Papers › FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising

FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising

11 Oct 2017arXiv:1710.04026archive 2025-07-28

Kai Zhang, WangMeng Zuo, Lei Zhang

Due to the fast inference and good performance, discriminative learning methods have been widely studied in image denoising. However, these methods mostly learn a specific model for each noise level, and require multiple models for denoising images with different noise levels. They also lack flexibility to deal with spatially variant noise, limiting their applications in practical denoising. To address these issues, we present a fast and flexible denoising convolutional neural network, namely FFDNet, with a tunable noise level map as the input. The proposed FFDNet works on downsampled sub-images, achieving a good trade-off between inference speed and denoising performance. In contrast to the existing discriminative denoisers, FFDNet enjoys several desirable properties, including (i) the ability to handle a wide range of noise levels (i.e., [0, 75]) effectively with a single network, (ii) the ability to remove spatially variant noise by specifying a non-uniform noise level map, and (iii) faster speed than benchmark BM3D even on CPU without sacrificing denoising performance. Extensive experiments on synthetic and real noisy images are conducted to evaluate FFDNet in comparison with state-of-the-art denoisers. The results show that FFDNet is effective and efficient, making it highly attractive for practical denoising applications.

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/FFDNet) was not harvested; the 7 samples below come from 2 community repositories.

Syntology 7 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 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): 7 samples from 2 repositories, 7 ran (7 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.

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

cszn/FFDNet officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
7568/ffdnet-pytorch mentioned on GitHubpytorchSyntology: not harvested report
Aoi-hosizora/FFDNet_pytorch mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
LucasElbert/FFDNet mentioned on GitHubpytorchSyntology: not harvested report
SamirMitha/Denoising mentioned on GitHubtfMITSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
deshanyang/abdominal-dir-qa mentioned on GitHubSyntology: not harvested report
deshanyang/liver-dir-qa mentioned on GitHubSyntology: not harvested report
mq0829/DL-CACTI mentioned on GitHubtfSyntology: 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

7 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 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.

7ran

Licence: 0 of the 7 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 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.

Aoi-hosizora/FFDNet_pytorch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
downsample in 59 papers utils.py ran fingerprinted MIT (permissive) · 32cbb0bf667d4344 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-26
is_image_gray utils.py ran fingerprinted MIT (permissive) · 4efa089015c96dbb · report fixture: signature image:ndarray/2/int · returned bool · level recorded 2026-09-26
upsample in 87 papers
census: 11 implementations from 16 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
utils.py ran fingerprinted MIT (permissive) · f8bb0108cfdc61e2 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-26
SamirMitha/Denoising community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
denormalize in 64 papers
census: 9 implementations from 11 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
FFDNet-Keras/utils.py ran fingerprinted MIT (permissive) · 9826ce88e0ace708 · report fixture: signature img:ndarray/3/float · returned ndarray · level recorded 2026-09-26
img_to_patches FFDNet-Keras/utils.py ran MIT (permissive) · 56373616d9d5d6e2 · report fixture: signature img:ndarray/3/float, patch_size:tuple/1/int · returned ndarray · level recorded 2026-09-26
img_to_patches DnCNN-Keras/utils.py ran MIT (permissive) · 36d462f86684d561 · report fixture: signature img:ndarray/3/float, patch_size:tuple/1/int · returned ndarray · 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
FFDNet-Keras/utils.py ran fingerprinted MIT (permissive) · 0ca1aabdc293fc5f · report fixture: signature img:ndarray/3/int · returned ndarray · level recorded 2026-09-26

Tasks

Color Image DenoisingDenoisingImage Denoising

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Color Image Denoising CBSD68 sigma15 FFDNet PSNR 33.87 #8 of 10 Archive leaderboard report
Color Image Denoising CBSD68 sigma25 FFDNet PSNR 31.21 #7 of 9 Archive leaderboard report
Color Image Denoising CBSD68 sigma35 FFDNet PSNR 29.58 #3 of 6 Archive leaderboard report
Color Image Denoising CBSD68 sigma50 FFDNet PSNR 27.96 #12 of 18 Archive leaderboard report
Color Image Denoising CBSD68 sigma75 FFDNet PSNR 26.24 #3 of 4 Archive leaderboard report
Color Image Denoising Kodak25 sigma15 FFDNet PSNR 34.63 #1 of 1 Archive leaderboard report
Color Image Denoising Kodak25 sigma25 FFDNet PSNR 32.13 #1 of 1 Archive leaderboard report
Color Image Denoising Kodak25 sigma35 FFDNet PSNR 30.57 #1 of 1 Archive leaderboard report
Color Image Denoising Kodak25 sigma50 FFDNet PSNR 28.98 #1 of 1 Archive leaderboard report
Color Image Denoising Kodak25 sigma75 FFDNet PSNR 27.27 #1 of 1 Archive leaderboard report
Color Image Denoising McMaster sigma15 FFDNet PSNR 34.66 #4 of 4 Archive leaderboard report
Color Image Denoising McMaster sigma25 FFDNet PSNR 32.35 #4 of 4 Archive leaderboard report
Color Image Denoising McMaster sigma35 FFDNet PSNR 30.81 #1 of 1 Archive leaderboard report
Color Image Denoising McMaster sigma50 FFDNet PSNR 29.18 #5 of 7 Archive leaderboard report
Color Image Denoising McMaster sigma75 FFDNet PSNR 27.33 #1 of 1 Archive leaderboard report
Color Image Denoising urban100 sigma15 FFDNet Average PSNR 33.83 #6 of 8 Archive leaderboard report
Denoising Darmstadt Noise Dataset FFDNet PSNR 34.40 #7 of 10 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma15 FFDNet PSNR 31.63 #11 of 16 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma25 FFDNet PSNR 29.19 #11 of 16 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma35 FFDNet PSNR 27.73 #1 of 2 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma50 FFDNet PSNR 26.29 #13 of 15 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma75 FFDNet PSNR 24.79 #1 of 2 Archive leaderboard report
Grayscale Image Denoising Clip300 sigma15 FFDNet-Clip PSNR 31.68 #1 of 1 Archive leaderboard report
Grayscale Image Denoising Clip300 sigma25 FFDNet-Clip PSNR 29.25 #1 of 1 Archive leaderboard report
Grayscale Image Denoising Clip300 sigma35 FFDNet-Clip PSNR 27.75 #1 of 1 Archive leaderboard report
Grayscale Image Denoising Clip300 sigma50 FFDNet-Clip PSNR 26.25 #1 of 1 Archive leaderboard report
Grayscale Image Denoising Clip300 sigma60 FFDNet-Clip PSNR 25.51 #1 of 1 Archive leaderboard report
Grayscale Image Denoising Set12 sigma15 FFDNet PSNR 25.49 #8 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.

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