Official implementation of the paper:
“Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting.”
DYG allows intuitive and flexible 3D scene editing by enabling users to drag 3D Gaussians while preserving fidelity and structure.
teaser.mp4
Visit our Project Page for more examples and visualizations.
Clone the repository:
git clone https://github.com/Quyans/Drag-Your-Gaussian.git
cd Drag-Your-Gaussian
git submodule update --init --recursive Create a new conda environment:
conda env create --file environment.yaml
conda activate DYGFollow 3DGS for reconstruction.
We recommend setting the spherical harmonic degree to 0.
Alternatively, you can use our prepared example data.
Example structure (e.g., face scene):
└── data
└── face
├── export_1
│ ├── drag_points.json
│ └── gaussian_mask.pt
├── image
├── sparse
└── point_cloud.ply
We use LightningDrag as the diffusion prior. Follow LightningDrag Installation Guide to download required models.
Organize them as follows:
└── checkpoints
├── dreamshaper-8-inpainting
├── lcm-lora-sdv1-5/
│ └── pytorch_lora_weights.safetensors
├── sd-vae-ft-ema/
│ ├── config.json
│ ├── diffusion_pytorch_model.bin
│ └── diffusion_pytorch_model.safetensors
├── IP-Adapter/models/
│ ├── image_encoder
│ └── ip-adapter_sd15.bin
└── lightning-drag-sd15/
├── appearance_encoder/
│ ├── config.json
│ └── diffusion_pytorch_model.safetensors
├── point_embedding/
│ └── point_embedding.pt
└── lightning-drag-sd15-attn.bin
Launch the WebUI:
python webui.py --colmap_dir <path_to_colmap> --gs_source <path_to_pointcloud.ply> --output_dir <save_path>Example:
python webui.py --colmap_dir ./data/face/ --gs_source ./data/face/point_cloud.ply --output_dir resultYou can train directly in the WebUI. Alternatively, after selecting drag points and masks, export the files and run:
python drag_3d.py --config configs/main.yaml --colmap_dir ./data/face/ --gs_source ./data/face/point_cloud.ply --point_dir ./data/face/export_1/drag_points.json --mask_dir ./data/face/export_1/gaussian_mask.pt --output_dir resultIf you find our work useful, please cite:
@article{qu2025drag,
title={Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting},
author={Qu, Yansong and Chen, Dian and Li, Xinyang and Li, Xiaofan and Zhang, Shengchuan and Cao, Liujuan and Ji, Rongrong},
journal={arXiv preprint arXiv:2501.18672},
year={2025}
}This project is licensed under the CC BY-NC-SA 4.0.
The code is intended for academic research purposes only.
For any questions or collaborations, feel free to contact:
📧 quyans@stu.xmu.edu.cn