DragGaussian: Enabling Drag-style Manipulation on 3D Gaussian Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shen, Sitian, Xu, Jing, Yuan, Yuheng, Yang, Xingyi, Shen, Qiuhong, Wang, Xinchao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913345313964032
author Shen, Sitian
Xu, Jing
Yuan, Yuheng
Yang, Xingyi
Shen, Qiuhong
Wang, Xinchao
author_facet Shen, Sitian
Xu, Jing
Yuan, Yuheng
Yang, Xingyi
Shen, Qiuhong
Wang, Xinchao
contents User-friendly 3D object editing is a challenging task that has attracted significant attention recently. The limitations of direct 3D object editing without 2D prior knowledge have prompted increased attention towards utilizing 2D generative models for 3D editing. While existing methods like Instruct NeRF-to-NeRF offer a solution, they often lack user-friendliness, particularly due to semantic guided editing. In the realm of 3D representation, 3D Gaussian Splatting emerges as a promising approach for its efficiency and natural explicit property, facilitating precise editing tasks. Building upon these insights, we propose DragGaussian, a 3D object drag-editing framework based on 3D Gaussian Splatting, leveraging diffusion models for interactive image editing with open-vocabulary input. This framework enables users to perform drag-based editing on pre-trained 3D Gaussian object models, producing modified 2D images through multi-view consistent editing. Our contributions include the introduction of a new task, the development of DragGaussian for interactive point-based 3D editing, and comprehensive validation of its effectiveness through qualitative and quantitative experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2405_05800
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DragGaussian: Enabling Drag-style Manipulation on 3D Gaussian Representation
Shen, Sitian
Xu, Jing
Yuan, Yuheng
Yang, Xingyi
Shen, Qiuhong
Wang, Xinchao
Graphics
Computer Vision and Pattern Recognition
User-friendly 3D object editing is a challenging task that has attracted significant attention recently. The limitations of direct 3D object editing without 2D prior knowledge have prompted increased attention towards utilizing 2D generative models for 3D editing. While existing methods like Instruct NeRF-to-NeRF offer a solution, they often lack user-friendliness, particularly due to semantic guided editing. In the realm of 3D representation, 3D Gaussian Splatting emerges as a promising approach for its efficiency and natural explicit property, facilitating precise editing tasks. Building upon these insights, we propose DragGaussian, a 3D object drag-editing framework based on 3D Gaussian Splatting, leveraging diffusion models for interactive image editing with open-vocabulary input. This framework enables users to perform drag-based editing on pre-trained 3D Gaussian object models, producing modified 2D images through multi-view consistent editing. Our contributions include the introduction of a new task, the development of DragGaussian for interactive point-based 3D editing, and comprehensive validation of its effectiveness through qualitative and quantitative experiments.
title DragGaussian: Enabling Drag-style Manipulation on 3D Gaussian Representation
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.05800