Papers › Plug-and-Play Image Restoration with Deep Denoiser Prior

Plug-and-Play Image Restoration with Deep Denoiser Prior

31 Aug 2020arXiv:2008.13751archive 2025-07-28

Kai Zhang, Yawei Li, WangMeng Zuo, Lei Zhang, Luc van Gool, Radu Timofte

Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems. Such a property induces considerable advantages for plug-and-play image restoration (e.g., integrating the flexibility of model-based method and effectiveness of learning-based methods) when the denoiser is discriminatively learned via deep convolutional neural network (CNN) with large modeling capacity. However, while deeper and larger CNN models are rapidly gaining popularity, existing plug-and-play image restoration hinders its performance due to the lack of suitable denoiser prior. In order to push the limits of plug-and-play image restoration, we set up a benchmark deep denoiser prior by training a highly flexible and effective CNN denoiser. We then plug the deep denoiser prior as a modular part into a half quadratic splitting based iterative algorithm to solve various image restoration problems. We, meanwhile, provide a thorough analysis of parameter setting, intermediate results and empirical convergence to better understand the working mechanism. Experimental results on three representative image restoration tasks, including deblurring, super-resolution and demosaicing, demonstrate that the proposed plug-and-play image restoration with deep denoiser prior not only significantly outperforms other state-of-the-art model-based methods but also achieves competitive or even superior performance against state-of-the-art learning-based methods. The source code is available at https://github.com/cszn/DPIR.

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 28 code samples harvested from 3 repositories linked to this paper: 18 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; 2 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 5 ran (3 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 23 samples from 2 repositories, 13 ran (13 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 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.

cszn/DPIR officialmentioned in papermentioned on GitHubpytorchMITSyntology: 5 samples, 5 ran (2 instrument-failed) · 0 unverified report
HedgehogCode/deep-plug-and-play-prior mentioned on GitHubtfMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
HedgehogCode/denoising-gan mentioned on GitHubtfMITSyntology: 19 samples, 10 ran (0 instrument-failed) · 9 unverified report
jihoojo03/UNet-CBAM_Keras mentioned on GitHubSyntology: 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

28 samples harvested: 18 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; 2 where Syntology's instrument failed) · 10 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 · our draft was wrong
16ran
10unverified

Licence: 3 of the 28 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 3 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.

cszn/DPIR official repository 5 samples, 5 ran (2 instrument-failed) · 0 unverified
conv in 178 papers models/basicblock.py ran · our draft was wrong MIT (permissive) · 0bb3503f833a6f8e · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, bias:bool/0/bool, mode:str/0/str, negative_slope:float/0/float · returned Sequential · level recorded 2026-09-22
pixel_unshuffle in 15 papers
census: 4 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
models/basicblock.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · e84da58ba9736585 · report fixture: signature input:Tensor/4/float, upscale_factor:int/0/int · returned Tensor · level recorded 2026-09-25
test in 377 papers utils/utils_model.py ran MIT (permissive) here; the stored copy is pointer only · 8afaf26fe2391d00 · report fixture: signature model:callable/0/?, L:Tensor/2/float · returned Tensor · level recorded 2026-09-24
test_pad utils/utils_model.py ran MIT (permissive) · 54f9c2acc0385e32 · report fixture: signature model:callable/0/?, L:Tensor/4/float, modulo:int/0/int · returned Tensor · level recorded 2026-09-25
upsample_pixelshuffle in 12 papers models/basicblock.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 1e826b826044c581 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, bias:bool/0/bool, mode:str/0/str, negative_slope:float/0/float · returned Sequential · level recorded 2026-09-24
HedgehogCode/deep-plug-and-play-prior community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
blur in 13 papers dppp/utils.py ran MIT (permissive) · a61cd181f14e6225 · report fixture: signature image:EagerTensor/4/float, kernel:EagerTensor/4/float, noise_stddev:float/0/float, mode:str/0/str, clip_final:bool/0/bool · returned EagerTensor · level recorded 2026-09-24
conv2D_filter_rgb dppp/utils.py ran MIT (permissive) · c46741143221e8c5 · report fixture: signature kernel:SymbolicTensor/2/float · returned EagerTensor · level recorded 2026-09-24
psnr in 88 papers
census: 9 implementations from 11 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
dppp/metrics.py ran MIT (permissive) · 1fe398ceae86d475 · report fixture: signature imgs_a:EagerTensor/4/float, imgs_b:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-24
ssim in 112 papers dppp/metrics.py unverified MIT (permissive) · 06800f3dd30271e0 · report
HedgehogCode/denoising-gan community (archive-listed) 19 samples, 10 ran (0 instrument-failed) · 9 unverified
apply_debug utils.py ran MIT (permissive) · 04bc984d219b19d0 · report fixture: signature config:dict/0/?, debug:bool/0/bool, dae:bool/0/bool · returned dict · level recorded 2026-09-24
dataset_filter evaluate.py ran MIT (permissive) · 39275635df4360a4 · report fixture: signature k:str/0/str · returned bool · level recorded 2026-09-24
degrade_filter evaluate.py ran MIT (permissive) · e625483ff10107d2 · report fixture: signature k:str/0/str · returned bool · level recorded 2026-09-24
disc_loss_clean dngan/losses.py ran MIT (permissive) · da6637e84b3f0f4c · report fixture: signature output_clean:EagerTensor/2/float, output_gen:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-24
dncnn_generator dngan/generator.py ran MIT (permissive) · 2267eb0d36c5ccaf · report fixture: signature out_channels:int/0/int, num_conv:int/0/int, internal_residuals:bool/0/bool, global_residual:bool/0/bool · returned function · level recorded 2026-09-24
evaluate_test dngan/training.py ran MIT (permissive) · 960754a03da290de · report fixture: signature model:callable/0/?, datasets:dict/0/?, metrics:dict/0/?, summary_prefix:str/0/str · returned tuple · level recorded 2026-09-24
get_from_environ utils.py ran fingerprinted MIT (permissive) · 5c074e16e43103be · report fixture: signature var_name:str/0/str, default_val:str/0/str · returned str · level recorded 2026-09-24
psnr in 88 papers
census: 9 implementations from 11 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
dngan/metrics.py ran MIT (permissive) · 63c3e31a8d2ca736 · report fixture: signature imgs_a:EagerTensor/4/float, imgs_b:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-24
read_config in 49 papers utils.py ran MIT (permissive) · 01a49af5dca2bf0e · report fixture: signature path_to_config:str/0/str · returned dict · level recorded 2026-09-24
residual_block in 18 papers dngan/blocks.py ran MIT (permissive) · 40fa25b27aa11ea8 · report fixture: signature layers:list/1/callable · returned function · level recorded 2026-09-24
conv2d_block dngan/blocks.py unverified MIT (permissive) · f959d134682f93e1 · report
conv2d_encoder dngan/blocks.py unverified MIT (permissive) · b3c94561a1919d7b · report
dncnn_generator_model dngan/generator.py unverified MIT (permissive) · b0287fea83093ef3 · report
evaluate in 514 papers dngan/training.py unverified MIT (permissive) · 164ed0ee1bf2880d · report
ms_ssim in 10 papers dngan/metrics.py unverified MIT (permissive) · c45644bf0bcadf02 · report
parse_args in 355 papers checkpoint_to_h5.py unverified MIT (permissive) · 01f3cd76105ef1fe · report
ssim in 112 papers dngan/metrics.py unverified MIT (permissive) · a45288c1028a27cc · report
vgg19_ba_loss dngan/losses.py unverified MIT (permissive) · c0ea75cc82eb3b38 · report
vgg19_loss dngan/losses.py unverified MIT (permissive) · b4203746b902cc9a · report

Tasks

DeblurringDemosaickingImage RestorationSuper-Resolution

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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