{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T20:28:13Z","timestamp":1780518493290,"version":"3.54.1"},"reference-count":95,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00131","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1356-1367","source":"Crossref","is-referenced-by-count":1,"title":["HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation"],"prefix":"10.1109","author":[{"given":"Hou In Derek","family":"Pun","sequence":"first","affiliation":[{"name":"Simon Fraser University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hou In Ivan","family":"Tam","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Austin T.","family":"Wang","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoliang","family":"Huo","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angel X.","family":"Chang","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manolis","family":"Savva","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00626"},{"key":"ref2","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Open-Universe indoor scene generation using LLM program synthesis and uncurated object databases","volume-title":"arXiv preprint","author":"Aguina-Kang","year":"2024"},{"key":"ref4","article-title":"Qwen3-VL Technical Report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92387-6_17"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1217"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383316"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0433"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00839"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01604"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755132"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02716"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366154"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818057"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01534-z"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130805"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237577"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0746"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00275"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.266"},{"key":"ref26","article-title":"Automatic generation of constrained furniture layouts","author":"Henderson","year":"2017","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61042.2026.00129"},{"key":"ref28","first-page":"19252","article-title":"SceneCraft: An LLM agent for synthesizing 3D scenes as Blender code","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Hu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01257"},{"key":"ref30","article-title":"Video perception models for 3D scene synthesis","author":"Huang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref31","author":"Ilharco","year":"2021","journal-title":"OpenCLIP"},{"key":"ref32","article-title":"Learning object arrangements in 3D scenes using human context","author":"Jiang","year":"2012","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630857"},{"key":"ref34","article-title":"SceneGen: Generative contextual scene augmentation using scene graph priors","author":"Keshavarzi","year":"2020","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"ref36","volume-title":"Automatic furniture population of large architectural models","author":"Anne H\u00f8ier Kj\u00f8laas","year":"2000"},{"key":"ref37","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3303766"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15236"},{"key":"ref40","article-title":"InstructScene: Instructiondriven 3D indoor scene synthesis with semantic graph prior","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Lin","year":"2024"},{"key":"ref41","first-page":"366","article-title":"Evaluating text-to-visual generation with image-to-text generation","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Lin","year":"2024"},{"key":"ref42","article-title":"Scenethesis: A language and vision agentic framework for 3D scene generation","volume-title":"arXiv preprint","author":"Ling","year":"2025"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.70036"},{"key":"ref44","author":"Liu","year":"2025","journal-title":"SceneFunctioner: Tailoring large language model for function-oriented interactive scene synthesis"},{"key":"ref45","article-title":"Agentic 3D scene generation with spatially contextualized VLMs","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"WorldCraft: Photo-realistic 3D world creation and customization via LLM agents","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275035"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2013.245"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964982"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.cagd.2024.102319"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591561"},{"key":"ref52","first-page":"12013","article-title":"ATISS: Autoregressive transformers for indoor scene synthesis","author":"Paschalidou","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref53","first-page":"1690","article-title":"Steerable scene generation with post training and inference-time search","volume-title":"Proceedings of The 8th Conference on Robot Learning","author":"Ezra Pfaff","year":"2025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_10"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00618"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02058"},{"key":"ref57","article-title":"Direct numerical layout generation for 3D indoor scene synthesis via spatial reasoning","volume-title":"arXiv preprint","author":"Ran","year":"2025"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00104"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00634"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1644"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925867"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_12"},{"key":"ref63","article-title":"CHOrD: Generation of collision-free, house-scale, and organized digital twins for 3D indoor scenes with controllable floor plans and optimal layouts","author":"Su","year":"2025","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02744"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_15"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32765"},{"key":"ref67","article-title":"SceneMotifCoder: Example-driven Visual Program Learning for Generating 3D Object Arrangements","volume-title":"Proceedings of the International Conference on 3D Vision (3DV)","author":"In","year":"2025"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61042.2026.00710"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3626731"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201362"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322941"},{"key":"ref73","article-title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00021"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2158"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3602216"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00832"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_17"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.873"},{"key":"ref80","first-page":"25","article-title":"Constraintbased automatic placement for scene composition","author":"Xu","year":"2002","journal-title":"Graphics Interface"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01539"},{"key":"ref82","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33017"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3443657"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964981"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2417575"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1307"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_10"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2949295"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475194"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613456"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3381866"},{"key":"ref95","article-title":"RoomCraft: Controllable and complete 3D indoor scene generation","author":"Zhou","year":"2025","journal-title":"arXiv preprint"}],"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\/11533297.pdf?arnumber=11533297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:02:42Z","timestamp":1779944562000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533297\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":95,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00131","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}