Advances on Multimodal Remote Sensing Foundation Models for Earth Observation Downstream Tasks: A Survey
Open Access
- 24 October 2025
- journal article
- review article
- Published by MDPI AG in Remote Sensing
- Vol. 17 (21) , 3532
Abstract
Remote sensing foundation models (RSFMs) have demonstrated excellent feature extraction and reasoning capabilities under the self-supervised learning paradigm of “unlabeled datasets—model pre-training—downstream tasks”. These models achieve superior accuracy and performance compared to existing models across numerous open benchmark datasets. However, when confronted with multimodal data, such as optical, LiDAR, SAR, text, video, and audio, the RSFMs exhibit limitations in cross-modal generalization and multi-task learning. Although several reviews have addressed the RSFMs, there is currently no comprehensive survey dedicated to vision–X (vision, language, audio, position) multimodal RSFMs (MM-RSFMs). To tackle this gap, this article provides a systematic review of MM-RSFMs from a novel perspective. Firstly, the key technologies underlying MM-RSFMs are reviewed and analyzed, and the available multimodal RS pre-training datasets are summarized. Then, recent advances in MM-RSFMs are classified according to the development of backbone networks and cross-modal interaction methods of vision–X, such as vision–vision, vision–language, vision–audio, vision–position, and vision–language–audio. Finally, potential challenges are analyzed, and perspectives for MM-RSFMs are outlined. This survey from this paper reveals that current MM-RSFMs face the following key challenges: (1) a scarcity of high-quality multimodal datasets, (2) limited capability for multimodal feature extraction, (3) weak cross-task generalization, (4) absence of unified evaluation criteria, and (5) insufficient security measures.Keywords
Funding Information
- National Natural Science Foundation of China (42461050)
- Guangxi Surveying and Mapping LiDAR Intelligent Equipment Technology Mid-Test Base (Guike AD23023012)
- Guangxi Science and Technology Talent Grand Project (Guike AD19254002)
- Innovation Project of Guangxi Graduate Education (YCSW2025385)
This publication has 202 references indexed in Scilit:
- LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model2024
- RSDiff: remote sensing image generation from text using diffusion modelNeural Computing and Applications, 2024
- DGGCCM: a hybrid neural model for legal event detectionArtificial Intelligence and Law, 2024
- Few-shot adaptation of multi-modal foundation models: a surveyArtificial Intelligence Review, 2024
- Adaptive Masked Autoencoder Transformer for image classificationApplied Soft Computing, 2024
- Multi-Constraint Transferable Generative Adversarial Networks for Cross-Modal Brain Image SynthesisInternational Journal of Computer Vision, 2024
- GPT models in construction industry: Opportunities, limitations, and a use case validationDevelopments in the Built Environment, 2023
- From single- to multi-modal remote sensing imagery interpretation: a survey and taxonomyScience China Information Sciences, 2023
- ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and BeyondInternational Journal of Computer Vision, 2023
- Learning to Prompt for Vision-Language ModelsInternational Journal of Computer Vision, 2022