基于哈希概率金字塔的欧拉高斯泼溅
Eulerian Gaussian Splatting using Hashed Probability Pyramids
用可学习体密度加哈希概率金字塔替代 3DGS 的手工致密化（ADC 的克隆/分裂/剔除），把基元位置当作密度采样，并用控制变量降低随机梯度方差——做新视角合成的人可直接把这套「概率化致密化」接到自己的 splatting 管线里，去掉调参脆弱的启发式先验。
原文依据 we treat primitive locations as samples drawn from a persistent, learnable density
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出一种基于泼溅的概率化辐射场框架，它保留了 3D 高斯泼溅（3DGS）的快速光栅化与测试时效率，同时以对体概率密度的梯度优化取代启发式的基元操作。我们不再通过手工调参的致密化（如 ADC）来移动、分裂或剔除高斯，而是将基元位置视为从持续存在、可学习的密度中抽取的样本。我们用一种新颖的、内存高效的多尺度层次网格来实例化该密度，从而实现对基元种群密度的端到端梯度控制。为稳定随机训练，我们推导了带控制变量的无偏梯度估计器，显著降低了方差。通过允许概率质量流向损失所要求的位置，本方法消除了脆弱的先验并自然地探索体积，在 mip-NeRF 360 上取得最优的重建质量，同时保持 3DGS 级别的渲染速度。
英文原文摘要 1006 字符
We introduce a probabilistic splat-based radiance field framework that retains the fast rasterization and test-time efficiency of 3D Gaussian Splatting (3DGS) while replacing heuristic primitive manipulation with gradient-based optimization of a volumetric probability density. Rather than relocating, splitting, or culling Gaussians via hand-tuned densification (e.g., ADC), we treat primitive locations as samples drawn from a persistent, learnable density. We instantiate this density with a novel, memory-efficient multi-scale hierarchical grid that enables end-to-end gradient-based control over primitive population density. To stabilize stochastic training, we derive an unbiased gradient estimator with control variates that markedly reduces variance. By allowing probability mass to flow to where the loss demands, our method eliminates brittle priors and naturally explores the volume, achieving state-of-the-art reconstruction quality on mip-NeRF 360 while preserving 3DGS-level rendering speed.