FantasyStyle: Controllable Stylized Distillation for 3D Gaussian Splatting

TL;DR

FantasyStyle introduces a novel 3D Gaussian Splatting style transfer method that enhances multi-view consistency and controllability by leveraging diffusion model distillation and negative guidance, outperforming previous approaches.

Contribution

It is the first to rely entirely on diffusion model distillation for 3D style transfer, addressing multi-view inconsistency and content leakage issues with novel frequency and guidance techniques.

Findings

Outperforms state-of-the-art methods in stylization quality

Achieves higher visual realism across various scenes and styles

Effectively suppresses content leakage and style conflicts

Abstract

The success of 3DGS in generative and editing applications has sparked growing interest in 3DGS-based style transfer. However, current methods still face two major challenges: (1) multi-view inconsistency often leads to style conflicts, resulting in appearance smoothing and distortion; and (2) heavy reliance on VGG features, which struggle to disentangle style and content from style images, often causing content leakage and excessive stylization. To tackle these issues, we introduce \textbf{FantasyStyle}, a 3DGS-based style transfer framework, and the first to rely entirely on diffusion model distillation. It comprises two key components: (1) \textbf{Multi-View Frequency Consistency}. We enhance cross-view consistency by applying a 3D filter to multi-view noisy latent, selectively reducing low-frequency components to mitigate stylized prior conflicts. (2) \textbf{Controllable Stylized Distillation}. To suppress content leakage from style images, we introduce negative guidance to exclude undesired content. In addition, we identify the limitations of Score Distillation Sampling and Delta Denoising Score in 3D style transfer and remove the reconstruction term accordingly. Building on these insights, we propose a controllable stylized distillation that leverages negative guidance to more effectively optimize the 3D Gaussians. Extensive experiments demonstrate that our method consistently outperforms state-of-the-art approaches, achieving higher stylization quality and visual realism across various scenes and styles. The code is available at https://github.com/yangyt46/FantasyStyle.