Foundation Models in Remote Sensing: Evolving from Unimodality to Multimodality

2026-03-01

AI Summary

This work presents a systematic survey of foundational models in remote sensing, tracing their evolution from single-modality to multimodal paradigms. It addresses the growing challenges posed by the rapid expansion in scale and modality diversity of remote sensing data, which demand more efficient approaches for understanding and integrating multisource information. The paper comprehensively reviews key aspects including model architectures, training strategies, multimodal fusion mechanisms, and adaptation methods for downstream tasks. Furthermore, it introduces a structured entry-level framework tailored for newcomers, offering a clear taxonomy of techniques, practical tutorials, and a research roadmap. This initiative significantly lowers the barrier to applying foundational models in remote sensing and provides a cohesive guide for future research directions in the field.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Deep Neural Architectures and Foundation Models
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Remote sensing (RS) techniques are increasingly crucial for deepening our understanding of the planet. As the volume and diversity of RS data continue to grow exponentially, there is an urgent need for advanced data modeling and understanding capabilities to manage and interpret these vast datasets effectively. Foundation models present significant new growth opportunities and immense potential to revolutionize the RS field. In this paper, we conduct a comprehensive technical survey on foundation models in RS, offering a brand-new perspective by exploring their evolution from unimodality to multimodality. We hope this work serves as a valuable entry point for researchers interested in both foundation models and RS and helps them launch new projects or explore new research topics in this rapidly evolving area. This survey addresses the following three key questions: What are foundation models in RS? Why are foundation models needed in RS? How can we effectively guide junior researchers in gaining a comprehensive and practical understanding of foundation models in RS applications? More specifically, we begin by outlining the background and motivation, emphasizing the importance of foundation models in RS. We then review existing foundation models in RS, systematically categorizing them into unimodal and multimodal approaches. Additionally, we provide a tutorial-like section to guide researchers, especially beginners, on how to train foundation models in RS and apply them to real-world tasks. The survey aims to equip researchers in RS with a deeper and more efficient understanding of foundation models, enabling them to get started easily and effectively apply these models across various RS applications.

Problem

• Foundation Models
• Remote Sensing
• Multimodality
• Data Understanding
• Model Training

Innovation

• Foundation Models
• Remote Sensing
• Multimodality
• Unimodality
• Technical Survey