{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T20:13:36Z","timestamp":1779308016354,"version":"3.51.4"},"reference-count":82,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tvcg.2026.3679097","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T19:52:38Z","timestamp":1774986758000},"page":"3530-3540","source":"Crossref","is-referenced-by-count":2,"title":["ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3139-7616","authenticated-orcid":false,"given":"Jinyan","family":"Yuan","sequence":"first","affiliation":[{"name":"Bytedance, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7604-5553","authenticated-orcid":false,"given":"Bangbang","family":"Yang","sequence":"additional","affiliation":[{"name":"Bytedance, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1854-2539","authenticated-orcid":false,"given":"Keke","family":"Wang","sequence":"additional","affiliation":[{"name":"Bytedance, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8631-012X","authenticated-orcid":false,"given":"Panwang","family":"Pan","sequence":"additional","affiliation":[{"name":"Bytedance, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2568-2735","authenticated-orcid":false,"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Bytedance, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9972-2916","authenticated-orcid":false,"given":"Xuehai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Bytedance, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6073-030X","authenticated-orcid":false,"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[{"name":"Bytedance, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7130-439X","authenticated-orcid":false,"given":"Zhaopeng","family":"Cui","sequence":"additional","affiliation":[{"name":"Zhejiang University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7734-7053","authenticated-orcid":false,"given":"Yuewen","family":"Ma","sequence":"additional","affiliation":[{"name":"Bytedance, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","volume-title":"BlenderMCP","volume":"2025","author":"Ahuja"},{"key":"ref2","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","author":"Bar-Tal","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Midas v3.1 - a model zoo for robust monocular relative depth estimation","author":"Birkl","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3321857"},{"key":"ref5","article-title":"Luciddreamer: Domain-free generation of 3d gaussian splatting scenes","volume-title":"arXiv preprint","author":"Chung","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00314"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1201775.882326"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02561"},{"key":"ref10","article-title":"Diffusion360: Seamless 360 degree panoramic image generation based on diffusion models","author":"Feng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Scenescape: Text-driven consistent scene generation","volume":"36","author":"Fridman","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-12107-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02005"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730607"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01381"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref18","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00615"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02202"},{"key":"ref21","volume-title":"SpeedTree","year":"2024"},{"key":"ref22","author":"Kratt","year":"2014","journal-title":"Adaptive billboard clouds for botanical tree models"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v19i1.27504"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3627101"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480525"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275042"},{"key":"ref27","author":"Li","year":"2024","journal-title":"4k4dgen: Panoramic 4d generation at 4k resolution"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00083"},{"key":"ref29","article-title":"Instructscene: Instruction-driven 3d indoor scene synthesis with semantic graph prior","volume-title":"The International Conference on Learning Representations","author":"Lin","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02085"},{"key":"ref31","article-title":"Scenethesis: A language and vision agentic framework for 3d scene generation","volume-title":"arXiv preprint","author":"Ling","year":"2025"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.01865.x"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681129"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130897"},{"key":"ref35","article-title":"Worldcraft: Photo-realistic 3d world creation and customization via llm agents","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"arXiv preprint","author":"Meng","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00069"},{"key":"ref38","volume-title":"Meshy ai - the no. 1 ai 3d model generator for creators"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_21"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383292"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3658222"},{"key":"ref42","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell","year":"2023"},{"key":"ref43","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":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01215"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01215"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref47","volume-title":"CLIP+MLP Aesthetic Score Predictor","author":"Schuhmann","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00119"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02744"},{"key":"ref50","article-title":"Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Blender Foundation","volume-title":"Blender","author":"Ton Roosendaal","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00486"},{"key":"ref53","article-title":"Q-align: Teaching lmms for visual scoring via discrete text-defined levels","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3658188"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02000"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00923"},{"key":"ref57","article-title":"Sketch2scene: Automatic generation of interactive 3d game scenes from user\u2019s casual sketches","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00994"},{"key":"ref59","article-title":"Depth anything v2","author":"Yang","year":"2024","journal-title":"arXiv"},{"key":"ref60","article-title":"Layerpano3d: Layered 3d panorama for hyper-immersive scene generation","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Layerpano3d: Layered 3d panorama for hyper-immersive scene generation","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102091"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3730841"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00555"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00607"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00607"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3361502"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-017-1465-7"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3658150"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref75","article-title":"SceneWiz3D: Towards text-guided 3D scene composition","author":"Zhang","year":"2023","journal-title":"arXiv"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3687905"},{"key":"ref77","article-title":"Holodreamer: Holistic 3d panoramic world generation from text descriptions","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref78","article-title":"Scenex: Procedural controllable large-scale scene generation via large-language models","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_19"},{"key":"ref80","article-title":"Gala3d: Towards text-to-3d complex scene generation via layout-guided generative gaussian splatting","volume-title":"arXiv preprint","author":"Zhou","year":"2024"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00983"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11526953\/11459369.pdf?arnumber=11459369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:52:54Z","timestamp":1779306774000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11459369\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":82,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2026.3679097","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]]}}}