Saved in:
Bibliographic Details
Main Authors: Yang, Liling, Chen, Ning, Yue, Jun, Liu, Yidan, Ma, Jiayi, Ghamisi, Pedram, Plaza, Antonio, Fang, Leyuan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.22964
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917044918681600
author Yang, Liling
Chen, Ning
Yue, Jun
Liu, Yidan
Ma, Jiayi
Ghamisi, Pedram
Plaza, Antonio
Fang, Leyuan
author_facet Yang, Liling
Chen, Ning
Yue, Jun
Liu, Yidan
Ma, Jiayi
Ghamisi, Pedram
Plaza, Antonio
Fang, Leyuan
contents Foundation models have transformed natural language processing and computer vision, and their impact is now reshaping remote sensing image analysis. With powerful generalization and transfer learning capabilities, they align naturally with the multimodal, multi-resolution, and multi-temporal characteristics of remote sensing data. To address unique challenges in the field, multimodal geospatial foundation models (GFMs) have emerged as a dedicated research frontier. This survey delivers a comprehensive review of multimodal GFMs from a modality-driven perspective, covering five core visual and vision-language modalities. We examine how differences in imaging physics and data representation shape interaction design, and we analyze key techniques for alignment, integration, and knowledge transfer to tackle modality heterogeneity, distribution shifts, and semantic gaps. Advances in training paradigms, architectures, and task-specific adaptation strategies are systematically assessed alongside a wealth of emerging benchmarks. Representative multimodal visual and vision-language GFMs are evaluated across ten downstream tasks, with insights into their architectures, performance, and application scenarios. Real-world case studies, spanning land cover mapping, agricultural monitoring, disaster response, climate studies, and geospatial intelligence, demonstrate the practical potential of GFMs. Finally, we outline pressing challenges in domain generalization, interpretability, efficiency, and privacy, and chart promising avenues for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22964
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Survey of Multimodal Geospatial Foundation Models: Techniques, Applications, and Challenges
Yang, Liling
Chen, Ning
Yue, Jun
Liu, Yidan
Ma, Jiayi
Ghamisi, Pedram
Plaza, Antonio
Fang, Leyuan
Computer Vision and Pattern Recognition
Foundation models have transformed natural language processing and computer vision, and their impact is now reshaping remote sensing image analysis. With powerful generalization and transfer learning capabilities, they align naturally with the multimodal, multi-resolution, and multi-temporal characteristics of remote sensing data. To address unique challenges in the field, multimodal geospatial foundation models (GFMs) have emerged as a dedicated research frontier. This survey delivers a comprehensive review of multimodal GFMs from a modality-driven perspective, covering five core visual and vision-language modalities. We examine how differences in imaging physics and data representation shape interaction design, and we analyze key techniques for alignment, integration, and knowledge transfer to tackle modality heterogeneity, distribution shifts, and semantic gaps. Advances in training paradigms, architectures, and task-specific adaptation strategies are systematically assessed alongside a wealth of emerging benchmarks. Representative multimodal visual and vision-language GFMs are evaluated across ten downstream tasks, with insights into their architectures, performance, and application scenarios. Real-world case studies, spanning land cover mapping, agricultural monitoring, disaster response, climate studies, and geospatial intelligence, demonstrate the practical potential of GFMs. Finally, we outline pressing challenges in domain generalization, interpretability, efficiency, and privacy, and chart promising avenues for future research.
title Survey of Multimodal Geospatial Foundation Models: Techniques, Applications, and Challenges
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.22964