Papers › Rethinking Noise Synthesis and Modeling in Raw Denoising

Rethinking Noise Synthesis and Modeling in Raw Denoising

10 Oct 2021ICCV 2021 10arXiv:2110.04756archive 2025-07-28

Yi Zhang, Hongwei Qin, Xiaogang Wang, Hongsheng Li

The lack of large-scale real raw image denoising dataset gives rise to challenges on synthesizing realistic raw image noise for training denoising models. However, the real raw image noise is contributed by many noise sources and varies greatly among different sensors. Existing methods are unable to model all noise sources accurately, and building a noise model for each sensor is also laborious. In this paper, we introduce a new perspective to synthesize noise by directly sampling from the sensor's real noise. It inherently generates accurate raw image noise for different camera sensors. Two efficient and generic techniques: pattern-aligned patch sampling and high-bit reconstruction help accurate synthesis of spatial-correlated noise and high-bit noise respectively. We conduct systematic experiments on SIDD and ELD datasets. The results show that (1) our method outperforms existing methods and demonstrates wide generalization on different sensors and lighting conditions. (2) Recent conclusions derived from DNN-based noise modeling methods are actually based on inaccurate noise parameters. The DNN-based methods still cannot outperform physics-based statistical methods.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2110.04756")

Code

Syntology Ran 1 of 1 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: official repository: 1 sample from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zhangyi-3/noise-synthesis officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

1 sample harvested; 1 ran; 1 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract

Licence: 0 of the 1 sample are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zhangyi-3/noise-synthesis. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

noise_profiles zhangyi-3/noise-synthesis/synthesize.py official repository ran · honoured contract MIT (permissive) · 87bc338739bd05f4 · report

Tasks

DenoisingImage Denoising

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Denoising ELD SonyA7S2 x100 SFRN PSNR (Raw) 46.02 #3 of 9 Archive leaderboard report
Image Denoising ELD SonyA7S2 x100 SFRN SSIM (Raw) 0.977 #3 of 9 Archive leaderboard report
Image Denoising ELD SonyA7S2 x200 SFRN PSNR (Raw) 44.10 #3 of 10 Archive leaderboard report
Image Denoising ELD SonyA7S2 x200 SFRN SSIM (Raw) 0.964 #3 of 10 Archive leaderboard report
Image Denoising SID SonyA7S2 x100 SFRN PSNR (Raw) 42.29 #2 of 5 Archive leaderboard report
Image Denoising SID SonyA7S2 x100 SFRN SSIM (Raw) 0.951 #2 of 5 Archive leaderboard report
Image Denoising SID SonyA7S2 x250 SFRN PSNR (Raw) 40.22 #3 of 10 Archive leaderboard report
Image Denoising SID SonyA7S2 x250 SFRN SSIM (Raw) 0.938 #3 of 10 Archive leaderboard report
Image Denoising SID x100 SFRN PSNR (Raw) 42.29 #3 of 8 Archive leaderboard report
Image Denoising SID x100 SFRN SSIM 0.951 #3 of 8 Archive leaderboard report
Image Denoising SID x300 SFRN PSNR (Raw) 36.87 #3 of 8 Archive leaderboard report
Image Denoising SID x300 SFRN SSIM 0.917 #3 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections