SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors

TL;DR

SVGS introduces spatially varying colors and opacity in Gaussian primitives, significantly improving multi-view scene reconstruction and novel-view synthesis over traditional Gaussian splatting methods.

Contribution

The paper proposes SVGS, a novel method using spatially varying functions within Gaussian primitives to enhance scene representation and rendering quality.

Findings

SVGS outperforms baseline in quantitative and qualitative tests.

Movable kernels achieve the best novel view synthesis results.

Spatially varying functions improve scene representation in complex environments.

Abstract

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