{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:57Z","timestamp":1779948117486,"version":"3.53.1"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"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":["2106825,2519216"],"award-info":[{"award-number":["2106825,2519216"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N00014-26-1-2099"],"award-info":[{"award-number":["N00014-26-1-2099"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005825","name":"NIFA","doi-asserted-by":"publisher","award":["2020-67021-32799"],"award-info":[{"award-number":["2020-67021-32799"]}],"id":[{"id":"10.13039\/100005825","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00150","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1577-1587","source":"Crossref","is-referenced-by-count":0,"title":["HDEdit: Editing Videos and 3D Scenes with Video Diffusion Through Hierarchical Task Decomposition"],"prefix":"10.1109","author":[{"given":"Yanming","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun-Kun","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jipeng","family":"Lyu","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Xiong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0160"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01991"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"ref7","article-title":"Slicedit: Zeroshot video editing with text-to-image diffusion models using spatio-temporal slices","author":"Cohen","year":"2024","journal-title":"arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2686"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_14"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"ref12","author":"Hertz","year":"2022","journal-title":"Prompt-to-prompt image editing with cross attention control"},{"key":"ref13","author":"Ho","year":"2022","journal-title":"Imagen video: High definition video generation with diffusion models"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref15","author":"Hong","year":"2022","journal-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323006"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_21"},{"key":"ref19","article-title":"Collaborative score distillation for consistent visual editing","author":"Kim","year":"2023","journal-title":"NeurIPS"},{"key":"ref20","author":"Kong","year":"2024","journal-title":"HunyuanVideo: A systematic framework for large video generative models"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01268"},{"key":"ref22","author":"Ku","year":"2024","journal-title":"AnyV2V: A tuning-free framework for any video-tovideo editing tasks"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01376"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3639307\/mm1"},{"key":"ref26","author":"Liu","year":"2024","journal-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models"},{"key":"ref27","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"ICLR","author":"Meng","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01907"},{"key":"ref30","author":"Achiam","year":"2023","journal-title":"GPT-4 technical report"},{"key":"ref31","author":"Pont-Tuset","year":"2017","journal-title":"The 2017 DAVIS challenge on video object segmentation"},{"key":"ref32","article-title":"DreamFusion: Text-to-3D using 2D diffusion","author":"Poole","year":"2023","journal-title":"ICLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref34","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00706"},{"key":"ref37","author":"Singer","year":"2022","journal-title":"Make-A-Video: Text-to-video generation without text-video data"},{"key":"ref38","author":"Song","year":"2023","journal-title":"EfficientNeRF2NeRF: Streamlining text-driven 3D editing with multiview correspondence-enhanced diffusion models"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591516"},{"key":"ref40","author":"Vachha","year":"2024","journal-title":"Instruct-GS2GS: Editing 3D Gaussian splats with instructions"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_23"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00701"},{"key":"ref44","author":"Zhangjie Wu","year":"2023","journal-title":"CVPR 2023 text guided video editing competition"},{"key":"ref45","author":"Xie","year":"2024","journal-title":"SV4D: Dynamic 3D content generation with multi-frame and multi-view consistency"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/e25101469"},{"key":"ref47","author":"Yang","year":"2024","journal-title":"CogVideoX: Text-to-video diffusion models with an expert transformer"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533322.pdf?arnumber=11533322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:02:56Z","timestamp":1779944576000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00150","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}