发表机构
Peking University（北京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对随机高斯泼溅渲染中的空间噪声，提出一种时间神经去噪器，结合双路径累积、信任预测和方差门控，实现快速稳定的自由导航渲染，且开销低于排序混合节省的时间。
AI 中文摘要
随机渲染消除了高斯泼溅中的排序和alpha混合过程，但代价是引入空间噪声。针对视图一致的随机泼溅渲染器共享的像素流，我们提出了一种时间神经去噪器，并在随机2D高斯泼溅渲染上进行了验证。该去噪器结合了双路径指数移动平均累积、用于历史验证的逐像素学习信任预测、固定各向异性空间滤波器以及带稳定化的方差门控合成。该去噪器抑制了噪声，在自由相机导航期间实现了时间稳定、视觉上令人信服的输出，同时保留了无排序、无混合的光栅化性能。组合流水线与排序alpha混合渲染器相比仍存在PSNR差距，但去噪器的开销低于去除排序和混合所节省的时间。
英文摘要
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.
CommentsVideo supplements: https://youtu.be/avWpgs4P1s8; https://www.bilibili.com/video/BV1Jkhk6YEcE
