{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:54:47Z","timestamp":1778082887720,"version":"3.51.4"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2023,12,5]]},"abstract":"<jats:p>Great progress has been made in estimating 3D human pose and shape from images and video by training neural networks to directly regress the parameters of parametric human models like SMPL. However, existing body models have simplified kinematic structures that do not correspond to the true joint locations and articulations in the human skeletal system, limiting their potential use in biomechanics. On the other hand, methods for estimating biomechanically accurate skeletal motion typically rely on complex motion capture systems and expensive optimization methods. What is needed is a parametric 3D human model with a biomechanically accurate skeletal structure that can be easily posed. To that end, we develop SKEL, which re-rigs the SMPL body model with a biomechanics skeleton. To enable this, we need training data of skeletons inside SMPL meshes in diverse poses. We build such a dataset by optimizing biomechanically accurate skeletons inside SMPL meshes from AMASS sequences. We then learn a regressor from SMPL mesh vertices to the optimized joint locations and bone rotations. Finally, we re-parametrize the SMPL mesh with the new kinematic parameters. The resulting SKEL model is animatable like SMPL but with fewer, and biomechanically-realistic, degrees of freedom. We show that SKEL has more biomechanically accurate joint locations than SMPL, and the bones fit inside the body surface better than previous methods. By fitting SKEL to SMPL meshes we are able to \"upgrade\" existing human pose and shape datasets to include biomechanical parameters. SKEL provides a new tool to enable biomechanics in the wild, while also providing vision and graphics researchers with a better constrained and more realistic model of human articulation. The model, code, and data are available for research at https:\/\/skel.is.tue.mpg.de.<\/jats:p>","DOI":"10.1145\/3618381","type":"journal-article","created":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T10:20:48Z","timestamp":1701771648000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":65,"title":["From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humans"],"prefix":"10.1145","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2611-8595","authenticated-orcid":false,"given":"Marilyn","family":"Keller","sequence":"first","affiliation":[{"name":"Max Planck Institute for Intelligent Systems, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3506-7769","authenticated-orcid":false,"given":"Keenon","family":"Werling","sequence":"additional","affiliation":[{"name":"Stanford University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0406-7611","authenticated-orcid":false,"given":"Soyong","family":"Shin","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9643-7551","authenticated-orcid":false,"given":"Scott","family":"Delp","sequence":"additional","affiliation":[{"name":"Stanford University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9604-7721","authenticated-orcid":false,"given":"Sergi","family":"Pujades","sequence":"additional","affiliation":[{"name":"Inria centre at the University Grenoble Alpes, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5926-0905","authenticated-orcid":false,"given":"C. Karen","family":"Liu","sequence":"additional","affiliation":[{"name":"Stanford University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6077-4540","authenticated-orcid":false,"given":"Michael J.","family":"Black","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems, Germany"}]}],"member":"320","published-online":{"date-parts":[[2023,12,5]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298751"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508415"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882311"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073207"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23010341"},{"key":"e_1_2_2_6_1","volume-title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion. In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). IEEE, 8726--8737","author":"Black Michael J.","year":"2023","unstructured":"Michael J. Black, Priyanka Patel, Joachim Tesch, and Jinlong Yang. 2023. BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion. In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). IEEE, 8726--8737. https:\/\/bedlam.is.tue.mpg.de\/."},{"key":"e_1_2_2_7_1","volume-title":"Dynamic FAUST: Registering Human Bodies in Motion. In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). IEEE, 6233--6242","author":"Bogo Federica","unstructured":"Federica Bogo, Javier Romero, Gerard Pons-Moll, and Michael J. Black. 2017. Dynamic FAUST: Registering Human Bodies in Motion. In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). IEEE, 6233--6242. https:\/\/dfaust.is.tue.mpg.de"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_2_2_9_1","volume-title":"IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). IEEE, 2718--2728","author":"Choutas Vasileios","unstructured":"Vasileios Choutas, Lea M\u00fcller, Chun-Hao P. Huang, Siyu Tang, Dimitrios Tzionas, and Michael J. Black. 2022. Accurate 3D Body Shape Regression using Metric and Semantic Attributes. In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). IEEE, 2718--2728. https:\/\/shapy.is.tue.mpg.de"},{"key":"e_1_2_2_10_1","volume-title":"CMU Graphics Lab Motion Capture Database","author":"Graphics CMU","unstructured":"CMU Graphics Lab 2000. CMU Graphics Lab Motion Capture Database. http:\/\/mocap.cs.cmu.edu. Accessed: 2012-12-11."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2007.901024"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222784"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2010.01718.x"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982438"},{"key":"e_1_2_2_15_1","volume-title":"End-to-end Recovery of Human Shape and Pose. In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). IEEE, 7122--7131","author":"Kanazawa Angjoo","year":"2018","unstructured":"Angjoo Kanazawa, Michael J. Black, David W. Jacobs, and Jitendra Malik. 2018. End-to-end Recovery of Human Shape and Pose. In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). IEEE, 7122--7131. https:\/\/openaccess.thecvf.com\/content_cvpr_2018\/papers\/Kanazawa_End-to-End_Recovery_of_CVPR_2018_paper.pdf"},{"key":"e_1_2_2_16_1","unstructured":"Manuel Kaufmann Velko Vechev and Dario Mylonopoulos. 2022. aitviewer. https:\/\/github.com\/eth-ait\/aitviewer"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.9754\/journal.wmc.2012.002903"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01984"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971217"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661273"},{"key":"e_1_2_2_23_1","volume-title":"International Conf. on Computer Vision (ICCV). IEEE, 5442--5451","author":"Mahmood Naureen","unstructured":"Naureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll, and Michael J. Black. 2019. AMASS: Archive of Motion Capture as Surface Shapes. In International Conf. on Computer Vision (ICCV). IEEE, 5442--5451. https:\/\/amass.is.tue.mpg.de\/"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-018-0209-y"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-00212-x"},{"key":"e_1_2_2_26_1","volume-title":"Efficient trajectory optimization for curved running using a 3D musculoskeletal model with implicit dynamics. Scientific reports 10, 1","author":"Nitschke Marlies","year":"2020","unstructured":"Marlies Nitschke, Eva Dorschky, Dieter Heinrich, Heiko Schlarb, Bjoern M Eskofier, Anne D Koelewijn, and Antonie J van den Bogert. 2020. Efficient trajectory optimization for curved running using a 3D musculoskeletal model with implicit dynamics. Scientific reports 10, 1 (2020), 1--12."},{"key":"e_1_2_2_27_1","volume-title":"Black","author":"Osman Ahmed A. A.","year":"2020","unstructured":"Ahmed A. A. Osman, Timo Bolkart, and Michael J. Black. 2020. STAR: Sparse Trained Articulated Human Body Regressor. In European Conf. on Computer Vision (ECCV), Vol. 12355. Springer, 598--613. https:\/\/star.is.tue.mpg.de\/"},{"key":"e_1_2_2_28_1","volume-title":"Black","author":"Osman Ahmed A A","year":"2022","unstructured":"Ahmed A A Osman, Timo Bolkart, Dimitrios Tzionas, and Michael J. Black. 2022. SUPR: A Sparse Unified Part-Based Human Body Model. In European Conf. on Computer Vision (ECCV). Springer, Springer, 568--585. https:\/\/supr.is.tue.mpg.de"},{"key":"e_1_2_2_29_1","volume-title":"IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). IEEE, 10975--10985","author":"Pavlakos Georgios","unstructured":"Georgios Pavlakos, Vasileios Choutas, Nima Ghorbani, Timo Bolkart, Ahmed A. A. Osman, Dimitrios Tzionas, and Michael J. Black. 2019. Expressive Body Capture: 3D Hands, Face, and Body from a Single Image. In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). IEEE, 10975--10985. https:\/\/smpl-x.is.tue.mpg.de"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/VRW58643.2023.00300"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2898748"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2586891"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766957"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.5220\/0010210600250036"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0141028"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107383"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00457"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1101\/2022.07.07.499061"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9290(88)90135-2"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322983"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_1"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1101\/2022.08.22.504896"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12575"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3618381","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3618381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T10:47:47Z","timestamp":1755773267000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3618381"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,5]]},"references-count":45,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,12,5]]}},"alternative-id":["10.1145\/3618381"],"URL":"https:\/\/doi.org\/10.1145\/3618381","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,5]]},"assertion":[{"value":"2023-12-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}