3D高斯泼溅中的几何感知风格迁移
Geometry-Aware Style Transfer in 3D Gaussian Splatting
AI总结：
提出一种几何感知风格迁移框架，通过解耦优化交替更新颜色和几何参数，并利用几何感知对比特征匹配（GCFM）将风格图像的结构特征迁移到高斯基元，实现外观与几何结构的同步迁移。
摘要：
在本文中，我们提出了一种新颖的几何感知风格迁移框架，用于3D高斯泼溅（3DGS），该框架同时迁移外观属性和几何结构。与先前主要关注基于颜色的风格化且常常忽略结构适应的工作不同，我们的方法通过解耦优化方案显式地融入几何适应，该方案交替更新颜色和几何参数。这种策略减轻了颜色和几何更新之间的潜在干扰，从而实现稳定且一致的场景级几何变换。解耦优化由所提出的几何感知对比特征匹配（GCFM）实现。GCFM将RGB、深度和边缘线索整合到对比目标中，并在两个优化阶段中使用，以有效地将风格图像的结构特征迁移到高斯基元。大量实验表明，我们的方法在定性保真度和定量指标方面均取得了优越的性能，显著优于现有的基于3DGS的风格化方法。我们的代码可在\href{this https URL}{this https URL}获取。
英文摘要：
In this paper, we present a novel geometry-aware style transfer framework for 3D Gaussian splatting (3DGS) that simultaneously transfers appearance attributes and geometric structures. Unlike prior works that primarily focus on color-based stylization and often overlook structural adaptation, our method explicitly incorporates geometry adaptation through a decoupled optimization scheme that alternately updates color and geometry parameters. This strategy alleviates potential interference between color and geometry updates, leading to stable and consistent scene-level geometry transformation. The decoupled optimization is enabled by the proposed geometry-aware contrastive feature matching (GCFM). GCFM integrates RGB, depth, and edge cues into a contrastive objective and is employed in both optimization phases to effectively transfer structural characteristics from style images to Gaussian primitives. Extensive experiments show that our approach achieves superior performance in both qualitative fidelity and quantitative metrics, significantly outperforming existing 3DGS-based stylization methods. Our code is available at \href{https://github.com/oweixx/gast}{https://github.com/oweixx/gast}.
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。
