提升3D高斯点阵优化速度5倍，同时保持高质量重建。
Faster-GS: Analyzing and Improving Gaussian Splatting Optimization
- 整合并改进前人高效优化策略，新增数值稳定性等新方法。
- 在多个基准上实现最高5倍加速，视觉质量无明显损失。
- 适用于3D与4D非刚性场景，适合资源受限的实时应用。
近期3D高斯点阵（3DGS）研究聚焦于加速优化过程，同时保持重建质量。然而，许多方法将实现层面的改进与基础算法修改混杂，或以牺牲保真度为代价换取性能，导致研究生态碎片化，难以公平比较。本文系统梳理并评估了前人中最有效且普适的优化策略，结合多项新提出的技术，深入探究了框架中被忽视的关键问题：数值稳定性、高斯点裁剪及梯度近似。所提出的Faster-GS系统在全面基准测试中表现优异，实验表明其训练速度最高可提升5倍，同时保持视觉质量。此外，该优化方案可拓展至4D高斯重建，实现高效的非刚性场景优化，建立了一个更高效、低成本的新基准。
原文摘要 · Abstract (English)
Recent advances in 3D Gaussian Splatting (3DGS) have focused on accelerating optimization while preserving reconstruction quality. However, many proposed methods entangle implementation-level improvements with fundamental algorithmic modifications or trade performance for fidelity, leading to a fragmented research landscape that complicates fair comparison. In this work, we consolidate and evaluate the most effective and broadly applicable strategies from prior 3DGS research and augment them with several novel optimizations. We further investigate underexplored aspects of the framework, including numerical stability, Gaussian truncation, and gradient approximation. The resulting system, Faster-GS, provides a rigorously optimized algorithm that we evaluate across a comprehensive suite of benchmarks. Our experiments demonstrate that Faster-GS achieves up to 5$\times$ faster training while maintaining visual quality, establishing a new cost-effective and resource efficient baseline for 3DGS optimization. Furthermore, we demonstrate that optimizations can be applied to 4D Gaussian reconstruction, leading to efficient non-rigid scene optimization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。