{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:12:33Z","timestamp":1784268753094,"version":"3.55.0"},"reference-count":110,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Artificial Intelligence Research Resource","award":["NAIRR250199"],"award-info":[{"award-number":["NAIRR250199"]}]},{"name":"Delta and DeltaAI at the National Center for Supercomputing Applications"},{"name":"ACCESS allocations","award":["CIS250012"],"award-info":[{"award-number":["CIS250012"]}]},{"name":"ACCESS allocations","award":["CIS250816"],"award-info":[{"award-number":["CIS250816"]}]},{"name":"ACCESS allocations","award":["CIS251188"],"award-info":[{"award-number":["CIS251188"]}]},{"name":"ERC Consolidator","award":["101171131"],"award-info":[{"award-number":["101171131"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3680779","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:01Z","timestamp":1775505361000},"page":"9519-9536","source":"Crossref","is-referenced-by-count":1,"title":["Motion2VecSets: Non-Rigid Shape Reconstruction and Tracking With 4D Latent Set Diffusion"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2939-0055","authenticated-orcid":false,"given":"Jiapeng","family":"Tang","sequence":"first","affiliation":[{"name":"Technical University of Munich, Munchen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5163-6484","authenticated-orcid":false,"given":"Wei","family":"Cao","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biao","family":"Zhang","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Luo","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munchen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5316-3028","authenticated-orcid":false,"given":"Yaoyao","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6093-5199","authenticated-orcid":false,"given":"Matthias","family":"Nie\u00dfner","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munchen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/280811.281026"},{"key":"ref2","first-page":"61","article-title":"Poisson surface reconstruction","volume-title":"Proc. 4th Eurographics Symp. Geometry Process.","author":"Kazhdan","year":"2006"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.19"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298631"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_22"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00761"},{"key":"ref8","first-page":"109","article-title":"As-rigid-as-possible surface modeling","volume-title":"Proc. Symp. Geometry Process.","author":"Sorkine","year":"2007"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276478"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref11","first-page":"598","article-title":"STAR: A sparse trained articulated human body regressor","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Osman","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.586"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00548"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00596"},{"key":"ref17","first-page":"6614","article-title":"CaDeX: Learning canonical deformation coordinate space for dynamic surface representation via neural homeomorphism","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Lei","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_31"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02426"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01937"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.591"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01247"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01276"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.19"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00053"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00209"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.264"},{"key":"ref33","first-page":"40","article-title":"Learning representations and generative models for 3D point clouds","volume-title":"Proc. Int. Conf. Mach. Learn. PMLR","author":"Achlioptas","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.701"},{"issue":"4","key":"ref36","first-page":"1","article-title":"O-CNN: Octree-based convolutional neural networks for 3D shape analysis","volume":"36","author":"Wang","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.230"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_4"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00030"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00308"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00467"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01006"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087358"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00609"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref46","first-page":"3569","article-title":"Implicit geometric regularization for learning shapes","volume-title":"Proc. Mach. Learn. Syst.","author":"Gropp","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00700"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_36"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_18"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01680"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00644"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1245"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01246"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00530"},{"key":"ref55","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref56","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref57","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref58","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal","year":"2021"},{"key":"ref59","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1114"},{"key":"ref62","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref63","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref65","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0313"},{"key":"ref68","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Austin","year":"2021"},{"key":"ref69","article-title":"DiffuSeq: Sequence to sequence text generation with diffusion models","author":"Gong","year":"2022"},{"key":"ref70","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00577"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00215"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_5"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3658170"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01322"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0462"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00112"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16788-1_18"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01447"},{"key":"ref85","first-page":"10021","article-title":"LION: Latent point diffusion models for 3D shape generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vahdat","year":"2022"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref88","article-title":"DreamFusion: Text-to-3D using 2D diffusion","author":"Poole","year":"2022"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"ref90","article-title":"LaGeM: A large geometry model for 3D representation learning and diffusion","author":"Zhang","year":"2024"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3873"},{"key":"ref93","article-title":"Hunyuan3D 1.0: A unified framework for text-to-3D and image-to-3D generation","author":"Yang","year":"2024"},{"key":"ref94","article-title":"Hunyuan3D 2.0: Scaling diffusion models for high resolution textured 3D assets generation","author":"Zhao","year":"2025"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1383"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3731149"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01491"},{"key":"ref98","article-title":"Human motion diffusion model","author":"Tevet","year":"2022"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1810"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3519"},{"key":"ref103","article-title":"Consistent4D: Consistent 360\u00b0 dynamic object generation from monocular video","author":"Jiang","year":"2023"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref105","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00908"},{"key":"ref107","first-page":"6572","article-title":"Neural ordinary differential equations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2018"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3633512"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11475204.pdf?arnumber=11475204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:44:49Z","timestamp":1783453489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11475204\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":110,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3680779","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}