Towards Vision‐Language Geo‐Foundation Models: A Survey
- 28 September 2026
- journal article
- review article
- Published by Wiley in The Photogrammetric Record
- Vol. 41 (196) , e70066
Abstract
Vision‐Language Foundation Models (VLFMs) have made remarkable progress on various multimodal tasks, such as image captioning, image–text retrieval, visual question answering, and visual grounding. However, most methods rely on training with general image datasets, and the lack of geospatial data leads to poor performance on earth observation. Numerous geospatial image–text pair datasets and VLFMs fine‐tuned on them have been proposed recently. These new approaches aim to leverage large‐scale, multimodal geospatial data to build versatile intelligent models with diverse geo‐perceptive capabilities, which we refer to as Vision‐Language Geo‐Foundation Models (VLGFMs). This paper thoroughly reviews VLGFMs, summarizing and analyzing recent developments in the field. In particular, we introduce the background and motivation behind the rise of VLGFMs, highlighting their unique research significance. Then, we systematically summarize the core technologies employed in VLGFMs, including data construction, model architectures, and applications of various multimodal geospatial tasks. Finally, we synthesize empirical trends, remote‐sensing‐specific challenges, and future research directions for reliable and measurement‐aware VLGFMs. Rather than claiming priority over concurrent surveys, this survey emphasizes an integrated organization of data pipelines, architectures, benchmarked capabilities, and practical limitations. We keep tracing related works at https://github.com/zytx121/Awesome‐VLGFM .Keywords
Funding Information
- National Natural Science Foundation of China (62506229)
- National Natural Science Foundation of China (62571315)
This publication has 68 references indexed in Scilit:
- RSUniVLM: A unified vision-language model for remote sensing via Granularity-oriented MoEPattern Recognition, 2026
- Multimodal mathematical reasoning embedded in aerial vehicle imagery: Benchmarking, analysis, and explorationISPRS Journal of Photogrammetry and Remote Sensing, 2025
- LHRS-Bot-Nova: Improved multimodal large language model for remote sensing vision-language interpretationISPRS Journal of Photogrammetry and Remote Sensing, 2025
- RSGPT: A remote sensing vision language model and benchmarkISPRS Journal of Photogrammetry and Remote Sensing, 2025
- SkyEyeGPT: Unifying remote sensing vision-language tasks via instruction tuning with large language modelISPRS Journal of Photogrammetry and Remote Sensing, 2025
- ShareGPT4V: Improving Large Multi-modal Models with Better Captions2024
- LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model2024
- MMBench: Is Your Multi-modal Model an All-Around Player?2024
- PatternNet: A benchmark dataset for performance evaluation of remote sensing image retrievalISPRS Journal of Photogrammetry and Remote Sensing, 2018
- An effective thin cloud removal procedure for visible remote sensing imagesISPRS Journal of Photogrammetry and Remote Sensing, 2014