arXiv:2605.29136cs.CVcs.LG2026-05

用概率金字塔优化高斯点分布,实现更快更准的3D重建。

Eulerian Gaussian Splatting using Hashed Probability Pyramids

论文配图:Eulerian Gaussian Splatting using Hashed Probability Pyramids
图 1 · 摘自论文原文
  • 将高斯点位置视为可学习的概率采样,取代人工调整。
  • 在mip-NeRF 360上达到当前最佳重建质量,渲染速度与3DGS相当。
  • 适合需要高效高质量3D重建的研究者和开发者。

我们提出一种基于概率的点云辐射场框架,保留了3D高斯溅射(3DGS)的快速渲染与测试时效率,同时用梯度优化替代启发式原型操作。不依赖人工密集化策略(如ADC)进行位置移动、分裂或剔除,而是将原型位置视为从持续可学习的概率密度中采样得到。我们使用一种新型的内存高效的多尺度分层网格来实现该密度的实例化,支持端到端梯度优化。为稳定优化过程,我们推导出带控制变量的无偏梯度估计器,显著降低方差。通过允许概率质量流向损失要求的位置,该框架消除了脆弱先验,自然探索空间,在mip-NeRF 360上实现了当前最优重建质量,同时保持3DGS级别的渲染速度。

原文摘要 · Abstract (English)

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 using a novel, memory-efficient multi-scale hierarchical grid that enables end-to-end gradient-based optimization. To stabilize the optimization, 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 framework 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.

3D重建高斯溅射概率建模

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。