{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T20:13:06Z","timestamp":1779307986042,"version":"3.51.4"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100019635","name":"IITP","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019635","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","award":["IITP-2026-RS-2024-00436398"],"award-info":[{"award-number":["IITP-2026-RS-2024-00436398"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2021-NR059444"],"award-info":[{"award-number":["RS-2021-NR059444"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003661","name":"Korea Institute for Advancement of Technology","doi-asserted-by":"publisher","award":["RS-2025-02304167"],"award-info":[{"award-number":["RS-2025-02304167"]}],"id":[{"id":"10.13039\/501100003661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tvcg.2026.3679893","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:12:20Z","timestamp":1775074340000},"page":"3125-3135","source":"Crossref","is-referenced-by-count":0,"title":["SceneLinker: Compositional 3D Scene Generation via Semantic Scene Graph from RGB Sequences"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7336-5699","authenticated-orcid":false,"given":"Seok-Young","family":"Kim","sequence":"first","affiliation":[{"name":"KAIST UVR Lab., Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6003-2181","authenticated-orcid":false,"given":"Dooyoung","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST KI-ITC ARRC, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4615-5630","authenticated-orcid":false,"given":"Woojin","family":"Cho","sequence":"additional","affiliation":[{"name":"KAIST KI-ITC PMRC, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4008-196X","authenticated-orcid":false,"given":"Hail","family":"Song","sequence":"additional","affiliation":[{"name":"KAIST UVR Lab., Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1614-6245","authenticated-orcid":false,"given":"Suji","family":"Kang","sequence":"additional","affiliation":[{"name":"KAIST UVR Lab., Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5501-4421","authenticated-orcid":false,"given":"Woontack","family":"Woo","sequence":"additional","affiliation":[{"name":"KAIST UVR Lab., Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2018.8446560"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_14"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00753"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075644"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92387-6_17"},{"key":"ref7","article-title":"Shapenet: An information-rich 3d model repository","volume":"abs\/1512.03012","author":"Chang","year":"2015","journal-title":"ArXiv"},{"key":"ref8","article-title":"Sam 3d: 3dfy anything in images","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474750"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237269"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01604"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964929"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_21"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.02353"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300577"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","article-title":"Video perception models for 3d scene synthesis","author":"Huang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02202"},{"key":"ref23","article-title":"Hydra: A real-time spatial per-ception system for 3d scene graph construction and optimization","author":"Hughes","year":"2022","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2025.3555901"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3746058.3758405"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2931042"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3746059.3747635"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00936"},{"key":"ref31","article-title":"Instructscene: Instruction-driven 3d indoor scene synthesis with semantic graph prior","volume-title":"arXiv preprint","author":"Lin","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0976"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00381"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00816"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref38","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Qi","year":"2017"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref40","article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable task planning","volume-title":"7th Annual Conference on Robot Learning","author":"Rana","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196885"},{"key":"ref43","article-title":"Khronos: A unified approachfor spatio-temporal metric-semantic slam in dynamic environments","author":"Schmid","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Sg-tailor: Inter-object commonsense relationship reasoning for scene graph manipulation","author":"Shang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3873"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR-Adjunct51615.2020.00072"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02086"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2015.7354011"},{"key":"ref50","article-title":"Neural discrete representation learning","volume":"30","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref51","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00775"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00402"},{"key":"ref54","article-title":"Hierarchicalopen-vocabulary 3d scene graphs for language-grounded robotnavigation","volume-title":"First Workshop on Vision-Language Models for Navigationand Manipulation at ICRA 2024","author":"Werby","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00490"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00743"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02000"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00477"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"issue":"3","key":"ref60","article-title":"Clevr3d: Compositional language and elementary visual reasoning for question answering in 3d real-world scenes","volume":"2","author":"Yan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33017"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610792"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_10"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1307"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00958"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11526953\/11460307.pdf?arnumber=11460307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:52:16Z","timestamp":1779306736000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11460307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":66,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2026.3679893","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}