{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:25:07Z","timestamp":1783106707674,"version":"3.54.6"},"reference-count":85,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2220868,IIS-RI 2212433"],"award-info":[{"award-number":["2220868,IIS-RI 2212433"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N00014-22-1-2677"],"award-info":[{"award-number":["N00014-22-1-2677"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01332","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14357-14368","source":"Crossref","is-referenced-by-count":1,"title":["DIMO: Diverse 3D Motion Generation for Arbitrary Objects"],"prefix":"10.1109","author":[{"given":"Linzhan","family":"Mou","sequence":"first","affiliation":[{"name":"University of Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahui","family":"Lei","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingjie","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kostas","family":"Daniilidis","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02130"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"ref4","article-title":"Vd3d: Taming large video diffusion transformers for 3d camera control","author":"Bahmani","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref7","volume-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3048"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref10","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"ref13","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00404"},{"key":"ref16","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00051"},{"key":"ref18","article-title":"Consistent4d: Consistent $360\\{\\backslash$ deg $\\}$ dynamic object generation from monocular video","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00192"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref21","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_15"},{"key":"ref24","article-title":"Collaborative video diffusion: Consistent multi-video generation with camera control","author":"Kuang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00647"},{"key":"ref26","article-title":"Mosca: Dynamic gaussian fusion from casual videos via 4d motion scaffolds","author":"Lei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Dreammesh4d: Video-to-4d generation with sparse-controlled gaussian-mesh hybrid representation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00931"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3519"},{"key":"ref30","article-title":"Human motion modeling using dvgans","author":"Lin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"ref32","first-page":"9298","article-title":"Zero-1-to3: Zero-shot one image to 3d object","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Liu","year":"2023"},{"key":"ref33","first-page":"851","article-title":"Smpl: A skinned multiperson linear model","volume":"2","author":"Loper","year":"2023","journal-title":"Seminal Graphics Papers: Pushing the Boundaries"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref35","article-title":"Unsupervised learning of object structure and dynamics from videos","volume":"32","author":"Minderer","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02615-z"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref39","first-page":"10985","article-title":"Actionconditioned 3d human motion synthesis with transformer vae","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Petrovich","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref41","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref43","article-title":"Dreamgaussian4d: Generative 4d gaussian splatting","author":"Ren","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"L4gm: Large 4d gaussian reconstruction model","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_16"},{"key":"ref47","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Text-to-4d dynamic scene generation","author":"Singer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","first-page":"109","article-title":"As-rigid-as-possible surface modeling","volume-title":"Symposium on Geometry processing","author":"Sorkine"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530178"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1275808.1276478"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00221"},{"key":"ref53","first-page":"90019010","article-title":"Bkind-3d: self-supervised 3d keypoint discovery from multiview videos","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Jennifer","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_6"},{"key":"ref55","article-title":"Eg4d: Explicit generation of 4d object without score distillation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref58","article-title":"Human motion diffusion model","volume-title":"The Eleventh International Conference on Learning Representations","author":"Tevet","year":"2023"},{"key":"ref59","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref62","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72913-3_3"},{"key":"ref64","article-title":"Shape of motion: 4 d reconstruction from a single video","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref66","article-title":"Controlling space and time with diffusion models","author":"Watson","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02427"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00849"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_21"},{"key":"ref70","article-title":"Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","article-title":"Camco: Cameracontrollable 3d-consistent image-to-video generation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01630"},{"key":"ref73","article-title":"Diffusion 2: Dynamic 3d content generation via score composition of orthogonal diffusion models","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01231"},{"key":"ref76","article-title":"4dgen: Grounded 4d content generation with spatial-temporal consistency","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_10"},{"key":"ref78","article-title":"4diffusion: Multi-view video diffusion model for 4 d generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657417"},{"key":"ref83","article-title":"Animate124: Animating one image to 4d dynamic scene","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00697"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_2"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443303.pdf?arnumber=11443303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:25Z","timestamp":1777613305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01332","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}