GS^2：基于图的空间分布优化用于紧凑三维高斯泼溅
GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting
提出基于图的空间分布优化与不透明度感知渐进剪枝，可在保持渲染质量的同时将高斯点数压缩至约12.5%，为3DGS的轻量化部署提供了可复用的稠密化控制与剪枝策略。
原文依据 we propose graph-based spatial distribution optimization for compact 3D Gaussian Splatting
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维高斯泼溅（3DGS）在新视角合成与实时渲染中展现出突破性性能。然而，由于高斯点数量庞大，其高内存开销限制了实际应用。许多基于剪枝的3DGS变体被提出以节省内存，但往往损害空间一致性并可能导致渲染伪影。为解决该问题，我们提出基于图的空间分布优化用于紧凑三维高斯泼溅（GS^2），通过优化高斯点的空间分布来提升重建质量。具体而言，我们引入基于证据下界（ELBO）的自适应稠密化策略，自动控制稠密化过程。此外，提出不透明度感知的渐进剪枝策略，通过动态移除低不透明度高斯点进一步降低内存消耗。进一步地，我们提出基于图的特征编码模块，通过特征引导的点移位来调整空间分布。大量实验验证GS^2在实现紧凑高斯表示的同时提供更优的渲染质量。与3DGS相比，其仅用约12.5%的高斯点即达到更高的峰值信噪比。此外，在渲染质量和内存效率上均优于所有对比基线。
英文原文摘要 1384 字符
3D Gaussian Splatting (3DGS) has demonstrated breakthrough performance in novel view synthesis and real-time rendering. Nevertheless, its practicality is constrained by the high memory cost due to a huge number of Gaussian points. Many pruning-based 3DGS variants have been proposed for memory saving, but often compromise spatial consistency and may lead to rendering artifacts. To address this issue, we propose graph-based spatial distribution optimization for compact 3D Gaussian Splatting (GS\textasciicircum2), which enhances reconstruction quality by optimizing the spatial distribution of Gaussian points. Specifically, we introduce an evidence lower bound (ELBO)-based adaptive densification strategy that automatically controls the densification process. In addition, an opacity-aware progressive pruning strategy is proposed to further reduce memory consumption by dynamically removing low-opacity Gaussian points. Furthermore, we propose a graph-based feature encoding module to adjust the spatial distribution via feature-guided point shifting. Extensive experiments validate that GS\textasciicircum2 achieves a compact Gaussian representation while delivering superior rendering quality. Compared with 3DGS, it achieves higher PSNR with only about 12.5% Gaussian points. Furthermore, it outperforms all compared baselines in both rendering quality and memory efficiency.