{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T02:12:24Z","timestamp":1783995144945,"version":"3.55.0"},"reference-count":74,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42401567"],"award-info":[{"award-number":["42401567"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012239","name":"Ministry of Natural Resources","doi-asserted-by":"publisher","award":["2024PF-1"],"award-info":[{"award-number":["2024PF-1"]}],"id":[{"id":"10.13039\/501100012239","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\/iccv51701.2025.02597","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27978-27988","source":"Crossref","is-referenced-by-count":4,"title":["Sat2City: 3D City Generation from a Single Satellite Image with Cascaded Latent Diffusion"],"prefix":"10.1109","author":[{"given":"Tongyan","family":"Hua","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lutao","family":"Jiang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying-Cong","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wufan","family":"Zhao","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Componerf: Text-guided multi-object compositional nerf with editable 3d scene layout","author":"Haotian","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01999"},{"key":"ref3","volume-title":"Shapenet: An information-rich 3d model repository","author":"Angel X","year":"2015"},{"key":"ref4","volume-title":"Meshxl: Neural coordinate field for generative 3d foundation models","author":"Sijin","year":"2024"},{"key":"ref5","volume-title":"Meshanything: Artist-created mesh generation with autoregressive transformers","author":"Yiwen","year":"2024"},{"key":"ref6","volume-title":"Meshanything v2: Artist-created mesh generation with adjacent mesh tokenization","author":"Yiwen","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3321857"},{"key":"ref8","volume-title":"Progressive3d: Progres sively local editing for text-to-3d content creation with com plex semantic prompts","author":"Xinhua","year":"2023"},{"key":"ref9","first-page":"2920","article-title":"Set-the-scene: Global-local training for generating controllable nerf scenes","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Dana","year":"2023"},{"key":"ref10","first-page":"1","article-title":"Streetscapes: Large-scale consistent street view generation using autoregressive video diffusion","volume-title":"ACM SIGGRAPH 2024 Conference Papers","author":"Boyang","year":"2024"},{"key":"ref11","volume-title":"Citycraft: A real crafter for 3d city generation","author":"Jie","year":"2024"},{"key":"ref12","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Prafulla","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","volume-title":"Syncity: Training-free generation of 3d worlds","author":"Paul","year":"2025"},{"key":"ref14","volume-title":"Disentangled 3d scene generation with layout learning","author":"Dave","year":"2024"},{"key":"ref15","volume-title":"Blender- a 3d modeling and animation software, 2025","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1734"},{"key":"ref17","first-page":"14072","article-title":"Gancraft: Unsupervised 3d neural rendering of minecraft worlds","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Zekun","year":"2021"},{"key":"ref18","volume-title":"Lrm: Large reconstruction model for single image to 3d","author":"Yicong","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00425"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555394"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680740"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01670"},{"issue":"(4)","key":"ref24","first-page":"139","article-title":"3d gaussian splatting for real-time radiance field rendering","volume":"42","author":"Bernhard","year":"2023","journal-title":"ACM Trans. Graph."},{"key":"ref25","volume-title":"Nuiscene: Exploring efficient generation of unbounded outdoor scenes","author":"Han-Hung","year":"2025"},{"key":"ref26","first-page":"71","article-title":"Grounding image matching in 3d with mast3r","volume-title":"European Conference on Computer Vision","author":"Vincent","year":"2024"},{"key":"ref27","volume-title":"Syntheocc: Synthesize geometric-controlled street view images through 3d semantic mpis","author":"Leheng","year":"2024"},{"key":"ref28","volume-title":"Crossviewdiff: A cross-view diffusion model for satellite to-street view synthesis","author":"Weijia","year":"2024"},{"key":"ref29","first-page":"12436","article-title":"Sat2vid: Street-view panoramic video synthesis from a single satellite image","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Zuoyue","year":"2021"},{"key":"ref30","first-page":"7141","article-title":"Sat2scene: 3d urban scene genera tion from satellite images with diffusion","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zuoyue","year":"2024"},{"key":"ref31","first-page":"22808","article-title":"Infinicity: Infinite-scale city synthesis","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Chieh Hubert","year":"2023"},{"key":"ref32","volume-title":"World craft: Photo-realistic 3d world creation and customization via llm agents","author":"Xinhang","year":"2025"},{"key":"ref33","volume-title":"Urban architect: Steerable 3d urban scene generation with layout prior","author":"Fan","year":"2024"},{"key":"ref34","first-page":"859","article-title":"Geometry-aware satellite to-ground image synthesis for urban areas","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Xiaohu","year":"2020"},{"key":"ref35","volume-title":"Infinicube: Unbounded and controllable dynamic 3d driving scene generation with world guided video models","author":"Yifan","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref37","volume-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Ben","year":"2022"},{"key":"ref38","first-page":"3683","article-title":"Sat2density: Faithful density learning from satellite-ground image pairs","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Ming","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00403"},{"key":"ref40","volume-title":"Scube: Instant large-scale scene reconstruction using voxsplats","author":"Xuanchi","year":"2024"},{"key":"ref41","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Robin","year":"2022"},{"key":"ref42","volume-title":"Progressive distillation for fast sampling of diffusion models","author":"Tim","year":"2022"},{"key":"ref43","volume-title":"Urbanworld: An urban world model for 3d city generation","author":"Yu","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3140750"},{"key":"ref45","first-page":"20875","article-title":"3d neural field generation using triplane diffusion","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Ryan","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref47","volume-title":"Denoising diffusion implicit models","author":"Jiaming","year":"2020"},{"key":"ref48","first-page":"5459","article-title":"Direct voxel grid optimization: Super-fast convergence for radiance fields reconstruction","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Cheng","year":"2022"},{"key":"ref49","volume-title":"Edgerunner: Auto-regressive auto-encoder for artistic mesh generation","author":"Jiaxiang","year":"2024"},{"key":"ref50","volume-title":"Cloudcompare (version 2.12.4) [gpl software],2025","year":"2025"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01277"},{"key":"ref52","volume-title":"Llama-mesh: Unifying 3d mesh generation with language models","author":"Zhengyi","year":"2024"},{"key":"ref53","volume-title":"Pivotmesh: Generic 3d mesh generation via pivot vertices guidance","author":"Haohan","year":"2024"},{"issue":"(4)","key":"ref54","first-page":"1","article-title":"Blockfusion: Expandable 3d scene generation using latent tri-plane extrapolation","volume":"43","author":"Zhennan","year":"2024","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00923"},{"key":"ref56","volume-title":"Gaussiancity: Generative gaussian splatting for unbounded 3d city generation","author":"Haozhe","year":"2024"},{"key":"ref57","volume-title":"Gamus: A geometry-aware multi-modal semantic segmentation benchmark for remote sensing data","author":"Zhitong","year":"2023"},{"key":"ref58","volume-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models","author":"Jiale","year":"2024"},{"key":"ref59","volume-title":"Geospecific view generation geometry-context aware high-resolution ground view inference from satellite views","author":"Ningli","year":"2024"},{"key":"ref60","volume-title":"Sketch2scene: Automatic generation of interactive 3d game scenes from user\u2019s casual sketches","author":"Yongzhi","year":"2024"},{"key":"ref61","first-page":"4541","article-title":"Pointflow: 3d point cloud generation with continuous normalizing flows","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Guandao","year":"2019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS61716.2024.10672567"},{"key":"ref64","first-page":"9199","article-title":"Urbangiraffe: Representing urban scenes as compositional generative neural feature fields","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Yuanbo","year":"2023"},{"key":"ref65","volume-title":"Scene123: One prompt to 3d scene generation via video-assisted and consistency-enhanced mae","author":"Yiying","year":"2024"},{"key":"ref66","volume-title":"Dreamscape: 3d scene creation via gaussian splatting joint correlation modeling","author":"Xuening","year":"2024"},{"key":"ref67","volume-title":"Lagem: A large geometry model for 3d representation learning and diffusion","author":"Biao","year":"2024"},{"issue":"(4)","key":"ref68","first-page":"1","article-title":"3dshape2vecset: A 3d shape representation for neural fields and generative diffusion models","volume":"42","author":"Biao","year":"2023","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00969"},{"key":"ref71","volume-title":"Cityx: Controllable procedural con tent generation for unbounded 3d cities","author":"Shougao","year":"2024"},{"key":"ref72","volume-title":"Scenex: Procedural control lable large-scale scene generation via large-language models","author":"Mengqi","year":"2024"},{"key":"ref73","volume-title":"Gala3d: Towards text-to-3d complex scene generation via layout-guided generative gaussian splatting","author":"Xiaoyu","year":"2024"},{"key":"ref74","first-page":"12786","article-title":"Nice-slam: Neural implicit scalable encoding for slam","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Zihan","year":"2022"}],"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\/11446050.pdf?arnumber=11446050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:58:00Z","timestamp":1777611480000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02597","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}