Ultra-fast Neural Inference for Stochastic Gaussian Splatting Denoising

2026-09-21

AI Summary

本文提出一种基于神经网络的时域去噪方法，用于解决随机高斯点渲染中的空间噪声问题，通过多路径累积和信任预测等技术实现快速稳定的去噪效果。

Abstract

Stochastic rendering eliminates the sorting and alpha blending process in Gaussian splatting, at the cost of introducing spatial noise. Formulating temporal denoising over the pixel stream shared by view-consistent stochastic splatting renderers, we propose a temporal neural denoiser validated on stochastic 2D Gaussian Splatting rendering, combining dual-path exponential moving average accumulation, per-pixel learned trust prediction for history validation, a fixed anisotropic spatial filter and a variance-gated composition with stabilization. The denoiser suppresses the noise, achieving temporally stable, visually compelling outputs during free camera navigation, all while retaining the sort-free, blend-free rasterization performance. The combined pipeline retains a PSNR gap to sorted alpha-blending renderers, but the denoiser's overhead stays below the time saved by removing sorting and blending.

Problem

• Stochastic Gaussian Splatting
• Spatial Noise
• Temporal Denoising

Innovation

• temporal neural denoiser
• dual-path exponential moving average accumulation
• per-pixel learned trust prediction
• anisotropic spatial filter
• variance-gated composition