{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T03:25:26Z","timestamp":1783740326965,"version":"3.55.0"},"reference-count":87,"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\/501100000038","name":"NSERC","doi-asserted-by":"publisher","award":["CFI\/BCKDF JELF"],"award-info":[{"award-number":["CFI\/BCKDF JELF"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2016532"],"award-info":[{"award-number":["2016532"]}],"id":[{"id":"10.13039\/100000001","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\/iccv51701.2025.00832","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8896-8907","source":"Crossref","is-referenced-by-count":4,"title":["Diorama: Unleashing Zero-Shot Single-View 3D Indoor Scene Modeling"],"prefix":"10.1109","author":[{"given":"Qirui","family":"Wu","sequence":"first","affiliation":[{"name":"Simon Fraser University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denys","family":"Iliash","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Ritchie","sequence":"additional","affiliation":[{"name":"Brown University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manolis","family":"Savva","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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01392"},{"key":"ref2","article-title":"SceneComplete: Open-world 3D scene completion in complex real world environments for robot manipulation","author":"Agarwal","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"Open-universe indoor scene generation using LLM program synthesis and uncurated object databases","author":"Rio","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00272"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","article-title":"ShapeNet: An information-rich 3D model repository","author":"Angel","year":"2015","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00142"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.124"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref11","article-title":"ACDC: Automated creation of digital cousins for robust policy learning","author":"Dai","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01377"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00677"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02653"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02059"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366154"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref19","article-title":"Scene-LLM: Extending language model for 3D visual understanding and reasoning","author":"Fu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3658236"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02012"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_30"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00399"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref27","article-title":"Aladdin: Zero-shot hallucination of stylized 3D assets from abstract scene descriptions","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_12"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_10"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811799"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.260"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_16"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01236"},{"key":"ref39","article-title":"SPARC: Sparse render-and-compare for CAD model alignment in a single RGB image","volume-title":"Proc. British Machine Vision Conference","author":"Langer","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_4"},{"key":"ref41","article-title":"Duoduo CLIP: Efficient 3D understanding with multi-view images","author":"Lee","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Evaluating real-world robot manipulation policies in simulation","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"InstructScene: Instructiondriven 3D indoor scene synthesis with semantic graph prior","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_25"},{"key":"ref45","article-title":"LASA: Instance reconstruction from real scans using a large-scale aligned shape annotation dataset","author":"Liu","year":"2023","journal-title":"arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02082"},{"key":"ref47","article-title":"OpenShape: Scaling up 3D shape representation towards open-world understanding","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00121"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3146082"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01847"},{"key":"ref51","article-title":"Scaling open-vocabulary object detection","author":"Houlsby","year":"2023","journal-title":"NeurIPS"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00945"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00013"},{"key":"ref55","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref56","first-page":"12013","article-title":"ATISS: Autoregressive transformers for indoor scene synthesis","volume":"34","author":"Paschalidou","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref59","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":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00634"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1644"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_12"},{"key":"ref64","first-page":"251","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","volume":"34","author":"Szot","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref65","article-title":"OpenMask3D: Open-vocabulary 3D instance segmentation","author":"Takmaz","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref66","article-title":"SceneMotifCoder: Example-driven visual program learning for generating 3D object arrangements","author":"In","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/34.88573"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201362"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322941"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02019"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00021"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01825"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73036-8_26"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00060"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref77","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4V","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref78","article-title":"ImOV3D: Learning open-vocabulary point clouds 3D object detection from only 2D images","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"ref80","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023","journal-title":"arXiv"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_4"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01240"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00219"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"ref85","article-title":"Zero-shot scene reconstruction from single images with deep prior assembly","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw67362.2025.00064"}],"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\/11445157.pdf?arnumber=11445157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:35Z","timestamp":1777529915000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445157\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00832","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}