeliski","year":"1994","unstructured":"Szeliski, R., Kang, S.B.: Recovering 3D shape and motion from image streams using nonlinear least squares. J. Vis. Commun. Image Represent. 5(1), 10\u201328 (1994)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"34_CR35","volume-title":"Multiple View Geometry in Computer Vision","author":"R Hartley","year":"2003","unstructured":"Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)"},{"issue":"3","key":"34_CR36","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s11263-005-3674-1","volume":"66","author":"F Rothganger","year":"2006","unstructured":"Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3D object modeling and recognition using local Affine-Invariant image descriptors and multi-view spatial constraints. Int. J. Comput. Vis. 66(3), 231\u2013259 (2006)","journal-title":"Int. J. Comput. Vis."},{"key":"34_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1007\/3-540-44480-7_21","volume-title":"Vision Algorithms: Theory and Practice","author":"B Triggs","year":"2000","unstructured":"Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle adjustment \u2014 a modern synthesis. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) IWVA 1999. LNCS, vol. 1883, pp. 298\u2013372. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-44480-7_21"},{"issue":"6","key":"34_CR38","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR39","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, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"34_CR40","unstructured":"Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9\u201315 June 2019, Long Beach, California, USA, Proceedings of Machine Learning Research, PMLR, vol. 97, pp. 6105\u20136114 (2019)"},{"key":"34_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5745\u20135753 (2019)","DOI":"10.1109\/CVPR.2019.00589"},{"key":"34_CR42","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bulo, S.R., Porzi, L., L\u00f3pez-Antequera, M., Kontschieder, P.: Disentangling monocular 3D object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1991\u20131999 (2019)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"34_CR43","doi-asserted-by":"crossref","unstructured":"Pitteri, G., Ramamonjisoa, M., Ilic, S., Lepetit, V.: On object symmetries and 6D pose estimation from images. In: 2019 International Conference on 3D Vision (3DV), pp. 614\u2013622. IEEE (2019)","DOI":"10.1109\/3DV.2019.00073"},{"key":"34_CR44","doi-asserted-by":"crossref","unstructured":"Hodan, T., et al.: Bop: Benchmark for 6d object pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 19\u201334 (2018)","DOI":"10.1007\/978-3-030-01249-6_2"},{"key":"34_CR45","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"34_CR46","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Zheng, E., Pollefeys, M., Frahm, J.M.: Pixelwise view selection for unstructured multi-view stereo. In: European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46487-9_31"}],"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\/978-3-030-58520-4_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:24:33Z","timestamp":1731889473000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58520-4_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585198","9783030585204"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58520-4_34","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":"19 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)"}}]}}