GSR4B

Official implementation for

GSR4B: Biomass Map Super-Resolution with Sentinel-1/2 Guidance
(ISPRS Geospatial Week 2025, Oral)


If you ❤️ or simply use this project, don't forget to give the repository a ⭐, it means a lot to us !

📰 Updates

• 04.04.2025 🚧 Code will soon be publicly released !

Citing our work

If your work uses all or part of the present code, please include the following citation:

@article{karaman2025gsr4b,
  title={GSR4B: Biomass Map Super-Resolution with Sentinel-1/2 Guidance},
  author={Karaman, Kaan and Jiang, Yuchang and Robert, Damien and Sainte Fare Garnot, Vivien and Santos, Maria João and Wegner, Jan Dirk},
  journal={ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences},
  year={2025},
}

You can find our paper 📄 on arxiv.

Also, if you ❤️ or simply use this project, don't forget to give the repository a ⭐, it means a lot to us !

Instructions for the Experiments

Before starting the experiments, please make sure to download the dataset and prepare it properly:

• Download the dataset from here.
• Update the data root path in the configuration file (/codes/configs.json).
• Update the data root path in the dataset script (/codes/source/biomassters.py).
• Run the notebook /codes/notebooks/prepare_dataset.ipynb. Then, please use train_and_test.py script to run the experiments. Before running:
• Update the WandB project name in the train_and_test.py script.
• Give the correct path for dataset and experiment results in the train_and_test.py script.

Models

The models are implemented in /codes/source/models/ directory. The folder /codes/source/external/ contains the implementations of the external methods used for comparison. Please refer them with their respective papers for more details.