Papers › Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

13 Aug 2016arXiv:1608.03981archive 2025-07-28

Kai Zhang, WangMeng Zuo, Yunjin Chen, Deyu Meng, Lei Zhang

Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image denoising. Specifically, residual learning and batch normalization are utilized to speed up the training process as well as boost the denoising performance. Different from the existing discriminative denoising models which usually train a specific model for additive white Gaussian noise (AWGN) at a certain noise level, our DnCNN model is able to handle Gaussian denoising with unknown noise level (i.e., blind Gaussian denoising). With the residual learning strategy, DnCNN implicitly removes the latent clean image in the hidden layers. This property motivates us to train a single DnCNN model to tackle with several general image denoising tasks such as Gaussian denoising, single image super-resolution and JPEG image deblocking. Our extensive experiments demonstrate that our DnCNN model can not only exhibit high effectiveness in several general image denoising tasks, but also be efficiently implemented by benefiting from GPU computing.

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

The archive's official repository (cszn/DnCNN) was not harvested; the 6 samples below come from 1 community repository.

Syntology 6 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 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): 6 samples from 1 repository, 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 6 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

cszn/DnCNN officialmentioned in paperpytorchSyntology: not harvested report
IlyaKodua/dncnn mentioned on GitHubpytorchMITSyntology: not harvested report
LabForComputationalVision/bias_free_denoising mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Robust and interpretable blind image denoising via bias-free convolutional neural networks (arXiv:1906.05478; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
MatusPilnan/nsiete-project mentioned on GitHubtfSyntology: not harvested report
ShakedDovrat/JpegArtifactRemoval mentioned on GitHubSyntology: not harvested report
abbasi-ali/noise2self mentioned on GitHubpytorchSyntology: not harvested report
anushkayadav/Denoising_cifar10 mentioned on GitHubpytorchSyntology: not harvested report
hekstra-lab/phase-retrieval mentioned on GitHubtfSyntology: not harvested report
kfallah/NODE-Denoiser mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Neural Ordinary Differential Equations (arXiv:1806.07366; that paper's own run record: 98 ran (of which 44 constructed an object rather than computing a result; 64 with no instrument failure: 2 honoured, 5 violated, 57 with no contract checked; 34 where Syntology's instrument failed) · 26 unverified); nothing checks that they implement this paper's method. report
mingcv/ytmt-strategy mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation (arXiv:2110.10546; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
shibuiwilliam/DeepLearningDenoise mentioned on GitHubSyntology: not harvested report
sunilbelde/Imagedenoising-dncnn-keras mentioned on GitHubtfSyntology: not harvested report
sunilbelde/Imagedenoising-dncnn-ridnet-keras mentioned on GitHubtfSyntology: not harvested report
tum-vision/learn_prox_ops mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems (arXiv:1704.03488; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
2023-MindSpore-1/ms-code-211 mindsporeSyntology: not harvested report
MindSpore-MS-Code2/code0 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code8 mindsporeSyntology: not harvested report
code-implementation1/Code1 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Training data-efficient image transformers & distillation through attention (arXiv:2012.12877; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
sldyns/DnCNN_paddle paddleApache-2.0Syntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
wwhio/megmodels pytorchSyntology: 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.

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

6 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 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.

6ran

Licence: 1 of the 6 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 sldyns/DnCNN_paddle. “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.

sldyns/DnCNN_paddle community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
Im2Patch in 6 papers dataset.py ran Apache-2.0 (permissive) · 2af2ba98f984835a · report fixture: signature img:ndarray/3/float, win:int/0/int, stride:int/0/int · returned ndarray · level recorded 2026-09-25
batch_PSNR in 7 papers infer.py ran Apache-2.0 (permissive) · 91e879f91cafe077 · report fixture: signature Img:ndarray/4/float, Iclean:ndarray/4/float, data_range:int/0/int · returned float64 · level recorded 2026-09-26
batch_PSNR in 7 papers utils.py ran Apache-2.0 (permissive) · 5dda571212a4f9cd · report fixture: signature img:Tensor/4/float, imclean:Tensor/4/float, data_range:int/0/int · returned float64 · level recorded 2026-09-26
data_augmentation in 11 papers utils.py ran fingerprinted Apache-2.0 (permissive) · 0b71fac5a3384432 · report fixture: signature image:ndarray/3/float, mode:int/0/int · returned ndarray · level recorded 2026-09-25
get_args in 84 papers infer.py ran Apache-2.0 (permissive) · dd2a1ad8f3a7814b · report fixture: signature add_help:bool/0/bool · returned Namespace · level recorded 2026-09-26
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
dataset.py ran fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 5dfad570b582b1ea · report fixture: signature data:Tensor/2/float · returned Tensor · level recorded 2026-09-24

Tasks

Color Image DenoisingDenoisingImage DeblockingImage DenoisingImage Super-ResolutionJPEG Artifact CorrectionSuper-Resolution

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

Set12

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Color Image Denoising BSD68 sigma15 DnCNN-3 PSNR 31.46 #4 of 4 Archive leaderboard report
Color Image Denoising BSD68 sigma25 DnCNN-3 PSNR 29.02 #4 of 4 Archive leaderboard report
Color Image Denoising CBSD68 sigma35 DnCNN-B* PSNR 28.74 #6 of 6 Archive leaderboard report
Color Image Denoising urban100 sigma15 DnCNN Average PSNR 32.98 #7 of 8 Archive leaderboard report
Denoising Darmstadt Noise Dataset CDnCNN-B PSNR 32.43 #9 of 10 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma25 DnCNN PSNR 29.23 #10 of 16 Archive leaderboard report
Grayscale Image Denoising Urban100 sigma15 DnCNN PSNR 32.67 #6 of 7 Archive leaderboard report
Grayscale Image Denoising Urban100 sigma25 DnCNN PSNR 29.97 #10 of 10 Archive leaderboard report
Image Super-Resolution BSD100 - 2x upscaling DnCNN-3 PSNR 31.9 #27 of 30 Archive leaderboard report
Image Super-Resolution BSD100 - 3x upscaling DnCNN-3 PSNR 28.85 #20 of 21 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling DnCNN-3 PSNR 27.29 #47 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling DnCNN-3 SSIM 0.7253 #47 of 71 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling DnCNN-3 PSNR 33.03 #31 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 3x upscaling DnCNN-3 PSNR 29.81 #21 of 24 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling DnCNN-3 PSNR 28.04 #80 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling DnCNN-3 SSIM 0.7672 #80 of 104 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling DnCNN-3 PSNR 37.58 #34 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 3x upscaling DnCNN-3 PSNR 33.75 #29 of 32 Archive leaderboard report
Image Super-Resolution Urban100 - 2x upscaling DnCNN-3 PSNR 30.74 #29 of 29 Archive leaderboard report
Image Super-Resolution Urban100 - 3x upscaling DnCNN-3 PSNR 27.15 #22 of 22 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling DnCNN-3 PSNR 25.2 #56 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling DnCNN-3 SSIM 0.7521 #56 of 65 Archive leaderboard report
JPEG Artifact Correction Classic5 (Quality 10 Grayscale) DnCNN-3 PSNR 29.4 #7 of 7 Archive leaderboard report
JPEG Artifact Correction Classic5 (Quality 20 Grayscale) DnCNN-3 PSNR 31.63 #6 of 6 Archive leaderboard report
JPEG Artifact Correction Classic5 (Quality 30 Grayscale) DnCNN-3 PSNR 32.91 #6 of 6 Archive leaderboard report
JPEG Artifact Correction Classic5 (Quality 40 Grayscale) DnCNN-3 PSNR 33.77 #5 of 5 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 20 Grayscale) DnCNN-3 PSNR 31.59 #11 of 12 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 30 Grayscale) DnCNN-3 PSNR 32.98 #6 of 7 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 40 Grayscale) DnCNN-3 PSNR 33.96 #5 of 5 Archive leaderboard report
JPEG Artifact Correction Live1 (Quality 10 Grayscale) DnCNN-3 PSNR 29.19 #11 of 13 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.

Methods

SPEED

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