{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:54Z","timestamp":1777865334320,"version":"3.51.4"},"reference-count":95,"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\/501100009023","name":"PRESTO","doi-asserted-by":"publisher","award":["JPMJPR22P8"],"award-info":[{"award-number":["JPMJPR22P8"]}],"id":[{"id":"10.13039\/501100009023","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"JSPS","doi-asserted-by":"publisher","award":["25K03177"],"award-info":[{"award-number":["25K03177"]}],"id":[{"id":"10.13039\/501100001691","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\/iccv51701.2025.00908","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9737-9748","source":"Crossref","is-referenced-by-count":0,"title":["GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields"],"prefix":"10.1109","author":[{"given":"Shunsuke","family":"Yasuki","sequence":"first","affiliation":[{"name":"Rikkyo University"}]},{"given":"Taiki","family":"Miyanishi","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Nakamasa","family":"Inoue","sequence":"additional","affiliation":[{"name":"Institute of Science Tokyo"}]},{"given":"Shuhei","family":"Kurita","sequence":"additional","affiliation":[{"name":"National Institute of Informatics"}]},{"given":"Koya","family":"Sakamoto","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Daichi","family":"Azuma","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Masato","family":"Taki","sequence":"additional","affiliation":[{"name":"Rikkyo University"}]},{"given":"Yutaka","family":"Matsuo","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref2","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_12"},{"key":"ref4","volume-title":"Opencity3d: 3d urban scene understanding with vision-language models. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","author":"Bieri","year":"2025"},{"key":"ref5","first-page":"706717","article-title":"A persistent spatial semantic representation for high-level natural language instruction execution","volume-title":"Proc. Conference on Robot Learning (CoRL)","author":"Blukis","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00143"},{"key":"ref7","first-page":"202","article-title":"Scanrefer: 3d object localization in rgb-d scans using natural language","volume-title":"Proc. European Conference on Computer Vision (ECCV)","author":"Zhenyu Chen","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3354624"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_23"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref12","article-title":"Layoutgpt: Compositional visual planning and generation with large language models","author":"Feng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2558"},{"key":"ref14","first-page":"59124","article-title":"Ue4-nerf :neural radiance field for real-time rendering of large-scale scene","volume-title":"Proc. Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Gu","year":"2023"},{"key":"ref15","article-title":"Streetsurf: Extending multi-view implicit surface reconstruction to street views","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01225"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCP61108.2024.10644903"},{"key":"ref19","article-title":"3d-llm: Injecting the 3d world into large language models","author":"Hong","year":"2023","journal-title":"arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.03.028"},{"key":"ref21","article-title":"Teochat: A large vision-language assistant for temporal earth observation data","author":"Andrew Irvin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Graspsplats: Efficient manipulation with 3d feature splatting","author":"Ji","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32410"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3658160"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref27","volume-title":"Diffusionsat: A generative foundation model for satellite imagery. In Proc.","author":"Khanna","year":"2024"},{"key":"ref28","first-page":"4015","volume-title":"Segment anything. In Proc.","author":"Kirillov","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32457"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1694"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00657"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02629"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_6"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00297"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00494"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_6"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_15"},{"key":"ref41","author":"Liu","year":"2024","journal-title":"Citygaussianv2: Efficient and geometrically accurate reconstruction for large-scale scenes"},{"key":"ref42","article-title":"Citygaussianv2 : Efficient and geometrically accurate reconstruction for large-scale scenes","author":"Liu","year":"2025","journal-title":"ICLR"},{"key":"ref43","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","volume-title":"Proc. Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Lu","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref45","article-title":"Skysensegpt: A fine-grained instruction tuning dataset and model for remote sensing vision-language understanding","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3385500"},{"key":"ref47","first-page":"3","year":"2024","journal-title":"Meta. Llama 3.2 connect 2024: Vision on the edge and mobile devices"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref49","article-title":"Cityrefer: Geography-aware 3d visual grounding dataset on city-scale point cloud data","volume-title":"Proc. Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Miyanishi","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_26"},{"key":"ref51","article-title":"OpenAI","volume-title":"Hello gpt-4o","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32683"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref55","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01393"},{"key":"ref57","author":"Schick","year":"2023","journal-title":"Toolformer: Language models can teach themselves to use tools"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.074"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00510"},{"key":"ref60","article-title":"Real-time view synthesis for large scenes with millions of square meters","volume-title":"2024. 2, 4, 13","author":"Shuai"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_22"},{"key":"ref62","author":"Stelzner","year":"2021","journal-title":"Decomposing 3d scenes into objects via unsupervised volume segmentation"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.65"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548316"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3453414"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681257"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01258"},{"key":"ref71","article-title":"Geoclip: Clip-inspired alignment between locations and images for effective worldwide geo-localization","volume-title":"Proc. Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Vivanco","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28393"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01417"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_7"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00923"},{"key":"ref76","article-title":"GaussianCity: Generative gaussian splatting for unbounded 3D city generation","author":"Xie","year":"2024","journal-title":"arXiv 2406.06526"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00802"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_5"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00140"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-23161-2_300365"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_19"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref85","author":"Zhang","journal-title":"Garfield++: Reinforced gaussian radiance fields for large-scale 3d scene reconstruction"},{"key":"ref86","article-title":"3DitScene: Editing any scene via language-guided disentangled gaussian splatting","author":"Zhang","year":"2024","journal-title":"arXiv"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3409624"},{"key":"ref88","article-title":"Earthmarker: A visual prompt learning framework for region-level and point-level remote sensing imagery comprehension","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111001"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01993"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3449154"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3079918"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02044"},{"key":"ref94","article-title":"Towards visionlanguage geo-foundation models: A survey","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref95","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\/11445360.pdf?arnumber=11445360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:42Z","timestamp":1777529862000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445360\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":95,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00908","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}