README.md

EarthVL: A Progressive Earth Vision-Language Understanding and Generation Framework

by Junjue Wang, Yanfei Zhong, Zihang Chen, Zhuo Zheng, Ailong Ma, and Liangpei Zhang

[Paper], [Dataset]

News

• 2026/01/06, New Global-LoveDA !!! We released the global-scale segmentation leaderboard at Global-LoveDA. Just zip all the test images into one file and submit it.
• 2026/01/06, The segmentation data is released at [Dataset].
• 2026/01/06, We are preparing the code and data for EarthVL.
• 2024/09/25, EarthVL is the extension of our EarthVQA and LoveDA projects.

Requirements:

• pytorch >= 1.1.0
• python >=3.6

Install Ever + Segmentation Models PyTorch

pip install ever-beta
pip install git+https://github.com/qubvel/segmentation_models.pytorch

Preparation

• Download Pre-trained vicuna-7B from hugging face: https://huggingface.co/lmsys/vicuna-7b-v1.5
• Unzip the data

Test

sh ./scripts/test.sh

Train

sh ./scripts/train_generation.sh

Citation

If you use EarthVL in your research, please cite our following papers.

    @article{wang2026earthvl,
      title={EarthVL: A Progressive Earth Vision-Language Understanding and Generation Framework},
      author={Wang, Junjue and Zhong, Yanfei and Chen, Zihang and Zheng, Zhuo and Ma, Ailong and Zhang, Liangpei},
      journal={arXiv preprint arXiv:2601.02783},
      year={2026}
    }
    @article{wang2024earthvqa, 
        title={EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering},
        url={https://ojs.aaai.org/index.php/AAAI/article/view/28357}, 
        DOI={10.1609/ai.v38i6.28357}, 
        author={Wang, Junjue and Zheng, Zhuo and Chen, Zihang and Ma, Ailong and Zhong, Yanfei}, 
        year={2024}, 
        month={Mar.},
        volume={38},
        pages={5481-5489}}
    @proceedings{wang2021loveda,
         author = {Wang, Junjue and Zheng, Zhuo and Ma, Ailong and Lu, Xiaoyan and Zhong, Yanfei},
         booktitle = {Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks},
         editor = {J. Vanschoren and S. Yeung},
         pages = {},
         publisher = {Curran Associates, Inc.},
         title = {LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation},
         url = {https://datasets-benchmarks-proceedings.neurips.cc/paper_files/paper/2021/file/4e732ced3463d06de0ca9a15b6153677-Paper-round2.pdf},
         volume = {1},
         year = {2021}
    }

Star History