GaussianPOP: 基于误差量化的原则性简化框架用于紧凑3D高斯点云渲染
GaussianPOP: Principled Simplification Framework for Compact 3D Gaussian Splatting via Error Quantification
AI总结：
GaussianPOP通过基于误差量化的原理性框架，实现3D高斯点云渲染的高效简化，提升模型紧凑性与渲染质量的平衡。
摘要：
现有的3D高斯点云简化方法通常使用重要性分数，如混合权重或敏感度，来识别冗余的高斯分布。然而，这些分数并非由视觉误差度量驱动，往往导致在紧凑性和渲染保真度之间做出次优的权衡。我们提出了GaussianPOP，一种基于分析高斯误差量化的原理性简化框架。我们的关键贡献是一个新的误差准则，直接从3DGS渲染方程导出，精确测量每个高斯分布对渲染图像的贡献。通过引入一个高效算法，我们的框架能够在单次正向传递中实现实用的误差计算。该框架既准确又灵活，支持训练期间的剪枝以及通过迭代误差重新量化进行训练后的简化，以提高稳定性。实验结果表明，我们的方法在两种应用场景中均优于现有最先进的剪枝方法，实现了在模型紧凑性和高质量渲染之间更优的权衡。
英文摘要：
Existing 3D Gaussian Splatting simplification methods commonly use importance scores, such as blending weights or sensitivity, to identify redundant Gaussians. However, these scores are not driven by visual error metrics, often leading to suboptimal trade-offs between compactness and rendering fidelity. We present GaussianPOP, a principled simplification framework based on analytical Gaussian error quantification. Our key contribution is a novel error criterion, derived directly from the 3DGS rendering equation, that precisely measures each Gaussian's contribution to the rendered image. By introducing a highly efficient algorithm, our framework enables practical error calculation in a single forward pass. The framework is both accurate and flexible, supporting on-training pruning as well as post-training simplification via iterative error re-quantification for improved stability. Experimental results show that our method consistently outperforms existing state-of-the-art pruning methods across both application scenarios, achieving a superior trade-off between model compactness and high rendering quality.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
