Repository files navigation

• 2 Jan 2025:PointSAM has been accepted by TGRS and is now availablehere.
• 8 Dec 2024: The complete code is released.
• 20 Sep 2024: The arXiv version is releasedhere.

To ensure compatibility,Python version must not exceed 3.10. Follow these steps to set up your environment:

conda create --name pointsam python=3.10conda activate pointsampip install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 --index-url https://download.pytorch.org/whl/cu118git clone https://github.com/Lans1ng/PointSAM.gitcd PointSAMpip install -r requirements.txt

Note:The CUDA version in thepip install command is specified ascu118 (CUDA 11.8). If your system uses a different CUDA version (e.g., CUDA 12.1), replacecu118 with the appropriate version tag (e.g.,cu121).

• Dataset download address:WHU Building Dataset。

• For converting semantic label to instance label, you can refer to correspondingconversion script.

• Dataset download address:HRSID Dataset.

• Dataset download address:NWPU VHR-10 Dataset.

• Instance label download address:NWPU VHR-10 Instance Label.

For convenience, the necessary JSON annotations are included in this repo. You only need to download the corresponding images. Organize your 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

Click the links below to download the checkpoint for the corresponding model type.

• vit-h:ViT-H SAM model.
• vit-l:ViT-L SAM model.
• vit-b:ViT-B SAM model.

After downloading, move the models to thepretrain folder.

Note: In our project, only thevit-b model is used.

For convenience, thescripts folder contains instructions forSupervised Training,Self-Training, andPointSAM on the NWPU VHR-10, WHU, and HRSID datasets.

Here’s an example of training PointSAM on the WHU dataset:

bash scripts/train_whu_pointsam.sh

Here’s an example of how to perform inference:

python inference.py --cfg <CONFIG_FILE_PATH> --out_dir <OUTPUT_DIR> --ckpt <CHECKPOINT_PATH>

Please replace<CONFIG_FILE_PATH>,<OUTPUT_DIR>, and<CHECKPOINT_PATH> with the values of the actual path.

Note: The generated results consist of four images arranged in parallel:

• The first image is the original input image.
• The second image is the visualization of the GT mask.
• The third image is the result obtained by direct testing through the original SAM.
• The fourth image is the result obtained using the provided checkpoint.

• wesam
• OWOD
• RSPrompter

If you find this project useful in your research, please consider starring ⭐ and citing 📚:

@ARTICLE{10839471,author={Liu, Nanqing and Xu, Xun and Su, Yongyi and Zhang, Haojie and Li, Heng-Chao},journal={IEEE Transactions on Geoscience and Remote Sensing},title={PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images},year={2025},volume={63},number={},pages={1-15},doi={10.1109/TGRS.2025.3529031}}