{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T11:40:35Z","timestamp":1786621235982,"version":"3.56.0"},"reference-count":50,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP220102197"],"award-info":[{"award-number":["DP220102197"]}],"id":[{"id":"10.13039\/501100000923","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                    We propose a novel framework for the statistical modeling and analysis of the spatio\u2010temporal shape variability in articulated 4D (i.e., 3D + time) shapes such as human bodies and animals. We treat articulated 3D shapes, represented using parametric models such as SMPL or its variants, as elements of the product space of shape and pose parameters. 4D shapes can then be seen as trajectories in this space, which has a nonlinear Riemannian structure. Our key contribution is to treat these trajectories as elements of a Riemannian shape space and propose computational tools that (\n                    <jats:bold>1<\/jats:bold>\n                    ) perform temporal alignment of such trajectories to account for variations in their execution rates, (\n                    <jats:bold>2<\/jats:bold>\n                    ) compute geodesics between trajectories, and thus 4D shapes, even when they exhibit different execution rates, and (\n                    <jats:bold>3<\/jats:bold>\n                    ) statistically model the spatio\u2010temporal variability of collections of 4D shapes, enabling us to compute statistical summaries such as means and principal modes of variation. We derive a simple, yet efficient, framework for characterizing populations of 4D shapes using statistical models, which in turn can be used as a generative model for synthesizing novel 4D shapes by sampling from these distributions. We demonstrate the effectiveness of the proposed framework using publicly available 4D human and animal datasets, and show that it outperforms the state\u2010of\u2010the\u2010art both in terms of accuracy and computational efficiency. Our code, dataset, and videos that illustrate the results are available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/arti4d.github.io\/Arti4D\/\">https:\/\/arti4d.github.io\/Arti4D\/<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1111\/cgf.70521","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T11:24:25Z","timestamp":1786620265000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Arti4D: Statistical Analysis and Modelling of the Spatio\u2010temporal Variability in Articulated 4D Shapes"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5183-0660","authenticated-orcid":false,"given":"Z.","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Technology Murdoch University  Perth Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9231-1671","authenticated-orcid":false,"given":"A.","family":"Amrani","sequence":"additional","affiliation":[{"name":"School of Information Technology Murdoch University  Perth Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6644-5833","authenticated-orcid":false,"given":"S.","family":"Rai","sequence":"additional","affiliation":[{"name":"School of Information Technology Murdoch University  Perth Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4758-7510","authenticated-orcid":false,"given":"H.","family":"Laga","sequence":"additional","affiliation":[{"name":"School of Information Technology Murdoch University  Perth Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"key":"e_1_2_8_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882311"},{"key":"e_1_2_8_3_2","doi-asserted-by":"crossref","unstructured":"AgataN. IgarashiT.: Motion control via metric-aligning motion matching. InProceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers(2025) pp.1\u201312. 6 7 8 9","DOI":"10.1145\/3721238.3730665"},{"key":"e_1_2_8_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439257"},{"key":"e_1_2_8_5_2","doi-asserted-by":"crossref","unstructured":"AnirudhR. TuragaP. SuJ. SrivastavaA.: Elastic functional coding of human actions: From vector-fields to latent variables. InIEEE CVPR(2015) pp.3147\u20133155. 3","DOI":"10.1109\/CVPR.2015.7298934"},{"key":"e_1_2_8_6_2","doi-asserted-by":"crossref","unstructured":"AlldieckT. XuH. SminchisescuC.: imghum: Implicit generative models of 3d human shape and articulated pose. InProceedings of the IEEE\/CVF International Conference on Computer Vision(2021) pp.5461\u20135470. 2","DOI":"10.1109\/ICCV48922.2021.00541"},{"key":"e_1_2_8_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01343-w"},{"key":"e_1_2_8_8_2","unstructured":"BaieriD. EspositoS. MaggioliF. Rodol\u00e0E.:Fluid dynamics network: Topology-agnostic 4d reconstruction via fluid dynamics priors 2023. URL:https:\/\/arxiv.org\/abs\/2303.09871 arXiv:2303.09871. 3"},{"key":"e_1_2_8_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964970"},{"key":"e_1_2_8_10_2","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000043755.93987.aa"},{"key":"e_1_2_8_11_2","doi-asserted-by":"crossref","unstructured":"BogoF. RomeroJ. Pons-MollG. BlackM. J.: Dynamic FAUST: Registering human bodies in motion. InIEEE Conf. on Computer Vision and Pattern Recognition (CVPR)(July2017). 6","DOI":"10.1109\/CVPR.2017.591"},{"key":"e_1_2_8_12_2","doi-asserted-by":"crossref","unstructured":"BlanzV. VetterT.: A morphable model for the synthesis of 3d faces. InACM Siggraph(1999) pp.187\u2013194. 2","DOI":"10.1145\/311535.311556"},{"issue":"1","key":"e_1_2_8_13_2","article-title":"Active shape models-their training and application","volume":"61","author":"Cootes T.","year":"1995","journal-title":"CVIU"},{"key":"e_1_2_8_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_8"},{"key":"e_1_2_8_14_3","doi-asserted-by":"crossref","unstructured":"doi:10.1007\/978-3-030-32251-9_8. 3","DOI":"10.1007\/978-3-030-32251-9_8"},{"key":"e_1_2_8_15_2","unstructured":"DebavelaereV. DurrlemanS. Allassonni\u00e8reS. InitiativeA. D. N.: Learning the Clustering of Longitudinal Shape Data Sets into a Mixture of Independent or Branching Trajectories.IJCV(2020) 1\u201316. 3"},{"key":"e_1_2_8_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2004.831793"},{"key":"e_1_2_8_17_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2012.03180.x"},{"key":"e_1_2_8_18_2","doi-asserted-by":"crossref","unstructured":"HeY. TiwariG. BirdalT. LenssenJ. E. Pons-MollG.: Nrdf: Neural riemannian distance fields for learning articulated pose priors. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2024) pp.1661\u20131671. 3","DOI":"10.1109\/CVPR52733.2024.00164"},{"key":"e_1_2_8_19_2","first-page":"804","volume-title":"European conference on computer vision","author":"Jermyn I. H.","year":"2012"},{"issue":"1","key":"e_1_2_8_20_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-031-01819-0","article-title":"Elastic shape analysis of three-dimensional objects","volume":"12","author":"Jermyn I. H.","year":"2017","journal-title":"Synthesis Lectures on Computer Vision"},{"key":"e_1_2_8_21_2","doi-asserted-by":"crossref","unstructured":"JooH. SimonT. SheikhY.: Total capture: A 3d deformation model for tracking faces hands and bodies. InProceedings of the IEEE conference on computer vision and pattern recognition(2018) pp.8320\u20138329. 2","DOI":"10.1109\/CVPR.2018.00868"},{"key":"e_1_2_8_22_2","doi-asserted-by":"crossref","unstructured":"KilianM. MitraN. J. PottmannH.: Geometric modeling in shape space. InACM SIGGRAPH(2007). 2","DOI":"10.1145\/1275808.1276457"},{"key":"e_1_2_8_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-811889-4.00007-5"},{"key":"e_1_2_8_24_2","unstructured":"LiZ. AmraniA. RaiS. LagaH.: Advances and trends in the 3d reconstruction of the shape and motion of animals.arXiv preprint arXiv:2508.16062(2025). 2 3"},{"key":"e_1_2_8_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_2_8_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_2_8_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3163720"},{"key":"e_1_2_8_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2647596"},{"key":"e_1_2_8_29_2","doi-asserted-by":"crossref","unstructured":"LyuJ. ZhuT. GuY. LinL. ChengP. LiuY. TangX. AnL.: AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer. InProceedings of the Computer Vision and Pattern Recognition Conference(2025) pp.17486\u201317496. 6","DOI":"10.1109\/CVPR52734.2025.01629"},{"key":"e_1_2_8_30_2","unstructured":"NizamaniA. LagaH. WangG. BoussaidF. BennamounM. SrivastavaA.: Dynamic neural surfaces for elastic 4d shape representation and analysis. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2025). 3 6 7 8 9"},{"key":"e_1_2_8_31_2","first-page":"598","volume-title":"European Conference on Computer Vision","author":"Osman A. A.","year":"2020"},{"key":"e_1_2_8_32_2","doi-asserted-by":"crossref","unstructured":"PavlakosG. ChoutasV. GhorbaniN. BolkartT. OsmanA. A. TzionasD. BlackM. J.: Expressive body capture: 3d hands face and body from a single image. InIEEE CVPR(2019) pp.10975\u201310985. 2","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_2_8_33_2","doi-asserted-by":"crossref","unstructured":"PavlakosG. ChoutasV. GhorbaniN. BolkartT. OsmanA. A. A. TzionasD. BlackM. J.: Expressive body capture: 3D hands face and body from a single image. InProceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)(2019) pp.10975\u201310985. 3 6","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_2_8_34_2","doi-asserted-by":"crossref","unstructured":"ParkJ. RomeroJ. SaitoS. PradaF. ShiratoriT. XuY. BogoF. YuS.-I. KitaniK. KhirodkarR.: ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling.IEEE\/CVF ICCV(2025). 2","DOI":"10.1109\/ICCV51701.2025.00614"},{"issue":"6","key":"e_1_2_8_35_2","article-title":"Embodied hands: Modeling and capturing hands and bodies together","volume":"36","author":"Romero J.","year":"2017","journal-title":"ACM Transactions on Graphics, (Proc. SIGGRAPH Asia)"},{"issue":"6","key":"e_1_2_8_36_2","article-title":"Embodied hands: Modeling and capturing hands and bodies together","volume":"36","author":"Romero J.","year":"2017","journal-title":"ACM Transactions on Graphics, (Proc. SIGGRAPH Asia)"},{"key":"e_1_2_8_37_2","doi-asserted-by":"crossref","unstructured":"R\u00fceggN. TripathiS. SchindlerK. BlackM. J. ZuffiS.: BITE: Beyond priors for improved three-D dog pose estimation. InIEEE\/CVF CVPR(2023) pp.8867\u20138876. 2 3","DOI":"10.1109\/CVPR52729.2023.00856"},{"key":"e_1_2_8_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.184"},{"key":"e_1_2_8_39_2","doi-asserted-by":"publisher","DOI":"10.1214\/13-AOAS701"},{"key":"e_1_2_8_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/2159516.2159517"},{"key":"e_1_2_8_41_2","doi-asserted-by":"crossref","unstructured":"TangJ. XuD. JiaK. ZhangL.:Learning parallel dense correspondence from spatio-temporal descriptors for efficient and robust 4d reconstruction 2021. doi:10.1109\/CVPR46437.2021.00596. 3","DOI":"10.1109\/CVPR46437.2021.00596"},{"key":"e_1_2_8_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-010-0416-9"},{"key":"e_1_2_8_43_2","unstructured":"WandM. JenkeP. HuangQ. BokelohM. GuibasL. SchillingA.: Reconstruction of deforming geometry from time-varying point clouds. InSGP(2007) pp.49\u201358. 2"},{"key":"e_1_2_8_44_2","first-page":"265","volume-title":"Computer Graphics Forum","author":"Weber O.","year":"2007"},{"key":"e_1_2_8_45_2","first-page":"2134","volume-title":"ICCV","author":"Windheuser T.","year":"2011"},{"key":"e_1_2_8_46_2","doi-asserted-by":"crossref","unstructured":"XuH. BazavanE. G. ZanfirA. FreemanW. T. SukthankarR. SminchisescuC.: Ghum & ghuml: Generative 3d human shape and articulated pose models. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2020) pp.6184\u20136193. 2","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"e_1_2_8_47_2","unstructured":"YuZ. FotiS. ZhangL. ZhaoA. KeskinC. ZafeiriouS. BirdalT.: Geometric neural distance fields for learning human motion priors.arXiv preprint arXiv:2509.09667(2025). 3"},{"key":"e_1_2_8_48_2","doi-asserted-by":"crossref","unstructured":"ZhangC. HeerenB. RumpfM. SmithW. A.: Shell PCA: statistical shape modelling in shell space. InIEEE CVPR(2015) pp.1671\u20131679. 2","DOI":"10.1109\/ICCV.2015.195"},{"key":"e_1_2_8_49_2","unstructured":"ZuffiS. KanazawaA. Berger-WolfT. BlackM. J.: Three-d safari: Learning to estimate zebra pose shape and texture from images. InIEEE CVPR(2019) pp.5359\u20135368. 2"},{"key":"e_1_2_8_50_2","doi-asserted-by":"crossref","unstructured":"ZuffiS. KanazawaA. JacobsD. W. BlackM. J.: 3d menagerie: Modeling the 3d shape and pose of animals. InProceedings of the IEEE conference on computer vision and pattern recognition(2017) pp.6365\u20136373. 2 3 6","DOI":"10.1109\/CVPR.2017.586"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70521","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70521","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T11:24:35Z","timestamp":1786620275000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70521"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":50,"alternative-id":["10.1111\/cgf.70521"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70521","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]},"assertion":[{"value":"2026-08-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70521"}}