{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T11:55:31Z","timestamp":1768737331365,"version":"3.49.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T00:00:00Z","timestamp":1623715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T00:00:00Z","timestamp":1623715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1007\/s11263-021-01488-2","type":"journal-article","created":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T15:04:11Z","timestamp":1623769451000},"page":"2499-2512","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Deep Unsupervised 3D Human Body Reconstruction from a Sparse set of Landmarks"],"prefix":"10.1007","volume":"129","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7384-5712","authenticated-orcid":false,"given":"Meysam","family":"Madadi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hugo","family":"Bertiche","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergio","family":"Escalera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,15]]},"reference":[{"key":"1488_CR1","doi-asserted-by":"crossref","unstructured":"Achilles, F., Ichim, A.E., Coskun, H., Tombari, F., Noachtar, S., & Navab, N. (2016). Patient mocap: Human pose estimation under blanket occlusion for hospital monitoring applications. In International conference on medical image computing and computer-assisted intervention (pp. 491\u2013499). Springer.","DOI":"10.1007\/978-3-319-46720-7_57"},{"key":"1488_CR2","doi-asserted-by":"crossref","unstructured":"Bhatnagar, B.L., Sminchisescu, C., Theobalt, C., & Pons-Moll, G. (2020). Combining implicit function learning and parametric models for 3D human reconstruction. In ECCV","DOI":"10.1007\/978-3-030-58536-5_19"},{"key":"1488_CR3","unstructured":"Bhatnagar, B. L., Sminchisescu, C., Theobalt, C., & Pons-Moll, G. (2020). LoopReg: Self-supervised learning of implicit surface correspondences, pose and shape for 3D human mesh registration. In Neural information processing systems (NeurIPS)."},{"key":"1488_CR4","doi-asserted-by":"crossref","unstructured":"Bogo, F., Black, M. J., Loper, M., & Romero, J. (2015). Detailed full-body reconstructions of moving people from monocular RGB-D sequences. In Proceedings of the IEEE international conference on computer vision (pp. 2300\u20132308).","DOI":"10.1109\/ICCV.2015.265"},{"key":"1488_CR5","doi-asserted-by":"crossref","unstructured":"Chai, J., & Hodgins, J. K. (2005). Performance animation from low-dimensional control signals. In ACM SIGGRAPH 2005 papers (pp. 686\u2013696).","DOI":"10.1145\/1073204.1073248"},{"key":"1488_CR6","doi-asserted-by":"crossref","unstructured":"Chen, C. H., Tyagi, A., Agrawal, A., Drover, D., Stojanov, S., & Rehg, J. M. (2019). Unsupervised 3D pose estimation with geometric self-supervision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5714\u20135724).","DOI":"10.1109\/CVPR.2019.00586"},{"key":"1488_CR7","doi-asserted-by":"crossref","unstructured":"Groueix, T., Fisher, M., Kim, V. G., Russell, B., & Aubry, M. (2018). 3D-coded: 3D correspondences by deep deformation. In ECCV.","DOI":"10.1007\/978-3-030-01216-8_15"},{"key":"1488_CR8","doi-asserted-by":"crossref","unstructured":"Hoyet, L., Ryall, K., McDonnell, R., & O\u2019Sullivan, C. (2012). Sleight of hand: Perception of finger motion from reduced marker sets. In Proceedings of the ACM SIGGRAPH symposium on interactive 3D graphics and games (pp. 79\u201386).","DOI":"10.1145\/2159616.2159630"},{"issue":"6","key":"1488_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3272127.3275108","volume":"37","author":"Y Huang","year":"2018","unstructured":"Huang, Y., Kaufmann, M., Aksan, E., Black, M. J., Hilliges, O., & Pons-Moll, G. (2018). Deep inertial poser: Learning to reconstruct human pose from sparse inertial measurements in real time. ACM Transactions on Graphics (TOG), 37(6), 1\u201315.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"1488_CR10","unstructured":"Insafutdinov, E., & Dosovitskiy, A. (2018). Unsupervised learning of shape and pose with differentiable point clouds. In Advances in neural information processing systems (pp. 2802\u20132812)."},{"key":"1488_CR11","doi-asserted-by":"crossref","unstructured":"Joo, H., Simon, T., & Sheikh, Y. (2018). 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).","DOI":"10.1109\/CVPR.2018.00868"},{"key":"1488_CR12","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M. J., Jacobs, D. W., & Malik, J. (2018). End-to-end recovery of human shape and pose. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7122\u20137131).","DOI":"10.1109\/CVPR.2018.00744"},{"key":"1488_CR13","unstructured":"Kudo, Y., Ogaki, K., Matsui, Y., & Odagiri, Y. (2018). Unsupervised adversarial learning of 3D human pose from 2D joint locations. Preprint retrieved from arXiv:1803.08244"},{"key":"1488_CR14","unstructured":"Lab, C. G. (2000). CMU graphics lab motion capture. http:\/\/mocap.cs.cmu.edu"},{"key":"1488_CR15","doi-asserted-by":"crossref","unstructured":"Liu, H., Wei, X., Chai, J., Ha, I., & Rhee, T. (2011). Realtime human motion control with a small number of inertial sensors. In Symposium on interactive 3D graphics and games (pp. 133\u2013140).","DOI":"10.1145\/1944745.1944768"},{"issue":"6","key":"1488_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2661229.2661273","volume":"33","author":"M Loper","year":"2014","unstructured":"Loper, M., Mahmood, N., & Black, M. J. (2014). Mosh: Motion and shape capture from sparse markers. ACM Transactions on Graphics (TOG), 33(6), 1\u201313.","journal-title":"ACM Transactions on Graphics (TOG)"},{"issue":"6","key":"1488_CR17","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. (2015). SMPL: A skinned multi-person linear model. ACM Transactions on Graphics (TOG), 34(6), 1\u201316.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"1488_CR18","unstructured":"Madadi, M., Bertiche, H., & Escalera, S. (2018). SMPLR: Deep SMPL reverse for 3D human pose and shape recovery. Preprint retrieved from arXiv:1812.10766."},{"key":"1488_CR19","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N. F., Pons-Moll, G., & Black, M. J. (2019). AMASS: Archive of motion capture as surface shapes. In Proceedings of the IEEE international conference on computer vision (pp. 5442\u20135451).","DOI":"10.1109\/ICCV.2019.00554"},{"key":"1488_CR20","doi-asserted-by":"crossref","unstructured":"Mehrizi, R., Peng, X., Tang, Z., Xu, X., Metaxas, D., & Li, K. (2018). Toward marker-free 3D pose estimation in lifting: A deep multi-view solution. In 2018 13th IEEE international conference on automatic face & gesture recognition (FG 2018) (pp. 485\u2013491). IEEE.","DOI":"10.1109\/FG.2018.00078"},{"key":"1488_CR21","doi-asserted-by":"publisher","unstructured":"Mehta, D., Sotnychenko, O., Mueller, F., Xu, W., Elgharib, M., Fua, P., Seidel, H. P., Rhodin, H., Pons-Moll, G., & Theobalt, C. (2020). XNect: Real-time multi-person 3D motion capture with a single RGB camera. Vol.\u00a039. https:\/\/doi.org\/10.1145\/3386569.3392410","DOI":"10.1145\/3386569.3392410"},{"issue":"12","key":"1488_CR22","doi-asserted-by":"publisher","first-page":"2262","DOI":"10.1109\/TPAMI.2010.46","volume":"32","author":"A Myronenko","year":"2010","unstructured":"Myronenko, A., & Song, X. (2010). Point set registration: Coherent point drift. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(12), 2262\u20132275.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1488_CR23","doi-asserted-by":"crossref","unstructured":"Omran, M., Lassner, C., Pons-Moll, G., Gehler, P., & Schiele, B. (2018). 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.","DOI":"10.1109\/3DV.2018.00062"},{"issue":"3","key":"1488_CR24","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1145\/1141911.1141970","volume":"25","author":"SI Park","year":"2006","unstructured":"Park, S. I., & Hodgins, J. K. (2006). Capturing and animating skin deformation in human motion. ACM Transactions on Graphics (TOG), 25(3), 881\u2013889.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"1488_CR25","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhu, L., Zhou, X., & Daniilidis, K. (2018). 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).","DOI":"10.1109\/CVPR.2018.00055"},{"key":"1488_CR26","doi-asserted-by":"crossref","unstructured":"Prokudin, S., Lassner, C., & Romero, J. (2019). Efficient learning on point clouds with basis point sets. In Proceedings of the IEEE international conference on computer vision (pp. 4332\u20134341).","DOI":"10.1109\/ICCVW.2019.00370"},{"key":"1488_CR27","doi-asserted-by":"crossref","unstructured":"Rhodin, H., Robertini, N., Casas, D., Richardt, C., Seidel, H. P., & Theobalt, C. (2016). General automatic human shape and motion capture using volumetric contour cues. In European conference on computer vision (pp. 509\u2013526). Springer.","DOI":"10.1007\/978-3-319-46454-1_31"},{"key":"1488_CR28","doi-asserted-by":"crossref","unstructured":"Schwarz, L. A., Mateus, D., & Navab, N. (2009). Discriminative human full-body pose estimation from wearable inertial sensor data. In 3D physiological human workshop (pp. 159\u2013172). Springer.","DOI":"10.1007\/978-3-642-10470-1_14"},{"key":"1488_CR29","unstructured":"Slyper, R., & Hodgins, J. K. (2008). Action capture with accelerometers. In Symposium on computer animation (pp. 193\u2013199)."},{"issue":"3","key":"1488_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1966394.1966397","volume":"30","author":"J Tautges","year":"2011","unstructured":"Tautges, J., Zinke, A., Kr\u00fcger, B., Baumann, J., Weber, A., Helten, T., et al. (2011). Motion reconstruction using sparse accelerometer data. ACM Transactions on Graphics (ToG), 30(3), 1\u201312.","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"1488_CR31","doi-asserted-by":"crossref","unstructured":"Trumble, M., Gilbert, A., Malleson, C., Hilton, A., & Collomosse, J. (2017). Total capture: 3D human pose estimation fusing video and inertial sensors. In BMVC (Vol. 2, p. 3).","DOI":"10.5244\/C.31.14"},{"key":"1488_CR32","doi-asserted-by":"crossref","unstructured":"Varol, G., Ceylan, D., Russell, B., Yang, J., Yumer, E., Laptev, I., & Schmid, C. (2018). Bodynet: Volumetric inference of 3D human body shapes. In Proceedings of the European conference on computer vision (ECCV) (pp. 20\u201336).","DOI":"10.1007\/978-3-030-01234-2_2"},{"key":"1488_CR33","doi-asserted-by":"crossref","unstructured":"Varol, G., Romero, J., Martin, X., Mahmood, N., Black, M. J., Laptev, I., & Schmid, C. (2017). Learning from synthetic humans. In CVPR","DOI":"10.1109\/CVPR.2017.492"},{"key":"1488_CR34","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., & Manzagol, P. A. (2010). Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research, 11, 3371\u20133408.","journal-title":"Journal of Machine Learning Research"},{"key":"1488_CR35","doi-asserted-by":"crossref","unstructured":"von Marcard, T., Henschel, R., Black, M. J., Rosenhahn, B., & Pons-Moll, G. (2018). 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).","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"1488_CR36","doi-asserted-by":"crossref","unstructured":"von Marcard, T., Rosenhahn, B., Black, M. J., & Pons-Moll, G. (2017). Sparse inertial poser: Automatic 3D human pose estimation from sparse IMUs. In Computer graphics forum (Vol. 36, pp. 349\u2013360). Wiley Online Library.","DOI":"10.1111\/cgf.13131"},{"issue":"8","key":"1488_CR37","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TPAMI.2016.2522398","volume":"38","author":"T Von Marcard","year":"2016","unstructured":"Von Marcard, T., Pons-Moll, G., & Rosenhahn, B. (2016). Human pose estimation from video and IMUs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(8), 1533\u20131547.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1488_CR38","unstructured":"Zhao, W., Chai, J., & Xu, Y.Q. (2012). Combining marker-based mocap and RGB-D camera for acquiring high-fidelity hand motion data. In Proceedings of the ACM SIGGRAPH\/eurographics symposium on computer animation (pp. 33\u201342). Eurographics Association"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01488-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01488-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01488-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,24]],"date-time":"2021-07-24T06:18:39Z","timestamp":1627107519000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01488-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,15]]},"references-count":38,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["1488"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01488-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,15]]},"assertion":[{"value":"1 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}