Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.07963 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915725599309824 |
|---|---|
| author | Dong, Jiahua Wang, Yu-Xiong |
| author_facet | Dong, Jiahua Wang, Yu-Xiong |
| contents | The transformative potential of 3D content creation has been progressively unlocked through advancements in generative models. Recently, intuitive drag editing with geometric changes has attracted significant attention in 2D editing yet remains challenging for 3D scenes. In this paper, we introduce 3DGS-Drag -- a point-based 3D editing framework that provides efficient, intuitive drag manipulation of real 3D scenes. Our approach bridges the gap between deformation-based and 2D-editing-based 3D editing methods, addressing their limitations to geometry-related content editing. We leverage two key innovations: deformation guidance utilizing 3D Gaussian Splatting for consistent geometric modifications and diffusion guidance for content correction and visual quality enhancement. A progressive editing strategy further supports aggressive 3D drag edits. Our method enables a wide range of edits, including motion change, shape adjustment, inpainting, and content extension. Experimental results demonstrate the effectiveness of 3DGS-Drag in various scenes, achieving state-of-the-art performance in geometry-related 3D content editing. Notably, the editing is efficient, taking 10 to 20 minutes on a single RTX 4090 GPU. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07963 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | 3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D Editing Dong, Jiahua Wang, Yu-Xiong Computer Vision and Pattern Recognition The transformative potential of 3D content creation has been progressively unlocked through advancements in generative models. Recently, intuitive drag editing with geometric changes has attracted significant attention in 2D editing yet remains challenging for 3D scenes. In this paper, we introduce 3DGS-Drag -- a point-based 3D editing framework that provides efficient, intuitive drag manipulation of real 3D scenes. Our approach bridges the gap between deformation-based and 2D-editing-based 3D editing methods, addressing their limitations to geometry-related content editing. We leverage two key innovations: deformation guidance utilizing 3D Gaussian Splatting for consistent geometric modifications and diffusion guidance for content correction and visual quality enhancement. A progressive editing strategy further supports aggressive 3D drag edits. Our method enables a wide range of edits, including motion change, shape adjustment, inpainting, and content extension. Experimental results demonstrate the effectiveness of 3DGS-Drag in various scenes, achieving state-of-the-art performance in geometry-related 3D content editing. Notably, the editing is efficient, taking 10 to 20 minutes on a single RTX 4090 GPU. |
| title | 3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.07963 |