CVPR 2025 Open Access Repository

Workshop on Foundation and Large Vision Models in Remote Sensing

Foundation Models for Remote Sensing: An Analysis of MLLMs for Object Localization.: Darryl Hannan,

John Cooper,

Dylan White,

Timothy Doster,

Henry Kvinge,

Yijing Watkins; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hannan_2025_CVPR, author = {Hannan, Darryl and Cooper, John and White, Dylan and Doster, Timothy and Kvinge, Henry and Watkins, Yijing}, title = {Foundation Models for Remote Sensing: An Analysis of MLLMs for Object Localization.}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {3028-3037} }
Bridging the Modality Gap: Training-free Adaptation of Vision-Language Models for Remote Sensing via Visual Prototypes: Clément Barbier,

Baptiste Abeloss,

Stéphane Herbin; [pdf]
[bibtex]
@InProceedings{Barbier_2025_CVPR, author = {Barbier, Cl\'ement and Abeloss, Baptiste and Herbin, St\'ephane}, title = {Bridging the Modality Gap: Training-free Adaptation of Vision-Language Models for Remote Sensing via Visual Prototypes}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {3057-3066} }
A Sensor Agnostic Domain Generalization Framework for Leveraging Geospatial Foundation Models: Enhancing Semantic Segmentation via Synergistic Pseudo-Labeling and Generative Learning: Anan Yaghmour,

Melba Crawford,

Saurabh Prasad; [pdf] [supp]
[bibtex]
@InProceedings{Yaghmour_2025_CVPR, author = {Yaghmour, Anan and Crawford, Melba and Prasad, Saurabh}, title = {A Sensor Agnostic Domain Generalization Framework for Leveraging Geospatial Foundation Models: Enhancing Semantic Segmentation via Synergistic Pseudo-Labeling and Generative Learning}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {3047-3056} }
Towards Efficient Benchmarking of Foundation Models in Remote Sensing: A Capabilities Encoding Approach: Pierre Adorni,

Minh-Tan Pham,

Stéphane May,

Sébastien Lefèvre; [pdf] [arXiv]
[bibtex]
@InProceedings{Adorni_2025_CVPR, author = {Adorni, Pierre and Pham, Minh-Tan and May, St\'ephane and Lef\`evre, S\'ebastien}, title = {Towards Efficient Benchmarking of Foundation Models in Remote Sensing: A Capabilities Encoding Approach}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {3096-3106} }
Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation: Thomas Kerdreux,

Alexandre Tuel,

Quentin Febvre,

Alexis Mouche,

Bertrand Chapron; [pdf] [arXiv]
[bibtex]
@InProceedings{Kerdreux_2025_CVPR, author = {Kerdreux, Thomas and Tuel, Alexandre and Febvre, Quentin and Mouche, Alexis and Chapron, Bertrand}, title = {Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {3017-3027} }
Deep Diffusion Models and Unsupervised Hyperspectral Unmixing for Realistic Abundance Map Synthesis: Martina Pastorino,

Michael Alibani,

Nicola Acito,

Gabriele Moser; [pdf]
[bibtex]
@InProceedings{Pastorino_2025_CVPR, author = {Pastorino, Martina and Alibani, Michael and Acito, Nicola and Moser, Gabriele}, title = {Deep Diffusion Models and Unsupervised Hyperspectral Unmixing for Realistic Abundance Map Synthesis}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {3038-3046} }
COP-GEN-Beta: Unified Generative Modelling of COPernicus Imagery Thumbnails: Miguel Espinosa,

Valerio Marsocci,

Yuru Jia,

Elliot Crowley,

Mikolaj Czerkawski; [pdf] [supp]
[bibtex]
@InProceedings{Espinosa_2025_CVPR, author = {Espinosa, Miguel and Marsocci, Valerio and Jia, Yuru and Crowley, Elliot and Czerkawski, Mikolaj}, title = {COP-GEN-Beta: Unified Generative Modelling of COPernicus Imagery Thumbnails}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {3085-3095} }
PAN-RSVQA: Vision Foundation Models as Pseudo-ANnotators for Remote Sensing Visual Question Answering: Christel Chappuis,

Gencer Sümbül,

Syrielle Montariol,

Sylvain Lobry,

Devis Tuia; [pdf]
[bibtex]
@InProceedings{Chappuis_2025_CVPR, author = {Chappuis, Christel and S\"umb\"ul, Gencer and Montariol, Syrielle and Lobry, Sylvain and Tuia, Devis}, title = {PAN-RSVQA: Vision Foundation Models as Pseudo-ANnotators for Remote Sensing Visual Question Answering}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {3005-3016} }
MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data: Paul Borne--Pons,

Mikolaj Czerkawski,

Rosalie Martin,

Romain Rouffet; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Borne--Pons_2025_CVPR, author = {Borne--Pons, Paul and Czerkawski, Mikolaj and Martin, Rosalie and Rouffet, Romain}, title = {MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {3067-3075} }
Dynamic State-Control Modeling for Generalized Remote Sensing Image Super-Resolution: Chenyu Li,

Zhaojie Pan,

Danfeng Hong; [pdf]
[bibtex]
@InProceedings{Li_2025_CVPR, author = {Li, Chenyu and Pan, Zhaojie and Hong, Danfeng}, title = {Dynamic State-Control Modeling for Generalized Remote Sensing Image Super-Resolution}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {3076-3084} }