{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T05:29:38Z","timestamp":1781328578361,"version":"3.54.1"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T00:00:00Z","timestamp":1626652800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Beijing Higher Institution Engineering Research Center"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61521002, 61772298"],"award-info":[{"award-number":["61521002, 61772298"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key Technology RD Program","award":["2017YFB1002604"],"award-info":[{"award-number":["2017YFB1002604"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2021,8,31]]},"abstract":"<jats:p>\n            In a conventional optical motion capture (MoCap) workflow, two processes are needed to turn captured raw marker sequences into correct skeletal animation sequences. Firstly, various tracking errors present in the markers must be fixed (\n            <jats:italic>cleaning<\/jats:italic>\n            or\n            <jats:italic>refining<\/jats:italic>\n            ). Secondly, an agent skeletal mesh must be prepared for the actor\/actress, and used to determine skeleton information from the markers (\n            <jats:italic>re-targeting<\/jats:italic>\n            or\n            <jats:italic>solving<\/jats:italic>\n            ). The whole process, normally referred to as\n            <jats:italic>solving<\/jats:italic>\n            MoCap data, is extremely time-consuming, labor-intensive, and usually the most costly part of animation production. Hence, there is a great demand for automated tools in industry. In this work, we present MoCap-Solver, a production-ready neural solver for optical MoCap data. It can directly produce skeleton sequences and clean marker sequences from raw MoCap markers, without any tedious manual operations. To achieve this goal, our key idea is to make use of neural encoders concerning three key intrinsic components: the template skeleton, marker configuration and motion, and to learn to predict these latent vectors from imperfect marker sequences containing noise and errors. By decoding these components from latent vectors, sequences of clean markers and skeletons can be directly recovered. Moreover, we also provide a novel normalization strategy based on learning a pose-dependent marker reliability function, which greatly improves system robustness. Experimental results demonstrate that our algorithm consistently outperforms the state-of-the-art on both synthetic and real-world datasets.\n          <\/jats:p>","DOI":"10.1145\/3450626.3459681","type":"journal-article","created":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T00:04:26Z","timestamp":1626739466000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["MoCap-solver"],"prefix":"10.1145","volume":"40","author":[{"given":"Kang","family":"Chen","sequence":"first","affiliation":[{"name":"NetEase Games AI LAB, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yupan","family":"Wang","sequence":"additional","affiliation":[{"name":"NetEase Games AI LAB, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song-Hai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen-Zhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"NetEase Games AI LAB, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi-Min","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,7,19]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392462"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2159516.2159523"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13362"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-011-0671-y"},{"key":"e_1_2_2_5_1","volume-title":"Proc. of VRIPHYS. 111--118","author":"Baumann Jan","year":"2011","unstructured":"Jan Baumann , Bj\u00f6rn Kr\u00fcger , Arno Zinke , and Andreas Weber . 2011 . Data-driven completion of motion capture data . In Proc. of VRIPHYS. 111--118 . Jan Baumann, Bj\u00f6rn Kr\u00fcger, Arno Zinke, and Andreas Weber. 2011. Data-driven completion of motion capture data. In Proc. of VRIPHYS. 111--118."},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbiomech.2016.04.016"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073248"},{"key":"e_1_2_2_8_1","unstructured":"CMU. 2000. CMU graphics lab motion capture database. http:\/\/mocap.cs.cmu.edu (2000).  CMU. 2000. CMU graphics lab motion capture database. http:\/\/mocap.cs.cmu.edu (2000)."},{"key":"e_1_2_2_9_1","unstructured":"Klaus Dorfm\u00fcller-Ulhaas. 2007. Robust optical user motion tracking using a kalman filter. (2007).  Klaus Dorfm\u00fcller-Ulhaas. 2007. Robust optical user motion tracking using a kalman filter. (2007)."},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2381659"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.03.013"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.494"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392480"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417836"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CA.2000.889046"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201302"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925975"},{"key":"e_1_2_2_18_1","first-page":"1","article-title":"Learning motion manifolds with convolutional autoencoders","volume":"18","author":"Holden Daniel","year":"2015","unstructured":"Daniel Holden , Jun Saito , Taku Komura , and Thomas Joyce . 2015 . Learning motion manifolds with convolutional autoencoders . In SIGGRAPH Asia Technical Briefs. 18 : 1 -- 18 :4. Daniel Holden, Jun Saito, Taku Komura, and Thomas Joyce. 2015. Learning motion manifolds with convolutional autoencoders. In SIGGRAPH Asia Technical Briefs. 18:1--18:4.","journal-title":"SIGGRAPH Asia Technical Briefs."},{"key":"e_1_2_2_19_1","volume-title":"Proc. of VR. 75--82","author":"Hornung Alexander","year":"2005","unstructured":"Alexander Hornung , Sandip Sar-Dessai , and Leif Kobbelt . 2005 . Self-calibrating optical motion tracking for articulated bodies . In Proc. of VR. 75--82 . Alexander Hornung, Sandip Sar-Dessai, and Leif Kobbelt. 2005. Self-calibrating optical motion tracking for articulated bodies. In Proc. of VR. 75--82."},{"key":"e_1_2_2_20_1","volume-title":"Convolutional autoencoders for human motion infilling. CoRR","author":"Kaufmann Manuel","year":"2020","unstructured":"Manuel Kaufmann , Emre Aksan , Jie Song , Fabrizio Pece , Remo Ziegler , and Otmar Hilliges . 2020. Convolutional autoencoders for human motion infilling. CoRR ( 2020 ). Manuel Kaufmann, Emre Aksan, Jie Song, Fabrizio Pece, Remo Ziegler, and Otmar Hilliges. 2020. Convolutional autoencoders for human motion infilling. CoRR (2020)."},{"key":"e_1_2_2_21_1","volume-title":"Forsyth","author":"Kirk Adam G.","year":"2005","unstructured":"Adam G. Kirk , James F. O'Brien , and David A . Forsyth . 2005 . Skeletal parameter estimation from optical motion capture data. In Proc. of CVPR. 782--788. Adam G. Kirk, James F. O'Brien, and David A. Forsyth. 2005. Skeletal parameter estimation from optical motion capture data. In Proc. of CVPR. 782--788."},{"key":"e_1_2_2_22_1","volume-title":"Lee","author":"Lai Ranch Y. Q.","year":"2011","unstructured":"Ranch Y. Q. Lai , Pong C. Yuen , and Kelvin K. W . Lee . 2011 . Motion capture data completion and denoising by singular value thresholding. In EG Short Papers . 45--48. Ranch Y. Q. Lai, Pong C. Yuen, and Kelvin K. W. Lee. 2011. Motion capture data completion and denoising by singular value thresholding. In EG Short Papers. 45--48."},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275071"},{"key":"e_1_2_2_24_1","volume-title":"Proc. of SCA. 179--188","author":"Li Lei","year":"2010","unstructured":"Lei Li , James McCann , Nancy S. Pollard , and Christos Faloutsos . 2010 . BoLeRO: A principled technique for including bone length constraints in motion capture occlusion filling . In Proc. of SCA. 179--188 . Lei Li, James McCann, Nancy S. Pollard, and Christos Faloutsos. 2010. BoLeRO: A principled technique for including bone length constraints in motion capture occlusion filling. In Proc. of SCA. 179--188."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2019.03.010"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2980316"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-006-0080-9"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2014.06.009"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_2_2_30_1","volume-title":"Black","author":"Mahmood Naureen","year":"2019","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 Proc. of ICCV. 5441--5450. Naureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll, and Michael J. Black. 2019. AMASS: Archive of motion capture as surface shapes. In Proc. of ICCV. 5441--5450."},{"key":"e_1_2_2_31_1","volume-title":"A deep recurrent framework for cleaning motion capture data. CoRR","author":"Mall Utkarsh","year":"2017","unstructured":"Utkarsh Mall , G. Roshan Lal , Siddhartha Chaudhuri , and Parag Chaudhuri . 2017. A deep recurrent framework for cleaning motion capture data. CoRR ( 2017 ). Utkarsh Mall, G. Roshan Lal, Siddhartha Chaudhuri, and Parag Chaudhuri. 2017. A deep recurrent framework for cleaning motion capture data. CoRR (2017)."},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141970"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_2_2_34_1","volume-title":"Real-time neural network prediction for handling two-hands mutual occlusions. Comput. Graph. X 2","author":"Pavllo Dario","year":"2019","unstructured":"Dario Pavllo , Mathias Delahaye , Thibault Porssut , Bruno Herbelin , and Ronan Boulic . 2019. Real-time neural network prediction for handling two-hands mutual occlusions. Comput. Graph. X 2 ( 2019 ). Dario Pavllo, Mathias Delahaye, Thibault Porssut, Bruno Herbelin, and Ronan Boulic. 2019. Real-time neural network prediction for handling two-hands mutual occlusions. Comput. Graph. X 2 (2019)."},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01245-6"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359566.3360060"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1966394.1966397"},{"key":"e_1_2_2_40_1","volume-title":"Roweis","author":"Taylor Graham W.","year":"2006","unstructured":"Graham W. Taylor , Geoffrey E. Hinton , and Sam T . Roweis . 2006 . Modeling human motion using binary latent variables. In Proc. of NIPS. 1345--1352. Graham W. Taylor, Geoffrey E. Hinton, and Sam T. Roweis. 2006. Modeling human motion using binary latent variables. In Proc. of NIPS. 1345--1352."},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP.2016.7877975"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2014.08.017"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_2_2_44_1","volume-title":"Van Der Horst","author":"Zordan Victor B.","year":"2003","unstructured":"Victor B. Zordan and Nicholas C . Van Der Horst . 2003 . Mapping optical motion capture data to skeletal motion using a physical model. In Proc. of SCA. 245--250. Victor B. Zordan and Nicholas C. Van Der Horst. 2003. Mapping optical motion capture data to skeletal motion using a physical model. In Proc. of SCA. 245--250."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3450626.3459681","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3450626.3459681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:17:16Z","timestamp":1750191436000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3450626.3459681"}},"subtitle":["a neural solver for optical motion capture data"],"short-title":[],"issued":{"date-parts":[[2021,7,19]]},"references-count":43,"aliases":["10.1145\/3476576.3476641"],"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,8,31]]}},"alternative-id":["10.1145\/3450626.3459681"],"URL":"https:\/\/doi.org\/10.1145\/3450626.3459681","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,19]]},"assertion":[{"value":"2021-07-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}