{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:07Z","timestamp":1777888687675,"version":"3.51.4"},"reference-count":55,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206147"],"award-info":[{"award-number":["62206147"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018898","name":"Ant Group","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018898","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\/iccv51701.2025.02694","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"29010-29020","source":"Crossref","is-referenced-by-count":0,"title":["LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion"],"prefix":"10.1109","author":[{"given":"Fangfu","family":"Liu","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"NTU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Chi","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghui","family":"Yang","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fudong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueqi","family":"Duan","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Amit","year":"2021","journal-title":"Segdiff: Image segmentation with diffusion probabilistic models"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref3","author":"Bahmani","year":"2024","journal-title":"Vd3d: Taming large video diffusion transformers for 3d camera control"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3494046"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref8","first-page":"40212","article-title":"Large spatial model: End-to-end unposed images to semantic 3d","volume":"37","author":"Fan","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00512"},{"key":"ref12","author":"He","year":"2024","journal-title":"Cameractrl: Enabling camera control for text-to-video generation"},{"key":"ref13","author":"Hu","year":"2024","journal-title":"Sparselgs: Sparse view language embedded gaussian splatting"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00193"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","article-title":"Language-driven semantic segmentation","volume-title":"International Conference on Learning Representations","author":"Li","year":"2022"},{"key":"ref20","author":"Li","year":"2024","journal-title":"Langsurf: Language-embedded surface gaussians for 3d scene understanding"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02051"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01963"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01419"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01668"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3666733"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72907-2_23"},{"key":"ref28","author":"Liu","year":"2024","journal-title":"Physics3d: Learning physical properties of 3d gaussians via video diffusion"},{"key":"ref29","author":"Loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01708"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkg509"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref35","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref36","article-title":"Language embedded radiance fields for zero-shot task-oriented grasping","volume-title":"7th Annual Conference on Robot Learning","author":"Rashid","year":"2023"},{"key":"ref37","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01208"},{"key":"ref39","author":"Shan","year":"2023","journal-title":"Robustness of segment anything model (sam) for autonomous driving in adverse weather conditions"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02127"},{"key":"ref41","author":"Sun","year":"2024","journal-title":"Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion"},{"key":"ref42","article-title":"Neural discrete representation learning","volume":"30","author":"Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref43","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref46","author":"Wu","year":"2024","journal-title":"Opengaussian: Towards point-level 3d gaussian-based open vocabulary understanding"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.4324\/9780203411148"},{"key":"ref49","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3687971"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1399"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref53","author":"Zhang","year":"2024","journal-title":"Sam-e: leveraging visual foundation model with sequence imitation for embodied manipulation"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_16"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"}],"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\/11445176.pdf?arnumber=11445176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:20Z","timestamp":1777611320000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02694","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}