SVGS：利用空间色彩变化基元增强高斯点云渲染

摘要

高斯溅射法基于高斯显式表示在多视图重建中展现出卓越效果。然而当前的高斯基元仅具备单一视角依赖色彩和透明度来描述场景外观与几何特征，导致表征形式不够紧凑。本文提出SVGS（空间变异高斯溅射）新方法，通过单个高斯基元中的空间变异色彩与透明度来提升表征能力。我们实现了双线性插值、可移动核函数以及微型神经网络作为空间变异函数。SVGS采用二维高斯面片作为基元，在保持高质量几何重建的同时，显著提升了新视角合成效果。该方法在实际应用中尤为有效，因为复杂纹理与相对简单几何结合的场景在真实环境中十分常见。定量与定性实验表明，三种函数均优于基线方法，其中可移动核函数在多个数据集上实现了最优的新视角合成性能，彰显了空间变异函数的强大潜力。项目页面：https://ruixu.me/html/SuperGaussians/index.html

English

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

SVGS：利用空间色彩变化基元增强高斯点云渲染

SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors

摘要

Support