{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:26:48Z","timestamp":1775068008217,"version":"3.50.1"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585389","type":"print"},{"value":"9783030585396","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\/978-3-030-58539-6_28","type":"book-chapter","created":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T19:02:46Z","timestamp":1604689366000},"page":"465-481","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":83,"title":["Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows"],"prefix":"10.1007","author":[{"given":"Andrei","family":"Zanfir","sequence":"first","affiliation":[]},{"given":"Eduard Gabriel","family":"Bazavan","sequence":"additional","affiliation":[]},{"given":"Hongyi","family":"Xu","sequence":"additional","affiliation":[]},{"given":"William T.","family":"Freeman","sequence":"additional","affiliation":[]},{"given":"Rahul","family":"Sukthankar","sequence":"additional","affiliation":[]},{"given":"Cristian","family":"Sminchisescu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,7]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Doersch, C., Zisserman, A.: Exploiting temporal context for 3D human pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3395\u20133404. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00351"},{"key":"28_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-319-46454-1_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"F Bogo","year":"2016","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep it SMPL: automatic estimation of 3D human pose and shape from a single image. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 561\u2013578. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_34"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7291\u20137299. IEEE (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"28_CR4","unstructured":"Dinh, L., Krueger, D., Bengio, Y.: Nice: non-linear independent components estimation. arXiv preprint arXiv:1410.8516 (2014)"},{"key":"28_CR5","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real nvp. arXiv preprint arXiv:1605.08803 (2016)"},{"key":"28_CR6","unstructured":"Doersch, C., Zisserman, A.: Sim2real transfer learning for 3D human pose estimation: motion to the rescue. In: Advances in Neural Information Processing Systems, pp. 12929\u201312941 (2019)"},{"key":"28_CR7","unstructured":"Germain, M., Gregor, K., Murray, I., Larochelle, H.: Made: masked autoencoder for distribution estimation. In: International Conference on Machine Learning, pp. 881\u2013889 (2015)"},{"issue":"7","key":"28_CR8","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Iskakov, K., Burkov, E., Lempitsky, V., Malkov, Y.: Learnable triangulation of human pose. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7718\u20137727 (2019)","DOI":"10.1109\/ICCV.2019.00781"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Jackson, A.S., Manafas, C., Tzimiropoulos, G.: 3D human body reconstruction from a single image via volumetric regression. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-11018-5_6"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Joo, H., Simon, T., Sheikh, Y.: Total capture: a 3D deformation model for tracking faces, hands, and bodies. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 8320\u20138329 (2018)","DOI":"10.1109\/CVPR.2018.00868"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7122\u20137131 (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Zhang, J.Y., Felsen, P., Malik, J.: Learning 3D human dynamics from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5614\u20135623 (2019)","DOI":"10.1109\/CVPR.2019.00576"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Kato, H., Ushiku, Y., Harada, T.: Neural 3d mesh renderer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3907\u20133916 (2018)","DOI":"10.1109\/CVPR.2018.00411"},{"key":"28_CR15","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1\u00a0$$\\times $$\u00a01 convolutions. In: Advances in neural information processing systems, pp. 10215\u201310224 (2018)"},{"key":"28_CR16","unstructured":"Kingma, D.P., Salimans, T., Jozefowicz, R., Chen, X., Sutskever, I., Welling, M.: Improved variational inference with inverse autoregressive flow. In: Advances in neural information processing systems, pp. 4743\u20134751 (2016)"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Athanasiou, N., Black, M.J.: Vibe: video inference for human body pose and shape estimation. arXiv preprint arXiv:1912.05656 (2019)","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2252\u20132261 (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Daniilidis, K.: Convolutional mesh regression for single-image human shape reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4501\u20134510 (2019)","DOI":"10.1109\/CVPR.2019.00463"},{"key":"28_CR20","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"},{"issue":"6","key":"28_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (TOG) 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR22","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":"28_CR23","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: Amass: archive of motion capture as surface shapes. arXiv preprint arXiv:1904.03278 (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"von Marcard, T., Henschel, R., Black, M., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3D human pose in the wild using imus and a moving camera. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 601\u2013617 (2018)","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3d human pose estimation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.288"},{"issue":"4","key":"28_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073596","volume":"36","author":"D Mehta","year":"2017","unstructured":"Mehta, D., et al.: Vnect: real-time 3D human pose estimation with a single rgb camera. ACM Trans. Graph. (TOG) 36(4), 1\u201314 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Omran, M., Lassner, C., Pons-Moll, G., Gehler, P.V., Schiele, B.: Neural body fitting: unifying deep learning and model-based human pose and shape estimation. In: 2018 international conference on 3D vision (3DV), pp. 484\u2013494 IEEE (2018)","DOI":"10.1109\/3DV.2018.00062"},{"key":"28_CR28","unstructured":"Papamakarios, G., Pavlakou, T., Murray, I.: Masked autoregressive flow for density estimation. In: Advances in Neural Information Processing Systems, pp. 2338\u20132347 (2017)"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3d hands, face, and body from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10975\u201310985. IEEE (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Derpanis, K.G., Daniilidis, K.: Coarse-to-fine volumetric prediction for single-image 3D human pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7025\u20137034 IEEE (2017)","DOI":"10.1109\/CVPR.2017.139"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhu, L., Zhou, X., Daniilidis, K.: Learning to estimate 3D human pose and shape from a single color image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 459\u2013468. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00055"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Popa, A., Zanfir, M., Sminchisescu, C.: Deep multitask architecture for integrated 2D and 3D human sensing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6289\u20136298. IEEE (2017)","DOI":"10.1109\/CVPR.2017.501"},{"key":"28_CR33","unstructured":"Rezende, D.J., Mohamed, S.: Variational inference with normalizing flows. arXiv preprint arXiv:1505.05770 (2015)"},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Rhodin, H., Robertini, N., Richardt, C., Seidel, H.P., Theobalt, C.: A versatile scene model with differentiable visibility applied to generative pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 765\u2013773 (2015)","DOI":"10.1109\/ICCV.2015.94"},{"key":"28_CR35","unstructured":"Rogez, G., Schmid, C.: Mocap-guided data augmentation for 3D pose estimation in the wild. In: Advances in neural information processing systems, pp. 3108\u20133116 (2016)"},{"key":"28_CR36","doi-asserted-by":"crossref","unstructured":"Sun, Y., Ye, Y., Liu, W., Gao, W., Fu, Y., Mei, T.: Human mesh recovery from monocular images via a skeleton-disentangled representation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5349\u20135358 (2019)","DOI":"10.1109\/ICCV.2019.00545"},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"Tekin, B., Marquez Neila, P., Salzmann, M., Fua, P.: Learning to fuse 2D and 3D image cues for monocular body pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 3941\u20133950 (2017)","DOI":"10.1109\/ICCV.2017.425"},{"key":"28_CR38","unstructured":"Tung, H.Y., Tung, H.W., Yumer, E., Fragkiadaki, K.: Self-supervised learning of motion capture. In: Advances in Neural Information Processing Systems, pp. 5236\u20135246 (2017)"},{"key":"28_CR39","doi-asserted-by":"crossref","unstructured":"Varol, G., et al.: BodyNet: volumetric inference of 3D human body shapes. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 20\u201336 (2018)","DOI":"10.1007\/978-3-030-01234-2_2"},{"key":"28_CR40","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 4724\u20134732. IEEE (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Xu, H., Bazavan, E.G., Zanfir, A., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: Ghum & ghuml: generative 3D human shape and articulated pose models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6184\u20136193 (2020)","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhu, S.C., Tung, T.: Denserac: joint 3D pose and shape estimation by dense render-and-compare. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7760\u20137770. IEEE (2019)","DOI":"10.1109\/ICCV.2019.00785"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Yang, W., Ouyang, W., Wang, X., Ren, J., Li, H., Wang, X.: 3D human pose estimation in the wild by adversarial learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5255\u20135264. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00551"},{"key":"28_CR44","doi-asserted-by":"crossref","unstructured":"Zanfir, A., Marinoiu, E., Sminchisescu, C.: Monocular 3d pose and shape estimation of multiple people in natural scenes-the importance of multiple scene constraints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2148\u20132157. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00229"},{"key":"28_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, C., Pujades, S., Black, M.J., Pons-Moll, G.: Detailed, accurate, human shape estimation from clothed 3D scan sequences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4191\u20134200. IEEE(2017)","DOI":"10.1109\/CVPR.2017.582"},{"key":"28_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, X., Huang, Q., Sun, X., Xue, X., Wei, Y.: Towards 3D human pose estimation in the wild: a weakly-supervised approach. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 398\u2013407. IEEE (2017)","DOI":"10.1109\/ICCV.2017.51"},{"key":"28_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. arXiv preprint arXiv:1812.07035 (2018)","DOI":"10.1109\/CVPR.2019.00589"}],"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\/978-3-030-58539-6_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:17:01Z","timestamp":1730852221000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58539-6_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585389","9783030585396"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58539-6_28","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":"7 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)"}}]}}