InstantStyleGaussian: Efficient Art Style Transfer with 3D Gaussian Splatting

TL;DR

InstantStyleGaussian introduces a fast and high-quality 3D style transfer method leveraging 3D Gaussian Splatting, diffusion models, and iterative dataset updates to efficiently stylize 3D scenes.

Contribution

The paper proposes a novel 3D style transfer approach that combines 3D Gaussian Splatting with diffusion models and an iterative dataset update, significantly improving speed and quality.

Findings

Achieves high-quality stylized 3D scenes

Significantly accelerates style transfer process

Maintains style transfer consistency

Abstract

We present InstantStyleGaussian, an innovative 3D style transfer method based on the 3D Gaussian Splatting (3DGS) scene representation. By inputting a target-style image, it quickly generates new 3D GS scenes. Our method operates on pre-reconstructed GS scenes, combining diffusion models with an improved iterative dataset update strategy. It utilizes diffusion models to generate target style images, adds these new images to the training dataset, and uses this dataset to iteratively update and optimize the GS scenes, significantly accelerating the style editing process while ensuring the quality of the generated scenes. Extensive experimental results demonstrate that our method ensures high-quality stylized scenes while offering significant advantages in style transfer speed and consistency.