{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T16:58:03Z","timestamp":1786553883954,"version":"build-2736575974"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["62125102"],"award-info":[{"award-number":["62125102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471014"],"award-info":[{"award-number":["62471014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2022ZD0160401"],"award-info":[{"award-number":["2022ZD0160401"]}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JL23005"],"award-info":[{"award-number":["JL23005"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["QY24125"],"award-info":[{"award-number":["QY24125"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3507010","type":"journal-article","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T18:47:56Z","timestamp":1732646876000},"page":"1764-1781","source":"Crossref","is-referenced-by-count":46,"title":["MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3504-9441","authenticated-orcid":false,"given":"Zhiping","family":"Yu","sequence":"first","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3034-6646","authenticated-orcid":false,"given":"Chenyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7158-6772","authenticated-orcid":false,"given":"Liqin","family":"Liu","sequence":"additional","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4772-3172","authenticated-orcid":false,"given":"Zhenwei","family":"Shi","sequence":"additional","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1774-552X","authenticated-orcid":false,"given":"Zhengxia","family":"Zou","sequence":"additional","affiliation":[{"name":"Department of Guidance, Navigation and Control, School of Astronautics, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3305243"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3382753"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3345866"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3043372"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339964"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3212915"},{"key":"ref8","first-page":"3609","article-title":"EGSDE: Unpaired image-to-image translation via energy-guided stochastic differential equations","volume-title":"Proc Adv. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3163183"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3308102"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3147570"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109347"},{"key":"ref14","article-title":"Synthetic data from diffusion models improves imagenet classification","author":"Azizi","year":"2023"},{"key":"ref15","first-page":"54683","article-title":"DatasetDM: Synthesizing data with perception annotations using diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref16","article-title":"Is sora a world simulator? A comprehensive survey on general world models and beyond","author":"Zhu","year":"2024"},{"key":"ref17","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023"},{"key":"ref18","article-title":"Genie: Generative interactive environments","author":"Bruce","year":"2024"},{"key":"ref19","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref23","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013"},{"key":"ref24","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Van Den"},{"key":"ref25","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende"},{"key":"ref26","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref27","first-page":"8162","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref29","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref30","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"issue":"47","key":"ref31","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref34","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref35","article-title":"DiffusionSat: A generative foundation model for satellite imagery","author":"Khanna","year":"2023"},{"key":"ref36","article-title":"CRS-Diff: Controllable generative remote sensing foundation model","author":"Tang","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3268331"},{"key":"ref38","article-title":"Generate your own Scotland: Satellite image generation conditioned on maps","author":"Espinosa","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317383"},{"key":"ref40","article-title":"RSDiff: Remote sensing image generation from text using diffusion model","author":"Sebaq","year":"2023"},{"key":"ref41","article-title":"SatDM: Synthesizing realistic satellite image with semantic layout conditioning using diffusion models","author":"Baghirli","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3335975"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3450874"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386381"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194732"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3362475"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01538"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00378"},{"key":"ref51","first-page":"197","article-title":"Satmae: Pre-training transformers for temporal and multi-spectral satellite imagery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cong"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02627"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01541"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref55","article-title":"RS5M: A large scale vision-language dataset for remote sensing vision-language foundation model","author":"Zhang","year":"2023"},{"key":"ref56","article-title":"Remote sensing vision-language foundation models without annotations via ground remote alignment","author":"Mall","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3308969"},{"key":"ref58","article-title":"Large language models for captioning and retrieving remote sensing images","author":"Silva","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2022.3150957"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3404604"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3218921"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3321752"},{"key":"ref63","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02629"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.01.020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3409624"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28393"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.029"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.00219"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01118"},{"key":"ref72","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref74","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref76","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10768939.pdf?arnumber=10768939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T06:04:31Z","timestamp":1738821871000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10768939\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":76,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3507010","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}