改进3D高斯点云的密度控制，提升渲染质量与优化效率。
Efficient Density Control for 3D Gaussian Splatting
- 提出长轴分裂策略，精准控制子高斯分布参数
- 通过恢复速度差异识别并移除过拟合高斯点
- 适合追求高质量3D重建与快速优化的研究者
3D高斯点云（3DGS）在新视角合成中表现优异，兼顾渲染质量和实时性。现有自适应密度控制（ADC）中的克隆与分裂操作效率不足，影响优化速度与细节恢复。同时，原始方法无法消除影响渲染质量的过拟合高斯点。为此，本文提出两项创新：(1) 长轴分裂，精确控制子高斯点的位置、形状与透明度，最小化分裂前后的差异；(2) 恢复感知剪枝，利用重置透明度后恢复速度的差异，识别并剔除过拟合高斯点，提升泛化性能。实验表明，该方法显著改善渲染质量。因重新投稿需要，当前版本已废弃，改进版见 https://xiaobin2001.github.io/improved-gs-web。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has demonstrated outstanding performance in novel view synthesis, achieving a balance between rendering quality and real-time performance. 3DGS employs Adaptive Density Control (ADC) to increase the number of Gaussians. However, the clone and split operations within ADC are not sufficiently efficient, impacting optimization speed and detail recovery. Additionally, overfitted Gaussians that affect rendering quality may exist, and the original ADC is unable to remove them. To address these issues, we propose two key innovations: (1) Long-Axis Split, which precisely controls the position, shape, and opacity of child Gaussians to minimize the difference before and after splitting. (2) Recovery-Aware Pruning, which leverages differences in recovery speed after resetting opacity to prune overfitted Gaussians, thereby improving generalization performance. Experimental results show that our method significantly enhances rendering quality. Due to resubmission reasons, this version has been abandoned. The improved version is available at https://xiaobin2001.github.io/improved-gs-web .
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。