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 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="1608.03981")

Code

Syntology Ran 1 of 6 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: community (archive-listed): 6 samples 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.

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

cszn/DnCNN officialmentioned in paperpytorch report
IlyaKodua/dncnn mentioned on GitHubpytorchMIT report
MatusPilnan/nsiete-project mentioned on GitHubtf report
abbasi-ali/noise2self mentioned on GitHubpytorch report
anushkayadav/Denoising_cifar10 mentioned on GitHubpytorch report
hekstra-lab/phase-retrieval mentioned on GitHubtf report
kfallah/NODE-Denoiser mentioned on GitHubpytorch report
mingcv/ytmt-strategy mentioned on GitHubpytorchApache-2.0 report
tum-vision/learn_prox_ops mentioned on GitHubtf report
sldyns/DnCNN_paddle paddleApache-2.0 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

6 samples harvested; 1 ran; 0 honoured the contract we drafted; 5 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
5unverified

Licence: 0 of the 6 samples 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 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. “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.

normalize sldyns/DnCNN_paddle/dataset.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 5dfad570b582b1ea · report
Im2Patch sldyns/DnCNN_paddle/dataset.py community (archive-listed) unverified Apache-2.0 (permissive) · 2af2ba98f984835a · report
batch_PSNR sldyns/DnCNN_paddle/infer.py community (archive-listed) unverified Apache-2.0 (permissive) · 91e879f91cafe077 · report
batch_PSNR sldyns/DnCNN_paddle/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 5dda571212a4f9cd · report
data_augmentation sldyns/DnCNN_paddle/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 0b71fac5a3384432 · report
get_args sldyns/DnCNN_paddle/infer.py community (archive-listed) unverified Apache-2.0 (permissive) · dd2a1ad8f3a7814b · report

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