Any Model, Any Place, Any Time: Get Remote Sensing Foundation Model Embeddings On Demand
This addresses the problem of high costs and barriers in adopting and benchmarking foundation models for researchers and practitioners in remote sensing, though it is incremental as it focuses on tooling rather than new model development.
The paper tackles the challenge of inconsistent model formats and interfaces in remote sensing foundation models by introducing rs-embed, a Python library that provides a unified interface for retrieving embeddings from any supported model for any location and time range with a single line of code, enabling efficient batch processing for large-scale use.
The remote sensing community is witnessing a rapid growth of foundation models, which provide powerful embeddings for a wide range of downstream tasks. However, practical adoption and fair comparison remain challenging due to substantial heterogeneity in model release formats, platforms and interfaces, and input data specifications. These inconsistencies significantly increase the cost of obtaining, using, and benchmarking embeddings across models. To address this issue, we propose rs-embed, a Python library that offers a unified, region of interst (ROI) centric interface: with a single line of code, users can retrieve embeddings from any supported model for any location and any time range. The library also provides efficient batch processing to enable large-scale embedding generation and evaluation. The code is available at: https://github.com/cybergis/rs-embed