Metraipolis › archive › dc_28591f4bf197

Parametric Gaussian Noise Mixer (PGNM): Unified Synthesis of Camera Noise and Film Grain — arXiv:2610.39868

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.39868
License (as archived): CC0-1.0
Archived: 2026-11-01T02:42:11.167Z
SHA-256 of the archived text: 0f7cfcf9b20e41268355956de6489ce4c67c6e91e35c868a8fa7db48daba1f04
Stable URL of this page: https://metraipolis.com/documento/dc_28591f4bf197

How to cite

Parametric Gaussian Noise Mixer (PGNM): Unified Synthesis of Camera Noise and Film Grain — arXiv:2610.39868 — arXiv (en), https://arxiv.org/abs/2610.39868 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_28591f4bf197 (Metraipolis archive dc_28591f4bf197, sha256 0f7cfcf9b20e41268355956de6489ce4c67c6e91e35c868a8fa7db48daba1f04)

BibTeX

@misc{dc28591f4bf197,
  title = {Parametric Gaussian Noise Mixer (PGNM): Unified Synthesis of Camera Noise and Film Grain — arXiv:2610.39868},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39868},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_28591f4bf197; sha256 0f7cfcf9b20e41268355956de6489ce4c67c6e91e35c868a8fa7db48daba1f04},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39868. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Noise synthesis is commonly approached through physical models of image formation or neural networks trained to generate noisy images. We explore a middle ground: an explicit statistical model fitted directly from paired clean and noisy images. A normalized convolution correlates a Gaussian field across pixels and color channels, and a lookup maps each Gaussian value to a residual given the clean intensity. Because the field stays standard Gaussian, the two components are fitted separately, without reproducing the physical process or training a neural generator. With one formulation for camera noise from SIDD and simulated film grain from Newson, the model has the lowest average distribution and correlation errors on SIDD among the evaluated methods and remains competitive on film grain. A denoiser trained on its noise comes closest to one trained on real noise, and a 1080p frame renders in 10 ms on GPU.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.39868 — 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 2026-11-01T02:16:43.955Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).