InstantStyleGaussian: Efficient Art Style Transfer with 3D Gaussian Splatting
This addresses efficient art style transfer for 3D content creation, though it appears incremental as it builds on existing 3DGS and diffusion model techniques.
The paper tackles 3D style transfer by developing InstantStyleGaussian, which uses 3D Gaussian Splatting and diffusion models to quickly generate stylized 3D scenes from a target-style image, achieving significant speed advantages while maintaining high-quality results.
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.