{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:25Z","timestamp":1777865365854,"version":"3.51.4"},"reference-count":77,"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\/iccv51701.2025.02641","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"28440-28450","source":"Crossref","is-referenced-by-count":0,"title":["HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Models"],"prefix":"10.1109","author":[{"given":"Yiwen","family":"Chen","sequence":"first","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hieu T.","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vikram","family":"Voleti","sequence":"additional","affiliation":[{"name":"Stability AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Varun","family":"Jampani","sequence":"additional","affiliation":[{"name":"Stability AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaizu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00659"},{"key":"ref2","article-title":"ARKitscenes - a diverse real-world dataset for 3d indoor scene understanding using mobile RGB-d data","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)","author":"Baruch","year":"2021"},{"key":"ref3","article-title":"Gaudi: A neural architect for immersive 3d scene generation","author":"Angel Bautista","year":"2022","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref5","author":"Blattmann","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2025.3611489"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"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","article-title":"Objaverse-xl: A universe of 10 ~{m}+3 ~{d} objects","author":"Deitke","year":"2024","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00047"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00069"},{"key":"ref14","article-title":"Layoutgpt: Compositional visual planning and generation with large language models","author":"Feng","year":"2024","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02114"},{"key":"ref18","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00926"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00934"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00342"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00433"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618149"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00956"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00908"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"ref32","article-title":"One-2\u20133-45: Any single image to 3 d mesh in 45 seconds without per-shape optimization","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref34","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2024","journal-title":"ICLR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref37","article-title":"Gta: A geometry-aware attention mechanism for multi-view transformers","author":"Miyato","year":"2024","journal-title":"ICLR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00083"},{"key":"ref39","article-title":"Text2immersion: Generative immersive scene with 3d gaussians","author":"Ouyang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Atiss: Autoregressive transformers for indoor scene synthesis","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Paschalidou","year":"2021"},{"key":"ref41","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2023","journal-title":"ICLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02058"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00403"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01384"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref47","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref48","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00593"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00529"},{"key":"ref51","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2024","journal-title":"ICLR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00086"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611800"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00814"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"ref57","article-title":"Mvdiffusion: Enabling holistic multiview image generation with correspondence-aware diffusion","author":"Tang","year":"2023","journal-title":"NeurIPS"},{"key":"ref58","article-title":"Triposr: Fast 3d object reconstruction from a single image","author":"Tochilkin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01059"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_4"},{"key":"ref62","article-title":"Consistent123: Improve consistency for one image to 3d object synthesis","volume-title":"arXiv preprint","author":"Weng","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3658188"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00676"},{"key":"ref66","article-title":"Scenecraft: Layout-guided 3d scene generation","author":"Yang","year":"2024","journal-title":"NeurIPS"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00027"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.29"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_10"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3361502"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00928"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01153"}],"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\/11445962.pdf?arnumber=11445962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:31Z","timestamp":1777530031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02641","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}