Papers › Noise2Noise: Learning Image Restoration without Clean Data

Noise2Noise: Learning Image Restoration without Clean Data

12 Mar 2018ICML 2018 7arXiv:1803.04189archive 2025-07-28

Jaakko Lehtinen, Jacob Munkberg, Jon Hasselgren, Samuli Laine, Tero Karras, Miika Aittala, Timo Aila

We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using clean data, without explicit image priors or likelihood models of the corruption. In practice, we show that a single model learns photographic noise removal, denoising synthetic Monte Carlo images, and reconstruction of undersampled MRI scans -- all corrupted by different processes -- based on noisy data only.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (NVlabs/noise2noise) was not harvested; the 7 samples below come from 4 community repositories.

Syntology 7 code samples harvested from 4 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 7 samples from 4 repositories, 6 ran (6 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

21 repositories listed; official and paper-mentioned ones first.

NVlabs/noise2noise officialmentioned in papermentioned on GitHubtfNOASSERTIONSyntology: not harvested report
COMP6248-Reproducability-Challenge/selfsupervised-denoising mentioned on GitHubpytorchSyntology: not harvested report
ChungHanYang/Image-retoration-based-on-SRresnet mentioned on GitHubpytorchSyntology: not harvested report
WangChen0902/noise2noise-paddle mentioned on GitHubpaddleMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
Wenchao-Du/Neighbor2Neighbor_Pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images (arXiv:2101.02824; that paper's own run record: 12 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
ZhenyuTan/Noise2Noise-Cryo-EM-image-denoising mentioned on GitHubpytorchMITSyntology: not harvested report
fanbeatsman/tensorflow-quick-start-image-processing-focus- mentioned on GitHubtfSyntology: not harvested report
foolish0/n2n mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
harshit0511/Unsupervised-Image-denoising mentioned on GitHubSyntology: not harvested report
hungyiwu/average-joe mentioned on GitHubtfMITSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
ishandutta2007/Image-Denoising-Landscape mentioned on GitHubMITSyntology: not harvested report
itsuki8914/simply-noise2noise-TF mentioned on GitHubtfSyntology: not harvested report
joeylitalien/noise2noise-pytorch mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
johnPertoft/noise2noise mentioned on GitHubtfSyntology: not harvested report
juglab/Noise2Noise-with-CSBDeep mentioned on GitHubtfBSD-3-ClauseSyntology: not harvested report
leili666/denoise_deep_learning mentioned on GitHubSyntology: not harvested report
saiteja2901/NVDIA_AI_NoiseRemoval mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
shivamsaboo17/Deep-Restore-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
tgieruc/Noise2Noise_PyTorch mentioned on GitHubpytorchSyntology: not harvested report
vlcekl/n2n-tomo mentioned on GitHubpytorchMITSyntology: not harvested report
zzskyy0301/ML_PROJECT mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

7 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
5ran
1unverified

Licence: 1 of the 7 samples is 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

WangChen0902/noise2noise-paddle community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
config_buffers_scene src/render.py ran MIT (permissive) · 4dc2ca09e71c0f1b · report fixture: signature args:Args/0/? · returned str · level recorded 2026-09-26
config_targets_scene src/render.py ran MIT (permissive) · e0d1db07072c560e · report fixture: signature args:Args/0/? · returned str · level recorded 2026-09-26
time_elapsed_since src/utils.py ran MIT (permissive) · 3acb658a0f2c8597 · report fixture: signature start:datetime/0/? · returned tuple · level recorded 2026-09-26
hungyiwu/average-joe community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
shuffle_label code/data_util.py ran fingerprinted MIT (permissive) · 68b05e71a06f016f · report fixture: signature arr:ndarray/2/float, label:ndarray/1/int · returned ndarray · level recorded 2026-09-26
joeylitalien/noise2noise-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
reinhard_tonemap src/utils.py ran fingerprinted MIT (permissive) · 244c8cc82cb47da6 · report fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-26
zzskyy0301/ML_PROJECT community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
load_image in 273 papers dataset_tool_tf.py ran · honoured contract licence not identified · pointer only · 6b60f5ef4a30c694 · report fixture: signature fname:str/0/str · returned ndarray · level recorded 2026-09-22

Tasks

BIG-bench Machine LearningDenoisingImage RestorationSalt-And-Pepper Noise Removal

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Salt-And-Pepper Noise Removal BSD300 Noise Level 30% Noise2Noise PSNR 39.83 #3 of 3 Archive leaderboard report
Salt-And-Pepper Noise Removal BSD300 Noise Level 50% Noise2Noise PSNR 35.92 #3 of 3 Archive leaderboard report
Salt-And-Pepper Noise Removal BSD300 Noise Level 70% Noise2Noise PSNR 31.42 #3 of 3 Archive leaderboard report
Salt-And-Pepper Noise Removal Kodak24 Noise Level 30% Noise2Noise PSNR 34.95 #2 of 3 Archive leaderboard report
Salt-And-Pepper Noise Removal Kodak24 Noise Level 50% Noise2Noise PSNR 32.27 #2 of 3 Archive leaderboard report
Salt-And-Pepper Noise Removal Kodak24 Noise Level 70% Noise2Noise PSNR 30.49 #2 of 3 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