{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:17Z","timestamp":1777865357114,"version":"3.51.4"},"reference-count":76,"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\/501100004270","name":"KTH Royal Institute of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004270","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004040","name":"KU Leuven","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004040","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\/iccv51701.2025.00789","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8429-8440","source":"Crossref","is-referenced-by-count":0,"title":["Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?"],"prefix":"10.1109","author":[{"given":"Yuru","family":"Jia","sequence":"first","affiliation":[{"name":"KU Leuven"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Valerio","family":"Marsocci","sequence":"additional","affiliation":[{"name":"European Space Agency"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyang","family":"Gong","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Yang","sequence":"additional","affiliation":[{"name":"SJTU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maarten","family":"Vergauwen","sequence":"additional","affiliation":[{"name":"KU Leuven"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Nascetti","sequence":"additional","affiliation":[{"name":"KTH"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Segdiff: Image segmentation with diffusion probabilistic models","author":"Amit","year":"2021","journal-title":"arXiv preprint arXiv:2112.00390"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_24"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01002"},{"key":"ref4","article-title":"Ddpm-cd: Denoising diffusion probabilistic models as feature extractors for change detection","author":"Gedara","year":"2022","journal-title":"arXiv preprint arXiv:2206.11892"},{"key":"ref5","article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"International Conference on Learning Representations","author":"Baranchuk","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01538"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref9","article-title":"Satmae: Pre-training transformers for temporal and multi-spectral satellite imagery","author":"Cong","year":"2022","journal-title":"arXiv preprint arXiv:2207.08051"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0433"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02614"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00291"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3658965"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0241"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3649001"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02613"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02631"},{"key":"ref19","article-title":"Tdiffde: A truncated diffusion model for remote sensing hyperspectral image denoising","author":"He","year":"2023","journal-title":"arXiv preprint arXiv:2311.13622"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3362475"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3384545"},{"key":"ref24","article-title":"Slime: Segment like me","author":"Khani","year":"2023","journal-title":"arXiv preprint arXiv:2309.03179"},{"key":"ref25","article-title":"Diffusionsat: A generative foundation model for satellite imagery","volume-title":"The Twelfth International Conference on Learning Representations","author":"Khanna","year":"2024"},{"key":"ref26","first-page":"8439","article-title":"Multiclass segmentation from aerial views using recursive noise diffusion","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Kolbeinsson","year":"2024"},{"key":"ref27","article-title":"Geobench: Toward foundation models for earth monitoring","author":"Lacoste","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00053"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28710"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2025.3560455"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3464685"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2057"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3557915.3561043"},{"key":"ref35","article-title":"Remote sensing vision-language foundation models without annotations via ground remote alignment","volume-title":"The Twelfth International Conference on Learning Representations","author":"Mall","year":"2024"},{"key":"ref36","author":"Marsocci","year":"2024","journal-title":"Cross-sensor selfsupervised training and alignment for remote sensing"},{"key":"ref37","author":"Marsocci","year":"2024","journal-title":"Pangaea: A global and inclusive benchmark for geospatial foundation models"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01541"},{"key":"ref39","article-title":"Gfm: Building geospatial foundation models via continual pretraining","author":"Mendieta","year":"2023","journal-title":"arXiv preprint arXiv:2302.04476"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_15"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00290"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29391"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00378"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref47","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv preprint arXiv:1701.06538"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-58125-4"},{"key":"ref49","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref50","article-title":"Ssl4eo-1: Datasets and foundation models for landsat imagery","volume":"36","author":"Stewart","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3453414"},{"key":"ref52","article-title":"Cross-scale mae: A tale of multiscale exploitation in remote sensing","author":"Tang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00341"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3371481"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02615"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2023.113888"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2024.3425961"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.12.001"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3408154"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3378720"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2022.3198244"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2023.3281651"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3381752"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2383"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01448"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref68","article-title":"Neural plasticity-inspired foundation model for observing the Earth crossing modalities","author":"Xiong","year":"2024","journal-title":"arXiv preprint arXiv:2403.15356"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref70","author":"Yu","year":"2024","journal-title":"Representation alignment for generation: Training diffusion transformers is easier than you think"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3507010"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_8"},{"key":"ref73","article-title":"Diffucd: Unsupervised hyperspectral image change detection with semantic correlation diffusion model","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2305.12410"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3475824"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3407206"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3365806"}],"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\/11446242.pdf?arnumber=11446242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:06Z","timestamp":1777530006000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00789","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}