GSDeformer: Direct, Real-time and Extensible Cage-based Deformation for 3D Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Jiajun, Xu, Shuolin, Yu, Hongchuan, Lee, Tong-Yee
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918534057033728
author Huang, Jiajun
Xu, Shuolin
Yu, Hongchuan
Lee, Tong-Yee
author_facet Huang, Jiajun
Xu, Shuolin
Yu, Hongchuan
Lee, Tong-Yee
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2405_15491
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GSDeformer: Direct, Real-time and Extensible Cage-based Deformation for 3D Gaussian Splatting
Huang, Jiajun
Xu, Shuolin
Yu, Hongchuan
Lee, Tong-Yee
Computer Vision and Pattern Recognition
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/
title GSDeformer: Direct, Real-time and Extensible Cage-based Deformation for 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.15491