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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Hu, C., Zhang, H., Zhang, Y., Gai, M., Wang, G., & Li, S. (2026). Ultra-fast Neural Inference for Stochastic Gaussian Splatting Denoising. https://omanscience.com/en/articles/ultra-fast-neural-inference-for-stochastic-gaussian-splatting-denoising
MLA 9
Hu, Chenxiao, et al. "Ultra-fast Neural Inference for Stochastic Gaussian Splatting Denoising." https://omanscience.com/en/articles/ultra-fast-neural-inference-for-stochastic-gaussian-splatting-denoising.
Chicago (author–date)
Hu, Chenxiao, Hao Zhang, Yanchen Zhang, Meng Gai, Guoping Wang, and Sheng Li. 2026. "Ultra-fast Neural Inference for Stochastic Gaussian Splatting Denoising." https://omanscience.com/en/articles/ultra-fast-neural-inference-for-stochastic-gaussian-splatting-denoising.
Harvard
Hu, C., Zhang, H., Zhang, Y., Gai, M., Wang, G. and Li, S. (2026) 'Ultra-fast Neural Inference for Stochastic Gaussian Splatting Denoising', Available at: https://omanscience.com/en/articles/ultra-fast-neural-inference-for-stochastic-gaussian-splatting-denoising.
Vancouver
Hu C, Zhang H, Zhang Y, Gai M, Wang G, Li S. Ultra-fast Neural Inference for Stochastic Gaussian Splatting Denoising. https://omanscience.com/en/articles/ultra-fast-neural-inference-for-stochastic-gaussian-splatting-denoising
IEEE
C. Hu, H. Zhang, Y. Zhang, M. Gai, G. Wang, and S. Li, "Ultra-fast Neural Inference for Stochastic Gaussian Splatting Denoising," https://omanscience.com/en/articles/ultra-fast-neural-inference-for-stochastic-gaussian-splatting-denoising.