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

TL;DR

DragGaussian introduces an interactive 3D editing framework that leverages 3D Gaussian Splatting and diffusion models to enable user-friendly, multi-view consistent modifications of 3D objects using drag-based manipulation.

Contribution

It presents a novel drag-based editing method for 3D Gaussian models, integrating diffusion models for open-vocabulary, multi-view consistent editing, and introduces a new 3D editing task.

Findings

Effective multi-view consistent editing demonstrated

User-friendly drag-based manipulation achieved

Quantitative and qualitative validation confirms effectiveness

Abstract

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.