Papers › Noise2Self: Blind Denoising by Self-Supervision

Noise2Self: Blind Denoising by Self-Supervision

30 Jan 2019arXiv:1901.11365archive 2025-07-28

Joshua Batson, Loic Royer

We propose a general framework for denoising high-dimensional measurements which requires no prior on the signal, no estimate of the noise, and no clean training data. The only assumption is that the noise exhibits statistical independence across different dimensions of the measurement, while the true signal exhibits some correlation. For a broad class of functions ("𝒥-invariant"), it is then possible to estimate the performance of a denoiser from noisy data alone. This allows us to calibrate 𝒥-invariant versions of any parameterised denoising algorithm, from the single hyperparameter of a median filter to the millions of weights of a deep neural network. We demonstrate this on natural image and microscopy data, where we exploit noise independence between pixels, and on single-cell gene expression data, where we exploit independence between detections of individual molecules. This framework generalizes recent work on training neural nets from noisy images and on cross-validation for matrix factorization.

PaperPDFCodeCode 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

Syntology 20 code samples harvested from 2 repositories linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 11 samples from 1 repository, 10 ran (7 with no instrument failure; 3 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.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

czbiohub/noise2self officialmentioned in papermentioned on GitHubpytorchMITSyntology: 9 samples, 9 ran (0 instrument-failed) · 0 unverified report
abbasi-ali/noise2self mentioned on GitHubpytorchSyntology: not harvested report
mozanunal/SparseCT mentioned on GitHubpytorchMITSyntology: 11 samples, 10 ran (3 instrument-failed) · 1 unverified report
royerlab/ssi-code mentioned on GitHubpytorchSyntology: not harvested 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

20 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 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.

3ran · our draft was wrong
16ran
1unverified

Licence: 3 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 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.

czbiohub/noise2self official repository 9 samples, 9 ran (0 instrument-failed) · 0 unverified
expand in 29 papers util.py ran MIT (permissive) · cc0b8b3068669a1f · report fixture: signature x:ndarray/2/int, r:int/0/int · returned ndarray · level recorded 2026-09-25
grid_distances gaussianprocess/gp.py ran MIT (permissive) · bc20a9e1ef9282cf · report fixture: signature n:int/0/int, torus:bool/0/bool · returned ndarray · level recorded 2026-09-25
interpolate_mask mask.py ran MIT (permissive) · f1eba247029d5ed9 · report fixture: signature tensor:Tensor/4/float, mask:Tensor/4/float, mask_inv:Tensor/4/float · returned Tensor · level recorded 2026-09-25
pad_circular models/singleconv.py ran fingerprinted MIT (permissive) · d5a41a224e76bb65 · report fixture: signature x:Tensor/2/float, pad:int/0/int · returned Tensor · level recorded 2026-09-25
pixel_grid_mask mask.py ran MIT (permissive) · 1a57c82d01231e95 · report fixture: signature shape:tuple/1/int, patch_size:int/0/int, phase_x:int/0/int, phase_y:int/0/int · returned Tensor · level recorded 2026-09-25
rbe_kernel gaussianprocess/gp.py ran fingerprinted MIT (permissive) · 72dec1fa899ff5e0 · report fixture: signature d:ndarray/2/float, length_scale:float/0/float, sigma:float/0/float · returned ndarray · level recorded 2026-09-25
sample_rbe_gp gaussianprocess/gp.py ran MIT (permissive) · 2bf40b28639a6492 · report fixture: signature size:int/0/int, length_scale:float/0/float, samples:int/0/int, torus:bool/0/bool · returned ndarray · level recorded 2026-09-25
scale_tensor util.py ran fingerprinted MIT (permissive) · d17b3b7c14cf588d · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-25
tensor_to_numpy in 10 papers util.py ran fingerprinted MIT (permissive) · 6d58cee70f947cab · report fixture: signature x:Tensor/4/float · returned ndarray · level recorded 2026-09-25
mozanunal/SparseCT community (archive-listed) 11 samples, 10 ran (3 instrument-failed) · 1 unverified
act in 30 papers sparse_ct/model/common.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · e3edcd371d85dd22 · report fixture: signature act_fun:str/0/str · returned LeakyReLU · level recorded 2026-09-22
bn in 19 papers sparse_ct/model/common.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · cd7e7024386fb823 · report fixture: signature num_features:int/0/int · returned BatchNorm2d · level recorded 2026-09-22
conv in 178 papers sparse_ct/model/common.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 040cc21cdcd6aae9 · report fixture: signature in_f:int/0/int, out_f:int/0/int, kernel_size:int/0/int, stride:int/0/int, bias:bool/0/bool, pad:str/0/str, downsample_mode:str/0/str · returned Sequential · level recorded 2026-09-22
get_kernel in 18 papers sparse_ct/model/downsampler.py ran MIT (permissive) · c4b67caf4a9fdb85 · report fixture: signature factor:int/0/int, kernel_type:str/0/str, phase:float/0/float, kernel_width:int/0/int, support:NoneType/0/?, sigma:NoneType/0/? · returned ndarray · level recorded 2026-09-24
im2tensor in 14 papers
census: 3 implementations from 6 papers, 3 distinct outputs on one shared input
sparse_ct/tool.py ran MIT (permissive) · 42c6887aee895c67 · report fixture: signature x:ndarray/2/float, grad:bool/0/bool · returned Tensor · level recorded 2026-09-24
np_to_torch in 5 papers sparse_ct/tool.py ran fingerprinted MIT (permissive) · 278458cc9bc9e16a · report fixture: signature img_np:ndarray/3/float · returned Tensor · level recorded 2026-09-24
torch_to_np sparse_ct/tool.py ran fingerprinted MIT (permissive) · 29a64a0e234ddf27 · report fixture: signature img_var:Tensor/4/float · returned ndarray · level recorded 2026-09-24
tv_2d_l1 sparse_ct/loss/tv.py ran fingerprinted MIT (permissive) · 5eb531b3d79ed2a0 · report fixture: signature img:Tensor/2/float · returned Tensor · level recorded 2026-09-24
tv_2d_l2 sparse_ct/loss/tv.py ran fingerprinted MIT (permissive) · 579bcc9f43d56e4e · report fixture: signature img:Tensor/2/float · returned Tensor · level recorded 2026-09-24
tvd_2d_l2 sparse_ct/loss/tv.py ran MIT (permissive) · 9b8471cb36f4d721 · report fixture: signature img:Tensor/2/float, direction:str/0/str · returned Tensor · level recorded 2026-09-24
Skip sparse_ct/model/skip.py unverified MIT (permissive) · e01560b51159d944 · report

Tasks

Denoising

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Color Image Denoising CellNet DnCNN (n2t) PSNR 34.4 #1 of 1 Archive leaderboard report
Color Image Denoising Hanzi DnCNN (n2t) PSNR 13.9 #1 of 1 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