Gaussian Splatting demonstrates impressive results in multi-view reconstruction based on Gaussian explicit representations. However, the current Gaussian primitives only have a single view-dependent color and an opacity to represent the appearance and geometry of the scene, resulting in a non-compact representation. In this paper, we introduce a new method called SVGS (Spatially Varying Gaussian Splatting) that utilizes spatially varying colors and opacity in a single Gaussian primitive to improve its representation ability. We have implemented bilinear interpolation, movable kernels, and tiny neural networks as spatially varying functions. SVGS employs 2D Gaussian surfels as primitives, which significantly enhances novel-view synthesis while maintaining high-quality geometric reconstruction. This approach is particularly effective in practical applications, as scenes combining complex textures with relatively simple geometry occur frequently in real-world environments. Quantitative and qualitative experimental results demonstrate that all three functions outperform the baseline, with the best movable kernels achieving superior novel view synthesis performance on multiple datasets, highlighting the strong potential of spatially varying functions. Project page: https://ruixu.me/html/SuperGaussians/index.html

翻译：高斯泼溅基于高斯显式表示在多视角重建中展现出令人瞩目的结果。然而，当前的高斯基元仅具有单一视角依赖的颜色和不透明度来描述场景的外观与几何结构，导致表示不够紧凑。本文提出一种名为SVGS（空间变化高斯泼溅）的新方法，通过在高斯基元中引入空间变化的颜色和不透明度来提升其表示能力。我们实现了双线性插值、可移动核函数和微型神经网络作为空间变化函数。SVGS采用二维高斯曲面作为基元，在显著增强新视角合成的同时保持高质量的几何重建。该方法在实际应用中尤为有效，因为真实环境中频繁出现复杂纹理与相对简单几何结构相结合的场景。定性与定量实验结果表明，三种函数均优于基准方法，其中最优的可移动核函数在多个数据集上实现了卓越的新视角合成性能，充分展示了空间变化函数的强大潜力。项目页面：https://ruixu.me/html/SuperGaussians/index.html