GSDeformer: Direct, Real-time and Extensible Cage-based Deformation for 3D Gaussian Splatting
This work addresses the challenge of interactive and extensible deformation for 3DGS users, offering a practical tool for editing 3D scenes, though it is incremental as it builds on existing 3DGS methods.
The paper tackles the problem of enabling cage-based deformation for 3D Gaussian Splatting (3DGS) by introducing GSDeformer, which uses a proxy point-cloud representation to apply deformations without modifying the core 3DGS architecture, resulting in superior deformation quality, robustness under extreme conditions, real-time performance, and no need for retraining.
We present GSDeformer, a method that enables cage-based deformation on 3D Gaussian Splatting (3DGS). Our approach bridges cage-based deformation and 3DGS by using a proxy point-cloud representation. This point cloud is generated from 3D Gaussians, and deformations applied to the point cloud are translated into transformations on the 3D Gaussians. To handle potential bending caused by deformation, we incorporate a splitting process to approximate it. Our method does not modify or extend the core architecture of 3D Gaussian Splatting, making it compatible with any trained vanilla 3DGS or its variants. Additionally, we automate cage construction for 3DGS and its variants using a render-and-reconstruct approach. Experiments demonstrate that GSDeformer delivers superior deformation results compared to existing methods, is robust under extreme deformations, requires no retraining for editing, runs in real-time, and can be extended to other 3DGS variants. Project Page: https://jhuangbu.github.io/gsdeformer/