{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T06:48:30Z","timestamp":1782283710007,"version":"3.54.5"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Zhongguancun Laboratory"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272018"],"award-info":[{"award-number":["62272018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206184"],"award-info":[{"award-number":["62206184"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tvcg.2026.3658429","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T20:29:14Z","timestamp":1769545754000},"page":"5034-5048","source":"Crossref","is-referenced-by-count":0,"title":["MaskScene: Hierarchical Conditional Masked Models for Real-Time 3D Indoor Scene Synthesis"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8398-0152","authenticated-orcid":false,"given":"Xinyu","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8478-1548","authenticated-orcid":false,"given":"Yusen","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0046-5794","authenticated-orcid":false,"given":"Qichuan","family":"Geng","sequence":"additional","affiliation":[{"name":"Information Engineering College, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5825-7517","authenticated-orcid":false,"given":"Zhong","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5101-1071","authenticated-orcid":false,"given":"Wenfeng","family":"Song","sequence":"additional","affiliation":[{"name":"Computer School, Beijing Information Science and Technology University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2417575"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00618"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00634"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_42"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3268115"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3361502"},{"key":"ref7","article-title":"FurniScene: A large-scale 3D room dataset with intricate furnishing scenes","author":"Zhang","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00021"},{"key":"ref9","first-page":"12013","article-title":"ATISS: Autoregressive transformers for indoor scene synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paschalidou"},{"key":"ref10","article-title":"Clip-layout: Style-consistent indoor scene synthesis with semantic furniture embedding","author":"Liu","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00558"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00381"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00748"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01604"},{"key":"ref16","first-page":"2024","article-title":"InstructScene: Instruction-driven 3D indoor scene synthesis with semantic graph prior","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref17","first-page":"30026","article-title":"CommonScenes: Generating commonsense 3D indoor scenes with scene graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhai"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref19","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_15"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_10"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref23","first-page":"40","article-title":"Learning representations and generative models for 3D point clouds","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achlioptas"},{"key":"ref24","article-title":"Point cloud GAN","author":"Li","year":"2018"},{"key":"ref25","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref27","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref28","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref29","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00500"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01011"},{"key":"ref33","first-page":"73969","article-title":"Michelangelo: Conditional 3D shape generation based on shape-image-text aligned latent representation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref34","first-page":"10021","article-title":"LION: Latent point diffusion models for 3D shape generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vahdat"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"ref37","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3209357"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456309"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3368621"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3521333"},{"key":"ref42","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_11"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_17"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00069"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755133"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2608"},{"key":"ref48","article-title":"The scene language: Representing scenes with programs, words, and embeddings","author":"Zhang","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.32969"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92387-6_17"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3303766"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16449-1_45"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681129"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237577"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1944"},{"key":"ref58","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00067"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"ref62","first-page":"1920","article-title":"Categorical reparametrization with gumble-softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang"},{"key":"ref63","article-title":"GPT-4: Openai\u2019s large multimodal model","year":"2023"},{"key":"ref64","first-page":"742","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"19","author":"Li"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"ref66","article-title":"Wenjuanxing","year":"2025"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11575570\/11365586.pdf?arnumber=11365586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T06:02:40Z","timestamp":1782280960000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11365586\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":66,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2026.3658429","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":[[2026,7]]}}}