Metraipolis › archive › dc_25f375fde90c

Ultra-fast Neural Inference for Stochastic Gaussian Splatting Denoising — arXiv:2609.25604

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25604
License (as archived)
CC0-1.0
Archived
2026-10-08T16:39:11.054Z
SHA-256 of the archived text
5881c0c7475bcfb9f9e5f0649b4c2064d14bcfa290e580d7b5ebcff1593c41b2
Stable URL of this page
https://metraipolis.com/documento/dc_25f375fde90c

How to cite

Ultra-fast Neural Inference for Stochastic Gaussian Splatting Denoising — arXiv:2609.25604 — arXiv (en), https://arxiv.org/abs/2609.25604 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_25f375fde90c (Metraipolis archive dc_25f375fde90c, sha256 5881c0c7475bcfb9f9e5f0649b4c2064d14bcfa290e580d7b5ebcff1593c41b2)
BibTeX
@misc{dc25f375fde90c,
  title = {Ultra-fast Neural Inference for Stochastic Gaussian Splatting Denoising — arXiv:2609.25604},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25604},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_25f375fde90c; sha256 5881c0c7475bcfb9f9e5f0649b4c2064d14bcfa290e580d7b5ebcff1593c41b2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25604. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2609.25604 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T15:56:18.110Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).