Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Survey

TL;DR

This survey reviews the development of remote sensing spatio-temporal vision-language models, highlighting their ability to generate human-readable insights from multi-temporal imagery and discussing future research directions.

Contribution

It provides the first comprehensive overview of RS-STVLMs, covering model evolution, key tasks, components, datasets, and evaluation metrics, guiding future advancements in the field.

Findings

Models now integrate visual and linguistic data for richer analysis.

Progress from task-specific to foundation models leveraging large language models.

Identified key challenges and promising directions for future research.

Abstract

The interpretation of multi-temporal remote sensing imagery is critical for monitoring Earth's dynamic processes-yet previous change detection methods, which produce binary or semantic masks, fall short of providing human-readable insights into changes. Recent advances in Vision-Language Models (VLMs) have opened a new frontier by fusing visual and linguistic modalities, enabling spatio-temporal vision-language understanding: models that not only capture spatial and temporal dependencies to recognize changes but also provide a richer interactive semantic analysis of temporal images (e.g., generate descriptive captions and answer natural-language queries). In this survey, we present the first comprehensive review of RS-STVLMs. The survey covers the evolution of models from early task-specific models to recent general foundation models that leverage powerful large language models. We discuss progress in representative tasks, such as change captioning, change question answering, and change grounding. Moreover, we systematically dissect the fundamental components and key technologies underlying these models, and review the datasets and evaluation metrics that have driven the field. By synthesizing task-level insights with a deep dive into shared architectural patterns, we aim to illuminate current achievements and chart promising directions for future research in spatio-temporal vision-language understanding for remote sensing. We will keep tracing related works at https://github.com/Chen-Yang-Liu/Awesome-RS-SpatioTemporal-VLMs