{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:29:27Z","timestamp":1780392567239,"version":"3.54.1"},"reference-count":64,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00626","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6645-6655","source":"Crossref","is-referenced-by-count":1,"title":["Placeit3d: Language-Guided Object Placement in Real 3D Scenes"],"prefix":"10.1109","author":[{"given":"Ahmed","family":"Abdelreheem","sequence":"first","affiliation":[{"name":"KAUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Filippo","family":"Aleotti","sequence":"additional","affiliation":[{"name":"Niantic Spatial"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jamie","family":"Watson","sequence":"additional","affiliation":[{"name":"Niantic Spatial"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zawar","family":"Qureshi","sequence":"additional","affiliation":[{"name":"Niantic Spatial"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdelrahman","family":"Eldesokey","sequence":"additional","affiliation":[{"name":"KAUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Wonka","sequence":"additional","affiliation":[{"name":"KAUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabriel","family":"Brostow","sequence":"additional","affiliation":[{"name":"Niantic Spatial"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Vicente","sequence":"additional","affiliation":[{"name":"Niantic Spatial"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillermo","family":"Garcia-Hernando","sequence":"additional","affiliation":[{"name":"Niantic Spatial"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00349"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref3","author":"Arnaud","year":"2025","journal-title":"Locate 3d: Real-world object localization via self-supervised learning in 3d"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref5","article-title":"Spatialbot: Precise spatial understanding with vision language models","author":"Cai","year":"2024","journal-title":"arXiv 2406.13642"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1217"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1006"},{"key":"ref8","article-title":"Sceneseer: 3d scene design with natural language","author":"Chang","year":"2017","journal-title":"arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383316"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref16","author":"Dawson-Haggerty","year":"2019","journal-title":"trimesh"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref18","article-title":"Layoutgpt: Compositional visual planning and generation with large language models","volume-title":"NeurIPS","author":"Feng","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366154"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3274922"},{"key":"ref22","article-title":"3D-LLM: Injecting the 3D world into large language models","volume-title":"NeurIPS","author":"Hong","year":"2023"},{"key":"ref23","article-title":"Chatscene: Bridging 3d scene and large language models with object identifiers","volume-title":"NeurIPS","author":"Huang","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01257"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00112"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00479"},{"key":"ref29","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv 2408.03326"},{"key":"ref30","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv 2407.07895"},{"key":"ref31","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li","year":"2023"},{"key":"ref32","article-title":"Visual instruction tuning","volume-title":"NeurIPS","author":"Liu","year":"2024"},{"key":"ref33","article-title":"Opa: object placement assessment dataset","author":"Liu","year":"2021","journal-title":"arXiv 2107.01889"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275035"},{"key":"ref35","author":"Ma","year":"2024","journal-title":"When llms step into the 3d world: A survey and meta-analysis of 3d tasks via multimodal large language models"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964982"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20097"},{"key":"ref38","article-title":"Atiss: Autoregressive transformers for indoor scene synthesis","volume-title":"NeurIPS","author":"Paschalidou","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01540"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/AIxVR59861.2024.00028"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref42","volume-title":"How Children Develop","author":"Siegler","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02744"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25335"},{"key":"ref46","article-title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","volume-title":"NeurIPS","author":"Takmaz","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"ref48","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani","year":"2017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322941"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01868"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01825"},{"key":"ref52","article-title":"3d-grand: A million-scale dataset for 3d-llms with better grounding and less hallucination","author":"Yang","year":"2024","journal-title":"arXiv 2406.05132"},{"key":"ref53","article-title":"Scenecraft: Layout-guided 3d scene generation","volume-title":"NeurIPS","author":"Yang","year":"2024"},{"key":"ref54","article-title":"Sampart3d: Segment any part in 3d objects","author":"Yang","year":"2024","journal-title":"arXiv 2411.07184"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964981"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref58","article-title":"Robopoint: A vision-language model for spatial affordance prediction for robotics","volume-title":"CoRL","author":"Yuan","year":"2024"},{"key":"ref59","article-title":"Vla-3d: A dataset for 3d semantic scene understanding and navigation","volume-title":"RSS Workshop","author":"Zhang","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_31"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00748"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_9"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00183"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"}],"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\/11445279.pdf?arnumber=11445279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T19:52:50Z","timestamp":1780084370000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00626","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}