FantasyStyle: 用于3D高斯点云的可控风格化蒸馏
FantasyStyle: Controllable Stylized Distillation for 3D Gaussian Splatting
AI总结：
FantasyStyle通过可控风格化蒸馏和多视图频率一致性，解决3DGS风格迁移中的多视图不一致和内容泄漏问题，提升风格化质量与视觉真实感。
摘要：
3DGS在生成和编辑应用中的成功引发了对基于3DGS的风格迁移的广泛关注。然而，当前方法仍面临两个主要挑战：（1）多视图不一致常常导致风格冲突，从而引起外观平滑和变形；（2）对VGG特征的依赖较大，难以从风格图像中分离风格和内容，常导致内容泄漏和过度风格化。为解决这些问题，我们引入FantasyStyle，一种基于3DGS的风格迁移框架，且是首个完全依赖扩散模型蒸馏的方法。它包含两个关键组件：（1）多视图频率一致性。我们通过应用3D滤波器对多视图噪声潜在特征进行增强，选择性地减少低频成分以缓解风格先验冲突。（2）可控风格化蒸馏。为抑制从风格图像中泄漏的内容，我们引入负向指导以排除不期望的内容。此外，我们识别了Score Distillation Sampling和Delta Denoising Score在3D风格迁移中的局限性，并相应地去除了重建项。基于这些见解，我们提出了一种可控的风格化蒸馏方法，利用负向指导更有效地优化3D高斯点云。大量实验表明，我们的方法在各种场景和风格中均优于最先进的方法，实现了更高的风格化质量和视觉真实感。代码可在https://github.com/yangyt46/FantasyStyle上获得。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
