优化高斯点云的生成策略，让3D重建更快更准。
Decomposing Densification in Gaussian Splatting for Faster 3D Scene Reconstruction
- 分阶段渐进式添加高斯点，先全局覆盖再局部细化。
- 训练速度提升2倍以上，用更少点实现更好画质。
- 适合追求高效3D重建的开发者和研究者。
3D高斯点阵（GS）已成为高质量场景重建的强大表示方法，但其训练过程常因低效的点云增殖和空间分布不佳而收敛缓慢。本文系统分析了增殖阶段的分裂与克隆操作，揭示其在细节保留与计算效率间的不同作用。基于此，提出全局到局部的增殖策略，促进高斯点在场景空间中更高效生长，兼顾整体覆盖与局部精细。为配合该策略并推动高斯点的空间扩散，引入能量引导的粗到精多分辨率训练框架，根据2D图像的能量密度逐步提升分辨率。同时动态剪枝冗余高斯点以加速训练。在MipNeRF-360、Deep Blending和Tanks & Temples数据集上的大量实验表明，本方法显著加速训练，实现超过2倍的速度提升，使用更少的高斯点且重建质量更优。
原文摘要 · Abstract (English)
3D Gaussian Splatting (GS) has emerged as a powerful representation for high-quality scene reconstruction, offering compelling rendering quality. However, the training process of GS often suffers from slow convergence due to inefficient densification and suboptimal spatial distribution of Gaussian primitives. In this work, we present a comprehensive analysis of the split and clone operations during the densification phase, revealing their distinct roles in balancing detail preservation and computational efficiency. Building upon this analysis, we propose a global-to-local densification strategy, which facilitates more efficient growth of Gaussians across the scene space, promoting both global coverage and local refinement. To cooperate with the proposed densification strategy and promote sufficient diffusion of Gaussian primitives in space, we introduce an energy-guided coarse-to-fine multi-resolution training framework, which gradually increases resolution based on energy density in 2D images. Additionally, we dynamically prune unnecessary Gaussian primitives to speed up the training. Extensive experiments on MipNeRF-360, Deep Blending, and Tanks & Temples datasets demonstrate that our approach significantly accelerates training,achieving over 2x speedup with fewer Gaussian primitives and superior reconstruction performance.
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。