Awesome
PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images
<p align="center"> <img src="https://i.imgur.com/waxVImv.png" alt="Oryx Video-ChatGPT"> </p>š¢ Latest Updates
- 20 Sep 2024: The arXiv version is released here. The code will be released soon.
šØ Overview
š® Getting Started
1.Install Environment
conda create --name pointsam python=3.10
conda activate pointsam
pip install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 --index-url https://download.pytorch.org/whl/cu118
git clone https://github.com/Lans1ng/PointSAM.git
cd PointSAM
pip install -r requirements.txt
cd segment_anything_2
pip install -e .
cd ..
2.Prepare Dataset
WHU Building Dataset
-
Dataset download address: WHU Building Datasetć
-
For converting semantic label to instance label, you can refer to corresponding conversion script.
HRSID Dataset
- Dataset download address: HRSID Dataset.
NWPU VHR-10 Dataset
-
Dataset download address: NWPU VHR-10 Dataset.
-
Instance label download address: NWPU VHR-10 Instance Label.
For convenience, we have included all the JSON annotations in this repo, and you only need to download the corresponding images. Specifically, organize the dataset as follows:
data
āāā WHU
ā āāā annotations
ā ā āāā WHU_building_train.json
ā ā āāā WHU_building_test.json
ā ā āāā WHU_building_val.json
ā āāā images
ā āāā train
ā ā āāā image
ā ā āāā label
ā āāā val
ā ā āāā image
ā ā āāā label
ā āāā test
ā āāā image
ā āāā label
āāā HRSID
ā āāā Annotations
ā ā āāā all
ā ā āāā inshore
ā ā ā āāā inshore_test.json
ā ā ā āāā inshore_train.json
ā ā āāā offshore
ā āāā Images
āāā NWPU
āāā Annotations
ā āāā NWPU_instnaces_train.json
ā āāā NWPU_instnaces_val.json
āāā Images
š” Acknowledgement
šļø Citation
If you find this project useful in your research, please consider cite:
@article{liu2024pointsam,
title={PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images},
author={Liu, Nanqing and Xu, Xun and Su, Yongyi and Zhang, Haojie and Li, Heng-Chao},
journal={arXiv preprint arXiv:2409.13401},
year={2024}
}