- 20 Sep 2024: The arXiv version is released here. The code will be released soon.
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 ..
-
Dataset download address: WHU Building Dataset。
-
For converting semantic label to instance label, you can refer to corresponding conversion script.
- Dataset download address: HRSID 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
├── WHU
│ ├── annotations
│ │ ├── WHU_building_train.json
│ │ ├── WHU_building_test.json
│ │ └── WHU_building_val.json
│ └── images
│ ├── train
│ │ ├── image
│ │ └── label
│ ├── val
│ │ ├── image
│ │ └── label
│ └── test
│ ├── image
│ └── label
├── HRSID
│ ├── Annotations
│ │ ├── all
│ │ ├── inshore
│ │ │ ├── inshore_test.json
│ │ │ └── inshore_train.json
│ │ └── offshore
│ └── Images
└── NWPU
├── Annotations
│ ├── NWPU_instnaces_train.json
│ └── NWPU_instnaces_val.json
└── Images
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}
}