Drag Your Gaussian: Effective Drag-Based Editing with
Score Distillation for 3D Gaussian Splatting

SIGGRAPH 2025

1Key Laboratory of Multimedia Trusted Perception and Efficient Computing,
Ministry of Education of China, Xiamen University.
2Baidu Inc.
arXiv
Code

Dragging results of DYG: The left video displays the original 3D scene and user input,
while the right video presents the results after the dragging edit.

TL;DR


Pipeline

The overall framework of DYG. Left: Given a 3D Gaussian scene, users provide 3D masks and several pairs of control points as input. Top-right: The Smooth Geometric Editing module predicts positional offsets for 3D Gaussians, resolving the issue of sparse distributions within the target region while ensuring seamless local editing. We adopt a two-stage training strategy: the first stage constructs the geometric scaffold of the edited Gaussians, and the second stage refines the texture details. Bottom-right: In the Score Distillation Guidance Module, to ensure stable optimization, 3D control points are projected onto 2D control points for a specified viewpoint. The RGB image and 2D mask, rendered from the mirrored initial 3D Gaussians, are encoded into point embeddings (P-Emb) and appearance embeddings (A-Emb), which act as conditions for the drag-based LDM. This process leverages our proposed Drag-SDS loss function to enable flexible and view-consistent 3D drag-based editing.

Video Comparison

Below shows the comparison of our results with other 3D Gaussian scene editing methods.

More Results

Multi-Round Edit

Our method supports multi-round dragging on different objects and the same objects.

Multi-round Dragging on Different Objects

Multi-round Dragging on Same Objects

Generalizability

Besides editing real scenes, our method can also edit recent text-to-3D generation results.

Citation

If you want to cite our work, please use: 

@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}
}

Acknowledgements

The website template was borrowed from Michaël Gharbi and MipNeRF360.