Papers › Simple Baselines for Image Restoration

Simple Baselines for Image Restoration

10 Apr 2022arXiv:2204.04676archive 2025-07-28

Liangyu Chen, Xiaojie Chu, Xiangyu Zhang, Jian Sun

Although there have been significant advances in the field of image restoration recently, the system complexity of the state-of-the-art (SOTA) methods is increasing as well, which may hinder the convenient analysis and comparison of methods. In this paper, we propose a simple baseline that exceeds the SOTA methods and is computationally efficient. To further simplify the baseline, we reveal that the nonlinear activation functions, e.g. Sigmoid, ReLU, GELU, Softmax, etc. are not necessary: they could be replaced by multiplication or removed. Thus, we derive a Nonlinear Activation Free Network, namely NAFNet, from the baseline. SOTA results are achieved on various challenging benchmarks, e.g. 33.69 dB PSNR on GoPro (for image deblurring), exceeding the previous SOTA 0.38 dB with only 8.4% of its computational costs; 40.30 dB PSNR on SIDD (for image denoising), exceeding the previous SOTA 0.28 dB with less than half of its computational costs. The code and the pre-trained models are released at https://github.com/megvii-research/NAFNet.

PaperPDFCodeCode Syntology ranMethod as code

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 30 code samples harvested from 9 repositories linked to this paper: 23 ran (of which 8 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 29 samples from 8 repositories, 22 ran (13 with no instrument failure; 9 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

megvii-research/NAFNet officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
dhryougit/afm mentioned on GitHubpytorchNOASSERTIONSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
dhryougit/learning-to-translate-noise mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
dslisleedh/NAFNet-flax mentioned on GitHubjaxSyntology: 1 sample, 0 ran · 1 unverified report
dslisleedh/NAFNet-tensorflow2 mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
megvii-research/TLC mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
megvii-research/tlsc mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
rflepp/efficient_mobile_denoising_models mentioned on GitHubtfSyntology: 4 samples, 3 ran (1 instrument-failed) · 1 unverified report
setsunil/dsdnet mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
2023-MindSpore-4/Code-5 mindsporeSyntology: not harvested report
Thehunk1206/Image-Restorers tfSyntology: 1 sample, 0 ran · 1 unverified report
lime-j/nafnet-jax jaxSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
murufeng/FUIR pytorchApache-2.0Syntology: 12 samples, 11 ran (8 instrument-failed) · 1 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.

Code Syntology ran Syntology

30 samples harvested: 23 ran (of which 8 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
5ran · our draft was wrong
4ran; the contract check could not run
12ran
7unverified

Licence: 22 of the 30 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 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 9 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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

megvii-research/NAFNet official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
NAFNet basicsr/models/archs/NAFNet_arch.py ran fingerprinted licence not identified · pointer only · b1bd781b7fd93162 · report fixture: signature inp:Tensor/4/float · returned Tensor · level recorded 2026-09-24
dhryougit/afm community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Baseline in 6 papers basicsr/models/archs/Baseline_arch.py ran fingerprinted licence not identified · pointer only · 6ce5b700c75ef796 · report fixture: returned Baseline · level recorded 2026-09-22
BaselineBlock basicsr/models/archs/Baseline_arch.py ran fingerprinted licence not identified · pointer only · 1a0ca651efcee9e4 · report fixture: signature inp:Tensor/4/float · returned Tensor · level recorded 2026-09-24
dhryougit/learning-to-translate-noise community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
NAFBlock in 5 papers models/modules/NAFNet_arch.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · aa1fe0a698ddd646 · report fixture: returned NAFBlock · level recorded 2026-09-22
NAFNet models/modules/NAFNet_arch.py ran · metamorphic tier: deterministic no licence file found · pointer only · 2dd382ce15e8576d · report fixture: returned NAFNet · level recorded 2026-09-22
dslisleedh/NAFNet-flax community (archive-listed) 1 sample, 0 ran · 1 unverified
NAFNet nafnet.py unverified no licence file found · pointer only · 11a0e1dab1191c4e · report
dslisleedh/NAFNet-tensorflow2 community (archive-listed) 1 sample, 0 ran · 1 unverified
NAFNet model.py unverified no licence file found · pointer only · 71e9dde3df3073c4 · report
rflepp/efficient_mobile_denoising_models community (archive-listed) 4 samples, 3 ran (1 instrument-failed) · 1 unverified
DYNUnet models/Dynamic_PlainNet.py ran licence not identified · pointer only · 6b743630418d829e · report fixture: signature input_shape:tuple/1/NoneType, enc_blocks:list/1/int, dec_blocks:list/1/int, bottom_layers:int/0/int, num_filters:int/0/int · returned Functional · level recorded 2026-09-22
PixelShuffle models/Dynamic_PlainNet.py ran licence not identified · pointer only · a6c8a89b84e34837 · report fixture: returned PixelShuffle · level recorded 2026-09-22
upconv_concat models/Dynamic_PlainNet.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · f73610cd536dfe73 · report fixture: signature net:EagerTensor/4/float, tensor_concat:EagerTensor/4/float, filters:int/0/int · returned EagerTensor · level recorded 2026-09-22
double_conv in 16 papers models/Dynamic_PlainNet.py unverified licence not identified · pointer only · 9d1741e20a9e38f5 · report
Thehunk1206/Image-Restorers community (archive-listed) 1 sample, 0 ran · 1 unverified
NAFnet models/archs/naf_net.py unverified MIT (permissive) · 913b39408baa4210 · report
lime-j/nafnet-jax community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
NAFBlock in 5 papers nafnet/models.py ran · metamorphic tier: deterministic no licence file found · pointer only · ea0be350b35c3e6e · report fixture: returned NAFBlock · level recorded 2026-09-22
NAFNet nafnet/models.py ran · metamorphic tier: deterministic no licence file found · pointer only · c1fd5bcc1ef3945c · report fixture: returned NAFNet · level recorded 2026-09-22
PixelShuffle nafnet/models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 2650084eb63ee78b · report fixture: returned PixelShuffle · level recorded 2026-09-22
SimpleAttention nafnet/models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 9817ec8782366e50 · report fixture: returned SimpleAttention · level recorded 2026-09-22
GlobalAvgPool2D nafnet/models.py unverified no licence file found · pointer only · 877c91a4cf4c1ce4 · report
SimpleGate nafnet/models.py unverified no licence file found · pointer only · 95df3ed7752edb6b · report
murufeng/FUIR community (archive-listed) 12 samples, 11 ran (8 instrument-failed) · 1 unverified
calculate_fid in 26 papers basicsr/metrics/fid.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 1d7ce6d6dd7ff5c1 · report fixture: signature mu1:ndarray/1/float, sigma1:ndarray/2/float, mu2:ndarray/1/float, sigma2:ndarray/2/float, eps:float/0/float · returned float64 · level recorded 2026-09-24
compute_feature in 10 papers basicsr/metrics/niqe.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 5170ff1c4106b27a · report fixture: signature block:ndarray/2/float · returned list · level recorded 2026-09-24
conv in 178 papers basicsr/models/archs/MIRNet_arch.py ran · our draft was wrong Apache-2.0 (permissive) · 013ca1b768620edd · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, bias:bool/0/bool, padding:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
conv in 178 papers basicsr/models/archs/HINet_arch.py ran · our draft was wrong Apache-2.0 (permissive) · ad4c565716dab068 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, bias:bool/0/bool, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
conv3x3 in 1,376 papers basicsr/models/archs/HINet_arch.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 822614ced2dcad7a · report fixture: signature in_chn:int/0/int, out_chn:int/0/int, bias:bool/0/bool · returned Conv2d · level recorded 2026-09-22
conv_down basicsr/models/archs/HINet_arch.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 9c428010a12468a3 · report fixture: signature in_chn:int/0/int, out_chn:int/0/int, bias:bool/0/bool · returned Conv2d · level recorded 2026-09-22
estimate_aggd_param in 9 papers basicsr/metrics/niqe.py ran · honoured contract Apache-2.0 (permissive) · a1282a48b0941f5d · report fixture: signature block:ndarray/2/float · returned tuple · level recorded 2026-09-24
extract_inception_features in 9 papers basicsr/metrics/fid.py ran Apache-2.0 (permissive) · c9fb213c957dc82d · report fixture: signature data_generator:generator/0/?, inception:callable/0/?, len_generator:int/0/int, device:str/0/str · returned Tensor · level recorded 2026-09-24
get_position_from_periods in 59 papers basicsr/models/lr_scheduler.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · cd569444547de84f · report fixture: signature iteration:int/0/int, cumulative_period:list/1/int · returned int · level recorded 2026-09-24
prepare_for_ssim in 9 papers basicsr/metrics/psnr_ssim.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 95c6eba9350a455a · report fixture: signature img:ndarray/2/float, k:int/0/int · returned ndarray · level recorded 2026-09-24
reorder_image in 18 papers basicsr/metrics/metric_util.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) here; the stored copy is pointer only · 95067518dc16b3e5 · report fixture: signature img:ndarray/3/int, input_order:str/0/str · returned ndarray · level recorded 2026-09-24
niqe in 9 papers basicsr/metrics/niqe.py unverified Apache-2.0 (permissive) · 0029cb1566e47350 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

8 assemblies on this paper: 8 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

8 sibling assemblies for NAFNet (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for NAFNet (graph method: NAFNet). 6 bricks; individually on a fixture: 4 ran (of which 4 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) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 8 siblings

  1. NAFNet entry · level 1 · ran · c1fd5bcc1ef3945c
  2. NAFBlock model · level 1 · ran · ea0be350b35c3e6e
  3. PixelShuffle helper · level 1 · ran · 2650084eb63ee78b
  4. SimpleAttention helper · level 1 · ran · 9817ec8782366e50
  5. SimpleGate helper · level 0 · unverified · 95df3ed7752edb6b
  6. GlobalAvgPool2D helper · level 0 · unverified · 877c91a4cf4c1ce4

harvested Assembly for NAFNet (graph method: NAFNet). 4 bricks; individually on a fixture: 4 ran (of which 3 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) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. NAFNet entry · level 1 · ran · 2dd382ce15e8576d
  2. NAFBlock model · level 1 · ran · aa1fe0a698ddd646
  3. LayerNorm helper · level 1 · ran · f5fbdad1df60c363
  4. SimpleGate model · level 1 · ran · 488d68589ba5c45e

harvested Assembly for NAFNet (graph method: NAFNet). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. NAFNet entry · level 0 · unverified · 71e9dde3df3073c4

harvested Assembly for NAFNet (graph method: NAFNet). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. NAFnet entry · level 0 · unverified · 913b39408baa4210

harvested Assembly for NAFNet (graph method: NAFNet). 4 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. DYNUnet entry · level 1 · ran · 6b743630418d829e
  2. double_conv model · level 0 · unverified · 9d1741e20a9e38f5
  3. upconv_concat model · level 1 · ran; the contract check could not run (RAISES) · f73610cd536dfe73
  4. PixelShuffle helper · level 1 · ran · a6c8a89b84e34837

harvested Assembly for NAFNet (graph method: NAFNet). 4 bricks; individually on a fixture: 4 ran (of which 3 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) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. Baseline entry · level 1 · ran · 6ce5b700c75ef796
  2. BaselineBlock helper · level 1 · ran · 1a0ca651efcee9e4
  3. LayerNorm2d helper · level 1 · ran · 26e0e3b2df966dee
  4. LayerNormFunction helper · level 1 · ran · e0c7c3f6540a28db

harvested Assembly for NAFNet (graph method: NAFNet). 5 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. NAFNet entry · level 1 · ran · b1bd781b7fd93162
  2. NAFBlock model · level 1 · ran · 359c5485e870e3e6
  3. LayerNorm2d helper · level 1 · ran · 26e0e3b2df966dee
  4. SimpleGate helper · level 1 · ran · 488d68589ba5c45e
  5. LayerNormFunction helper · level 1 · ran · e0c7c3f6540a28db

harvested Assembly for NAFNet (graph method: NAFNet). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. NAFNet entry · level 0 · unverified · 11a0e1dab1191c4e

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2204.04676") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DeblurringDenoisingImage DeblurringImage DenoisingImage RestorationSingle Image Desnowing

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Deblurring GoPro NAFNet PSNR 33.69 #14 of 56 Archive leaderboard report
Deblurring GoPro NAFNet SSIM 0.967 #14 of 56 Archive leaderboard report
Deblurring MSU BASED NAFNet (REDS) ERQAv2.0 0.74508 #1 of 11 Archive leaderboard report
Deblurring MSU BASED NAFNet (REDS) LPIPS 0.08561 #1 of 11 Archive leaderboard report
Deblurring MSU BASED NAFNet (REDS) PSNR 30.54803 #1 of 11 Archive leaderboard report
Deblurring MSU BASED NAFNet (REDS) SSIM 0.95035 #1 of 11 Archive leaderboard report
Deblurring MSU BASED NAFNet (REDS) Subjective 2.8405 #1 of 11 Archive leaderboard report
Deblurring MSU BASED NAFNet (REDS) VMAF 66.85941 #1 of 11 Archive leaderboard report
Image Deblurring GoPro NAFNet - TLC PSNR 33.69 #18 of 55 Archive leaderboard report
Image Deblurring GoPro NAFNet - TLC Params (M) 67.89 #18 of 55 Archive leaderboard report
Image Deblurring GoPro NAFNet - TLC SSIM 0.967 #18 of 55 Archive leaderboard report
Image Denoising SIDD NAFNet PSNR (sRGB) 40.30 #3 of 22 Archive leaderboard report
Image Denoising SIDD NAFNet SSIM (sRGB) 0.961 #3 of 22 Archive leaderboard report
Image Restoration CDD-11 NAFNet Average PSNR (dB) 24.13 #11 of 14 Archive leaderboard report
Image Restoration CDD-11 NAFNet SSIM 0.7964 #11 of 14 Archive leaderboard report
Single Image Desnowing CSD NAFNet Average PSNR (dB) 35.13 #4 of 6 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

NAFNetSoftmax

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