Papers › Multi-Stage Progressive Image Restoration

Multi-Stage Progressive Image Restoration

4 Feb 2021CVPR 2021 1arXiv:2102.02808archive 2025-07-28

Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao

Image restoration tasks demand a complex balance between spatial details and high-level contextualized information while recovering images. In this paper, we propose a novel synergistic design that can optimally balance these competing goals. Our main proposal is a multi-stage architecture, that progressively learns restoration functions for the degraded inputs, thereby breaking down the overall recovery process into more manageable steps. Specifically, our model first learns the contextualized features using encoder-decoder architectures and later combines them with a high-resolution branch that retains local information. At each stage, we introduce a novel per-pixel adaptive design that leverages in-situ supervised attention to reweight the local features. A key ingredient in such a multi-stage architecture is the information exchange between different stages. To this end, we propose a two-faceted approach where the information is not only exchanged sequentially from early to late stages, but lateral connections between feature processing blocks also exist to avoid any loss of information. The resulting tightly interlinked multi-stage architecture, named as MPRNet, delivers strong performance gains on ten datasets across a range of tasks including image deraining, deblurring, and denoising. The source code and pre-trained models are available at https://github.com/swz30/MPRNet.

PaperPDFConference PDFCodeCode 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 26 code samples harvested from 5 repositories linked to this paper: 18 ran (of which 13 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 4 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 22 samples from 4 repositories, 16 ran (15 with no instrument failure; 1 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.

swz30/MPRNet officialmentioned in papermentioned on GitHubpytorchSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
HDCVLab/MC-Blur-Dataset mentioned on GitHubpytorchSyntology: not harvested report
sotiraslab/AgileFormer mentioned on GitHubpytorchSyntology: not harvested report
swz30/CycleISP mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (1 instrument-failed) · 0 unverified report
swz30/MIRNet mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
swz30/mirnetv2 mentioned on GitHubpytorchSyntology: 10 samples, 8 ran (0 instrument-failed) · 2 unverified report
swz30/restormer mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
taowangzj/llformer mentioned on GitHubpytorchNOASSERTIONSyntology: 6 samples, 3 ran (0 instrument-failed) · 3 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

26 samples harvested: 18 ran (of which 13 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 8 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.

1ran · our draft was wrong
17ran
8unverified

Licence: 25 of the 26 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 5 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 10 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. 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.

swz30/MPRNet official repository 4 samples, 2 ran (0 instrument-failed) · 2 unverified
ORB Deblurring/MPRNet.py ran fingerprinted licence not identified · pointer only · 0248b30780d949dc · report fixture: returned ORB · level recorded 2026-09-22
UpSample in 9 papers Deblurring/MPRNet.py ran licence not identified · pointer only · 6f67ba4ae094dbdf · report fixture: returned UpSample · level recorded 2026-09-22
MPRNet Deblurring/MPRNet.py unverified licence not identified · pointer only · f07bf53bd31a377c · report
ORSNet Deblurring/MPRNet.py unverified licence not identified · pointer only · e3f5a4be55c14019 · report
swz30/CycleISP community (archive-listed) 5 samples, 5 ran (1 instrument-failed) · 0 unverified
DAB networks/denoising_rgb.py ran fingerprinted licence not identified · pointer only · fc4aa1da5676f5f6 · report fixture: returned DAB · level recorded 2026-09-22
DenoiseNet networks/denoising_rgb.py ran fingerprinted licence not identified · pointer only · 3803599e00731bf3 · report fixture: returned DenoiseNet · level recorded 2026-09-22
RRG networks/denoising_rgb.py ran fingerprinted licence not identified · pointer only · 69df2e5e6ab1bfad · report fixture: returned RRG · level recorded 2026-09-22
conv in 178 papers networks/denoising_rgb.py ran · our draft was wrong licence not identified · pointer only · dddca40fb4dbccdc · 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
spatial_attn_layer networks/denoising_rgb.py ran fingerprinted licence not identified · pointer only · 55ca1005128011e2 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
swz30/mirnetv2 community (archive-listed) 10 samples, 8 ran (0 instrument-failed) · 2 unverified
ContextBlock basicsr/models/archs/mirnet_v2_arch.py ran fingerprinted licence not identified · pointer only · 9905ed97879ec410 · report fixture: returned ContextBlock · level recorded 2026-09-22
Down in 17 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
basicsr/models/archs/mirnet_v2_arch.py ran fingerprinted licence not identified · pointer only · 95877fdf404e7e2d · report fixture: returned Down · level recorded 2026-09-22
DownSample in 11 papers basicsr/models/archs/mirnet_v2_arch.py ran fingerprinted licence not identified · pointer only · 823880bb4a4fd803 · report fixture: returned DownSample · level recorded 2026-09-22
MRB basicsr/models/archs/mirnet_v2_arch.py ran licence not identified · pointer only · 9f0ec2d0ebd79268 · report fixture: returned MRB · level recorded 2026-09-22
RCB basicsr/models/archs/mirnet_v2_arch.py ran fingerprinted licence not identified · pointer only · 92fe045c36c149b1 · report fixture: returned RCB · level recorded 2026-09-22
SKFF basicsr/models/archs/mirnet_v2_arch.py ran licence not identified · pointer only · cecd263c57a13552 · report fixture: returned SKFF · level recorded 2026-09-22
Up in 24 papers basicsr/models/archs/mirnet_v2_arch.py ran fingerprinted licence not identified · pointer only · 1c8472333e5c2601 · report fixture: returned Up · level recorded 2026-09-22
UpSample in 9 papers basicsr/models/archs/mirnet_v2_arch.py ran fingerprinted licence not identified · pointer only · 7ad799995cd1b005 · report fixture: returned UpSample · level recorded 2026-09-22
MIRNet_v2 basicsr/models/archs/mirnet_v2_arch.py unverified licence not identified · pointer only · e229ec6cd3be0368 · report
RRG basicsr/models/archs/mirnet_v2_arch.py unverified licence not identified · pointer only · ab472a2ed659eb18 · report
swz30/restormer community (archive-listed) 1 sample, 0 ran · 1 unverified
Restormer basicsr/models/archs/restormer_arch.py unverified MIT (permissive) · 266026630c2bfcd7 · report
taowangzj/llformer community (archive-listed) 6 samples, 3 ran (0 instrument-failed) · 3 unverified
FeedForward in 198 papers model/LLFormer.py ran · metamorphic tier: invariant licence not identified · pointer only · 2e4380a675a7a636 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
NextAttentionImplZ model/LLFormer.py ran fingerprinted licence not identified · pointer only · dcfcd2cfc0518597 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
NextAttentionZ model/LLFormer.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · f3c858250a132490 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
LAM_Module_v2 model/LLFormer.py unverified licence not identified · pointer only · df51bfb12d6bab5a · report
LLFormer model/LLFormer.py unverified licence not identified · pointer only · e1acb5598af874ea · report
TransformerBlock in 73 papers model/LLFormer.py unverified licence not identified · pointer only · 2d417e1b35e33481 · 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.

5 assemblies on this paper: 5 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for MPRNet (graph method: MPRNet). 12 bricks; individually on a fixture: 10 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. MPRNet entry · level 0 · unverified · f07bf53bd31a377c
  2. CAB model · level 1 · ran · 678f3130b1d60fa6
  3. Decoder model · level 1 · ran · 51c52bb9f66035a4
  4. Encoder model · level 1 · ran · 3354aabf0ecc8c18
  5. ORSNet model · level 0 · unverified · e3f5a4be55c14019
  6. SAM model · level 1 · ran · 4bf95f287cef1b67
  7. conv helper · level 1 · ran · our draft was wrong · ad4c565716dab068
  8. CALayer helper · level 1 · ran · d487b4aabe9c084e
  9. SkipUpSample model · level 1 · ran · 486b1e7f3f32e75e
  10. DownSample model · level 1 · ran · 45d120cfa343ebec
  11. ORB model · level 1 · ran · 0248b30780d949dc
  12. UpSample model · level 1 · ran · 6f67ba4ae094dbdf

harvested Assembly for MPRNet (graph method: MPRNet). 12 bricks; individually on a fixture: 11 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. Restormer entry · level 0 · unverified · 266026630c2bfcd7
  2. Downsample model · level 1 · ran · 43cd6fa3751bab78
  3. OverlapPatchEmbed model · level 1 · ran · 099f2dc5f59fa05f
  4. TransformerBlock model · level 1 · ran · 543f89fa45313251
  5. Upsample model · level 1 · ran · a334b6b5228fd884
  6. Attention helper · level 1 · ran · 98e962e3944f0fb6
  7. FeedForward helper · level 1 · ran · 479ae430111a6061
  8. LayerNorm helper · level 1 · ran · 7add138148389ff5
  9. BiasFree_LayerNorm helper · level 1 · ran · db9f0e70f3f18049
  10. WithBias_LayerNorm helper · level 1 · ran · 1d90d30671b0d4b8
  11. to_3d helper · level 1 · ran; the contract check could not run · 82a15cc1e46f7e4d
  12. to_4d helper · level 1 · ran; the contract check could not run · b20f2a5df739a59e

harvested Assembly for MPRNet (graph method: MPRNet). 10 bricks; individually on a fixture: 8 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 8 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 5 siblings

  1. MIRNet_v2 entry · level 0 · unverified · e229ec6cd3be0368
  2. RRG model · level 0 · unverified · ab472a2ed659eb18
  3. MRB model · level 1 · ran · 9f0ec2d0ebd79268
  4. DownSample helper · level 1 · ran · 823880bb4a4fd803
  5. RCB helper · level 1 · ran · 92fe045c36c149b1
  6. SKFF helper · level 1 · ran · cecd263c57a13552
  7. UpSample helper · level 1 · ran · 7ad799995cd1b005
  8. Down helper · level 1 · ran · 95877fdf404e7e2d
  9. ContextBlock helper · level 1 · ran · 9905ed97879ec410
  10. Up helper · level 1 · ran · 1c8472333e5c2601

harvested Assembly for MPRNet (graph method: MPRNet). 8 bricks; individually on a fixture: 8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. DenoiseNet entry · level 1 · ran · 3803599e00731bf3
  2. RRG model · level 1 · ran · 69df2e5e6ab1bfad
  3. conv helper · level 1 · ran · our draft was wrong · dddca40fb4dbccdc
  4. DAB model · level 1 · ran · fc4aa1da5676f5f6
  5. CALayer model · level 1 · ran · 0802c53335f5c2fc
  6. spatial_attn_layer model · level 1 · ran · 55ca1005128011e2
  7. BasicConv helper · level 1 · ran · 704f1adafa5b1dc0
  8. ChannelPool helper · level 1 · ran · 436816a2dc1cce55

harvested Assembly for MPRNet (graph method: MPRNet). 14 bricks; individually on a fixture: 11 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. LLFormer entry · level 0 · unverified · e1acb5598af874ea
  2. Downsample model · level 1 · ran · 43cd6fa3751bab78
  3. LAM_Module_v2 model · level 0 · unverified · df51bfb12d6bab5a
  4. OverlapPatchEmbed model · level 1 · ran · 099f2dc5f59fa05f
  5. TransformerBlock model · level 0 · unverified · 2d417e1b35e33481
  6. Upsample model · level 1 · ran · a334b6b5228fd884
  7. FeedForward helper · level 1 · ran · 2e4380a675a7a636
  8. LayerNorm model · level 1 · ran · 7add138148389ff5
  9. NextAttentionZ helper · level 1 · ran · f3c858250a132490
  10. BiasFree_LayerNorm helper · level 1 · ran · db9f0e70f3f18049
  11. WithBias_LayerNorm helper · level 1 · ran · 1d90d30671b0d4b8
  12. to_3d helper · level 1 · ran; the contract check could not run · 82a15cc1e46f7e4d
  13. to_4d helper · level 1 · ran; the contract check could not run · b20f2a5df739a59e
  14. NextAttentionImplZ helper · level 1 · ran · dcfcd2cfc0518597

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="2102.02808") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DeblurringDecoderDenoisingImage DeblurringImage DenoisingImage RestorationRain RemovalSingle Image DerainingSpectral Reconstruction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Deblurring GoPro MPRNet PSNR 32.66 #33 of 56 Archive leaderboard report
Deblurring GoPro MPRNet SSIM 0.959 #33 of 56 Archive leaderboard report
Deblurring HIDE (trained on GOPRO) MPRNet PSNR (sRGB) 30.96 #17 of 26 Archive leaderboard report
Deblurring HIDE (trained on GOPRO) MPRNet Params (M) 20.1 #17 of 26 Archive leaderboard report
Deblurring HIDE (trained on GOPRO) MPRNet SSIM (sRGB) 0.939 #17 of 26 Archive leaderboard report
Deblurring RSBlur MPRNet Average PSNR 33.61 #9 of 12 Archive leaderboard report
Deblurring RealBlur-J MPRNet PSNR (sRGB) 31.76 #15 of 17 Archive leaderboard report
Deblurring RealBlur-J MPRNet Params(M) 20.1 #15 of 17 Archive leaderboard report
Deblurring RealBlur-J MPRNet SSIM (sRGB) 0.922 #15 of 17 Archive leaderboard report
Deblurring RealBlur-J (trained on GoPro) MPRNet PSNR (sRGB) 28.70 #10 of 15 Archive leaderboard report
Deblurring RealBlur-J (trained on GoPro) MPRNet SSIM (sRGB) 0.873 #10 of 15 Archive leaderboard report
Deblurring RealBlur-R MPRNet PSNR (sRGB) 39.31 #14 of 17 Archive leaderboard report
Deblurring RealBlur-R MPRNet SSIM (sRGB) 0.972 #14 of 17 Archive leaderboard report
Deblurring RealBlur-R (trained on GoPro) MPRNet PSNR (sRGB) 35.99 #8 of 19 Archive leaderboard report
Deblurring RealBlur-R (trained on GoPro) MPRNet SSIM (sRGB) 0.952 #8 of 19 Archive leaderboard report
Image Deblurring GoPro MPRNet PSNR 32.66 #34 of 55 Archive leaderboard report
Image Deblurring GoPro MPRNet Params (M) 20.1 #34 of 55 Archive leaderboard report
Image Deblurring GoPro MPRNet SSIM 0.959 #34 of 55 Archive leaderboard report
Image Denoising DND MPRNet PSNR (sRGB) 39.80 #9 of 16 Archive leaderboard report
Image Denoising DND MPRNet SSIM (sRGB) 0.954 #9 of 16 Archive leaderboard report
Image Denoising SIDD MPRNet PSNR (sRGB) 39.71 #12 of 22 Archive leaderboard report
Image Denoising SIDD MPRNet SSIM (sRGB) 0.958 #12 of 22 Archive leaderboard report
Image Restoration CDD-11 MPRNet Average PSNR (dB) 25.47 #9 of 14 Archive leaderboard report
Image Restoration CDD-11 MPRNet SSIM 0.8555 #9 of 14 Archive leaderboard report
Single Image Deraining Rain100H MPRNet PSNR 30.41 #10 of 19 Archive leaderboard report
Single Image Deraining Rain100H MPRNet SSIM 0.89 #10 of 19 Archive leaderboard report
Single Image Deraining Rain100L MPRNet PSNR 36.40 #12 of 19 Archive leaderboard report
Single Image Deraining Rain100L MPRNet SSIM 0.965 #12 of 19 Archive leaderboard report
Single Image Deraining Test100 MPRNet PSNR 30.27 #6 of 12 Archive leaderboard report
Single Image Deraining Test100 MPRNet SSIM 0.897 #6 of 12 Archive leaderboard report
Single Image Deraining Test1200 MPRNet PSNR 32.91 #7 of 14 Archive leaderboard report
Single Image Deraining Test1200 MPRNet SSIM 0.916 #7 of 14 Archive leaderboard report
Single Image Deraining Test2800 MPRNet PSNR 33.64 #5 of 12 Archive leaderboard report
Single Image Deraining Test2800 MPRNet SSIM 0.938 #5 of 12 Archive leaderboard report
Spectral Reconstruction ARAD-1K MPRNet MRAE 0.1817 #3 of 11 Archive leaderboard report
Spectral Reconstruction ARAD-1K MPRNet PSNR 33.50 #3 of 11 Archive leaderboard report
Spectral Reconstruction ARAD-1K MPRNet RMSE 0.0270 #3 of 11 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

Introduced by this paper: MPRNet

MPRNet

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