{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T14:15:17Z","timestamp":1774361717886,"version":"3.50.1"},"reference-count":52,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:00:00Z","timestamp":1774310400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:00:00Z","timestamp":1774310400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003665","name":"National IT Industry Promotion Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Foot\u2010ground contact information plays a crucial role in character animation and gait analysis, as it helps accurately simulating realistic movement patterns and understanding the biomechanics of walking. Existing motion datasets do not explicitly include foot\u2010ground contact information, requiring separate computation or manual annotation. Obtaining accurate foot\u2010ground contact information typically requires additional sensors such as pressure mats or force plates. Without such devices, estimating contact becomes a highly challenging task. We propose ContactVision, a deep learning framework that detects heel and toe contact states directly from video. Our network is trained in a supervised manner using contact labels derived from motion capture data via ground reaction force estimation. This enables training on existing datasets without the need for additional hardware. We demonstrate the utility of our contact detection network in two downstream tasks: gait motion reconstruction and gait analysis. For animation, we incorporate predicted contact labels into a reinforcement learning framework with a two\u2010segment foot model, enabling realistic foot articulation behavior. For analysis, we estimate clinically relevant gait parameters such as double and single support times, and validate the accuracy against pressure sensor mat data and prior video\u2010based methods. Our results show competitive performance in both animation and analysis settings. The code is publicly available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"http:\/\/github.com\/DaeeYong\/ContactVision\">github.com\/DaeeYong\/ContactVision<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1111\/cgf.70334","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:25:12Z","timestamp":1774358712000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ContactVision: Learning Foot Contact from Video for Physically Plausible Gait Animation"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3574-3007","authenticated-orcid":false,"given":"Daeyong","family":"Kim","sequence":"first","affiliation":[{"name":"Dept. of Artificial Intelligence Ajou University  South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0391-2544","authenticated-orcid":false,"given":"Gyuseok","family":"Yi","sequence":"additional","affiliation":[{"name":"Dept. of Software and Computer Engineering Ajou University  South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2377-8654","authenticated-orcid":false,"given":"Ri","family":"Yu","sequence":"additional","affiliation":[{"name":"Dept. of Artificial Intelligence Ajou University  South Korea"},{"name":"Dept. of Software and Computer Engineering Ajou University  South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"e_1_2_12_2_2","doi-asserted-by":"crossref","unstructured":"AbdolhosseiniF. LingH. Y. XieZ. PengX. B. Van de PanneM.: On learning symmetric locomotion. InProceedings of the 12th ACM SIGGRAPH Conference on Motion Interaction and Games(2019) pp.1\u201310. 3","DOI":"10.1145\/3359566.3360070"},{"key":"e_1_2_12_3_2","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1016\/j.gaitpost.2021.08.004","article-title":"Extraction of gait parameters from marker-free video recordings of timed up-and-go tests: Validity, inter-and intra-rater reliability","volume":"90","author":"\u00c5berg A. C.","year":"2021","journal-title":"Gait & Posture"},{"key":"e_1_2_12_4_2","doi-asserted-by":"crossref","unstructured":"AkibaT. SanoS. YanaseT. OhtaT. KoyamaM.: Optuna: A next-generation hyperparameter optimization framework. InProceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining(2019). 6","DOI":"10.1145\/3292500.3330701"},{"issue":"4","key":"e_1_2_12_5_2","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1109\/TITB.2007.899493","article-title":"Gait analysis using a shoe-integrated wireless sensor system","volume":"12","author":"Bamberg S. J. M.","year":"2008","journal-title":"IEEE transactions on information technology in biomedicine"},{"issue":"1","key":"e_1_2_12_6_2","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","article-title":"Openpose: Realtime multi-person 2d pose estimation using part affinity fields","volume":"43","author":"Cao Z.","year":"2019","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"1","key":"e_1_2_12_7_2","doi-asserted-by":"crossref","first-page":"3840","DOI":"10.1038\/s41598-024-53217-7","article-title":"Validation of portable in-clinic video-based gait analysis for prosthesis users","volume":"14","author":"Cimorelli A.","year":"2024","journal-title":"Scientific reports"},{"key":"e_1_2_12_8_2","doi-asserted-by":"crossref","unstructured":"ChenR. ShiM. HuangS. TanP. KomuraT. ChenX.: Taming diffusion probabilistic models for character control. InACM SIGGRAPH 2024 Conference Papers(2024) pp.1\u201310. 3","DOI":"10.1145\/3641519.3657440"},{"key":"e_1_2_12_9_2","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.medengphy.2017.10.004","article-title":"Prediction of ground reaction forces for parkinson's disease patients using a kinect-driven musculoskeletal gait analysis model","volume":"50","author":"Eltoukhy M.","year":"2017","journal-title":"Medical engineering & physics"},{"key":"e_1_2_12_10_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-04077-3"},{"issue":"14","key":"e_1_2_12_11_2","doi-asserted-by":"crossref","first-page":"6489","DOI":"10.3390\/s23146489","article-title":"Automated gait analysis based on a marker-free pose estimation model","volume":"23","author":"Hii C. S. T.","year":"2023","journal-title":"Sensors"},{"key":"e_1_2_12_12_2","doi-asserted-by":"crossref","unstructured":"HanX. SenderlingB. ToS. KumarD. WhitingE. SaitoJ.: Groundlink: A dataset unifying human body movement and ground reaction dynamics. InSIGGRAPH Asia 2023 Conference Papers(2023) pp.1\u201310. 1 3","DOI":"10.1145\/3610548.3618247"},{"issue":"7","key":"e_1_2_12_13_2","doi-asserted-by":"crossref","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","article-title":"Human3. 6m: Large scale datasets and predictive methods for 3d human sensing in natural environments","volume":"36","author":"Ionescu C.","year":"2013","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"11","key":"e_1_2_12_14_2","doi-asserted-by":"crossref","first-page":"2693","DOI":"10.1016\/j.jbiomech.2014.05.007","article-title":"Ground reaction force estimation using an insole-type pressure mat and joint kinematics during walking","volume":"47","author":"Jung Y.","year":"2014","journal-title":"Journal of biomechanics"},{"key":"e_1_2_12_15_2","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbiomech.2020.110074","article-title":"Estimation of the ground reaction forces from a single video camera based on the spring-like center of mass dynamics of human walking","volume":"113","author":"Jeong H.","year":"2020","journal-title":"Journal of Biomechanics"},{"issue":"1","key":"e_1_2_12_16_2","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-019-55432-z","article-title":"Analysis of 1.2 million foot scans from north america, europe and asia","volume":"9","author":"Jurca A.","year":"2019","journal-title":"Scientific reports"},{"key":"e_1_2_12_17_2","first-page":"e14988","volume-title":"Computer Graphics Forum","author":"Kim C.","year":"2024"},{"key":"e_1_2_12_18_2","article-title":"Flexible automatic motion blending with registration curves","volume":"2","author":"Kovar L.","year":"2003","journal-title":"Symposium on Computer Animation"},{"issue":"4","key":"e_1_2_12_19_2","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1145\/3386569.3392432","article-title":"Fast and flexible multilegged locomotion using learned centroidal dynamics","volume":"39","author":"Kwon T.","year":"2020","journal-title":"ACM Transactions on Graphics (TOG)"},{"issue":"6","key":"e_1_2_12_20_2","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1007\/s00371-015-1097-8","article-title":"Human motion control with physically plausible foot contact models","volume":"31","author":"Kim J.","year":"2015","journal-title":"The Visual Computer"},{"key":"e_1_2_12_21_2","first-page":"97","volume-title":"Footskate cleanup for motion capture editing","author":"Kovar L."},{"key":"e_1_2_12_21_3","doi-asserted-by":"crossref","unstructured":"doi:10.1145\/545261.545277. 2","DOI":"10.1145\/545261.545277"},{"key":"e_1_2_12_22_2","doi-asserted-by":"crossref","unstructured":"KovarL. SchreinerJ. GleicherM.: Footskate cleanup for motion capture editing. InProceedings of the 2002 ACM SIGGRAPH\/Eurographics symposium on Computer animation(2002) pp.97\u2013104. 3","DOI":"10.1145\/545261.545277"},{"key":"e_1_2_12_23_2","doi-asserted-by":"crossref","first-page":"6330","DOI":"10.1109\/WACV61041.2025.00617","volume-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","author":"Koleini F.","year":"2025"},{"key":"e_1_2_12_24_2","unstructured":"Lab C. M. U. G.:Cmu graphics lab motion capture database.http:\/\/mocap.cs.cmu.edu\/ 2003. Accessed: 2025-08-26. 2"},{"key":"e_1_2_12_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566607"},{"key":"e_1_2_12_25_3","doi-asserted-by":"crossref","unstructured":"doi:10.1145\/566654.566607. 2","DOI":"10.1145\/566654.566607"},{"issue":"1","key":"e_1_2_12_26_2","doi-asserted-by":"crossref","DOI":"10.1002\/cav.2217","article-title":"Foot-constrained spatial-temporal transformer for keyframe-based complex motion synthesis","volume":"35","author":"Li H.","year":"2024","journal-title":"Computer Animation and Virtual Worlds"},{"key":"e_1_2_12_27_2","doi-asserted-by":"crossref","unstructured":"Leal-JuniorA. Frizera-NetoA.:Optical fiber sensors for the next generation of rehabilitation robotics. Academic Press 2021. 13","DOI":"10.1016\/B978-0-32-385952-3.00014-7"},{"key":"e_1_2_12_28_2","doi-asserted-by":"crossref","unstructured":"LeeJ. ShinS. Y.: A hierarchical approach to interactive motion editing for human-like figures. InProceedings of the 26th annual conference on Computer graphics and interactive techniques(1999) pp.39\u201348. 2","DOI":"10.1145\/311535.311539"},{"key":"e_1_2_12_29_2","doi-asserted-by":"crossref","unstructured":"LiZ. SedlarJ. CarpentierJ. LaptevI. MansardN. SivicJ.: Estimating 3d motion and forces of person-object interactions from monocular video. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2019) pp.8640\u20138649. 2","DOI":"10.1109\/CVPR.2019.00884"},{"key":"e_1_2_12_30_2","doi-asserted-by":"crossref","unstructured":"LiJ. XuC. ChenZ. BianS. YangL. LuC.: Hybrik: A hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation. InProceedings of the IEEE\/CVF conference on computer vision and pattern recognition(2021) pp.3383\u20133393. 3 8","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"e_1_2_12_31_2","doi-asserted-by":"crossref","DOI":"10.3389\/fbioe.2022.857975","article-title":"The reliability and validity of gait analysis system using 3d markerless pose estimation algorithms","volume":"10","author":"Liang S.","year":"2022","journal-title":"Frontiers in Bioengineering and Biotechnology"},{"key":"e_1_2_12_32_2","first-page":"195","volume-title":"Computer Graphics Forum","author":"Mourot L.","year":"2022"},{"key":"e_1_2_12_33_2","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.medengphy.2020.10.001","article-title":"Prediction of ground reaction force and joint moments based on optical motion capture data during gait","volume":"86","author":"Mundt M.","year":"2020","journal-title":"Medical Engineering & Physics"},{"key":"e_1_2_12_34_2","volume-title":"3D Vision (3DV), 2017 Fifth International Conference on","author":"Mehta D.","year":"2017"},{"key":"e_1_2_12_34_3","doi-asserted-by":"crossref","unstructured":"doi:10.1109\/3dv.2017.00064. 2","DOI":"10.1109\/3DV.2017.00064"},{"issue":"3","key":"e_1_2_12_35_2","doi-asserted-by":"crossref","first-page":"370","DOI":"10.2106\/00004623-199903000-00009","article-title":"Relationship between clinical measurements and motion of the first metatarsophalangeal joint during gait","volume":"81","author":"Nawoczenski D. A.","year":"1999","journal-title":"JBJS"},{"key":"e_1_2_12_36_2","unstructured":"NandyA. ChakrabortyS. ChakrabortyJ. VentureG.:Modern methods for affordable clinical gait analysis: theories and applications in healthcare systems. Academic Press 2021. 13"},{"issue":"3","key":"e_1_2_12_37_2","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/j.gaitpost.2010.05.014","article-title":"Ambulatory assessment of 3d ground reaction force using plantar pressure distribution","volume":"32","author":"Rouhani H.","year":"2010","journal-title":"Gait & posture"},{"key":"e_1_2_12_38_2","unstructured":"RempeD. GuibasL. J. HertzmannA. RussellB. VillegasR. YangJ.: Contact and human dynamics from monocular video. InProceedings of the European Conference on Computer Vision (ECCV)(2020). 2 3 7 9 10 11 12 14"},{"issue":"1","key":"e_1_2_12_39_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3407659","article-title":"Motionet: 3d human motion reconstruction from monocular video with skeleton consistency","volume":"40","author":"Shi M.","year":"2020","journal-title":"Acm transactions on graphics (tog)"},{"issue":"4","key":"e_1_2_12_40_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3450626.3459825","article-title":"Neural monocular 3d human motion capture with physical awareness","volume":"40","author":"Shimada S.","year":"2021","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"e_1_2_12_41_2","doi-asserted-by":"crossref","unstructured":"SongW. JinX. LiS. ChenC. HaoA. HouX. LiN. QinH.: Arbitrary motion style transfer with multi-condition motion latent diffusion model. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2024) pp.821\u2013830. 3","DOI":"10.1109\/CVPR52733.2024.00084"},{"key":"e_1_2_12_42_2","doi-asserted-by":"crossref","unstructured":"TruongT. E. PisenoM. XieZ. LiuK.: Pdp: Physics-based character animation via diffusion policy. InSIGGRAPH Asia 2024 Conference Papers(2024) pp.1\u201310. 3","DOI":"10.1145\/3680528.3687683"},{"key":"e_1_2_12_43_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Advances in neural information processing systems"},{"issue":"6","key":"e_1_2_12_44_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3355089.3356499","article-title":"Learning body shape variation in physics-based characters","volume":"38","author":"Won J.","year":"2019","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_12_45_2","first-page":"213","volume-title":"Computer Graphics Forum","author":"Xie Z.","year":"2020"},{"issue":"6","key":"e_1_2_12_46_2","article-title":"Human dynamics from monocular video with dynamic camera movements","volume":"40","author":"Yu R.","year":"2021","journal-title":"ACM Trans. Graph."},{"issue":"4","key":"e_1_2_12_47_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201397","article-title":"Learning symmetric and low-energy locomotion","volume":"37","author":"Yu W.","year":"2018","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_12_48_2","doi-asserted-by":"crossref","unstructured":"ZhangZ. LiuR. HanockaR. AbermanK.: Tedi: Temporally-entangled diffusion for long-term motion synthesis. InACM SIGGRAPH 2024 Conference Papers(2024) pp.1\u201311. 3","DOI":"10.1145\/3641519.3657515"},{"key":"e_1_2_12_49_2","doi-asserted-by":"crossref","unstructured":"ZouY. YangJ. CeylanD. ZhangJ. PerazziF. HuangJ.-B.: Reducing footskate in human motion reconstruction with ground contact constraints. InProceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)(March2020). 2 3","DOI":"10.1109\/WACV45572.2020.9093329"},{"key":"e_1_2_12_50_2","unstructured":"ZouY. YangJ. CeylanD. ZhangJ. PerazziF. HuangJ.-B.: Reducing footskate in human motion reconstruction with ground contact constraints. InProceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision(2020) pp.459\u2013468. 2 3"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70334","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70334","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:25:28Z","timestamp":1774358728000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70334"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,24]]},"references-count":52,"alternative-id":["10.1111\/cgf.70334"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70334","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,24]]},"assertion":[{"value":"2026-03-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70334"}}