ARAP-GS: Drag-Driven As-Rigid-As-Possible 3D Gaussian Splatting Editing with Diffusion Prior

Drag-driven editing is popular among designers for enabling intuitive shape manipulation with minimal technical skills, and has been widely applied to 2D image and 3D mesh editing. However, few studies have explored drag-driven editing for the widely-used 3D Gaussian Splatting (3DGS) representation, as deforming 3DGS while preserving shape coherence and visual continuity remains challenging. In this paper, we introduce ARAP-GS, a drag-driven editing framework that directly applies As-Rigid-As-Possible (ARAP) deformation to 3D Gaussians, enabling flexible geometric control. To maintain visual quality and multi-view consistency, we incorporate a diffusion prior for image enhancement into our iterative optimization process. Experiments show that ARAP-GS outperforms current methods across diverse scenes, achieving effective and efficient drag-driven 3DGS editing in 10–20 minutes on a single RTX 3090 GPU.