Papers › SwinIR: Image Restoration Using Swin Transformer

SwinIR: Image Restoration Using Swin Transformer

23 Aug 2021arXiv:2108.10257archive 2025-07-28

Jingyun Liang, JieZhang Cao, Guolei Sun, Kai Zhang, Luc van Gool, Radu Timofte

Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). While state-of-the-art image restoration methods are based on convolutional neural networks, few attempts have been made with Transformers which show impressive performance on high-level vision tasks. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image reconstruction. In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection. We conduct experiments on three representative tasks: image super-resolution (including classical, lightweight and real-world image super-resolution), image denoising (including grayscale and color image denoising) and JPEG compression artifact reduction. Experimental results demonstrate that SwinIR outperforms state-of-the-art methods on different tasks by up to 0.14∼0.45dB, while the total number of parameters can be reduced by up to 67%.

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 45 code samples harvested from 6 repositories linked to this paper: 30 ran (of which 14 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 14 where Syntology's instrument failed) · 15 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 7 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 3 ran (0 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 40 samples from 5 repositories, 27 ran (16 with no instrument failure; 11 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.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

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. 2 of the 30 samples that ran have no recorded date.

jingyunliang/swinir officialmentioned in papermentioned on GitHubpytorchSyntology: 5 samples, 3 ran (3 instrument-failed) · 2 unverified report
ayanglab/swinganmr mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (arXiv:2103.14030; that paper's own run record: 123 ran (of which 45 constructed an object rather than computing a result; 79 with no instrument failure: 6 honoured, 3 violated, 70 with no contract checked; 44 where Syntology's instrument failed) · 84 unverified); nothing checks that they implement this paper's method. report
ayanglab/swinmr mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Swin Transformer for Fast MRI (arXiv:2201.03230; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
jingyunliang/vrt mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to VRT: A Video Restoration Transformer (arXiv:2201.12288; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mv-lab/swin2sr mentioned on GitHubpytorchSyntology: 12 samples, 8 ran (3 instrument-failed) · 4 unverified report
rami0205/ngramswin mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
skchen1993/SwinIR mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
XPixelGroup/BasicSR pytorchSyntology: 12 samples, 7 ran (5 instrument-failed) · 5 unverified report
pilot7747/sldl pytorchSyntology: 12 samples, 10 ran (2 instrument-failed) · 2 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

45 samples harvested: 30 ran (of which 14 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 14 where Syntology's instrument failed) · 15 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 · our draft was wrong
7ran; the contract check could not run
16ran
15unverified

Licence: 5 of the 45 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 6 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. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another 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 5 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.

jingyunliang/swinir official repository 5 samples, 3 ran (3 instrument-failed) · 2 unverified
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/network_swinir.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence of this copy not recorded · 144d10b49baeb8a6 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded, date not recorded
setup in 24 papers main_test_swinir.py ran · our draft was wrong Apache-2.0 (permissive) · 31b521c272528885 · report fixture: signature args:Args/0/? · returned tuple · level recorded 2026-09-22
window_reverse in 296 papers models/network_swinir.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 61bf152e6a42a184 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded, date not recorded
RSTB in 9 papers models/network_swinir.py unverified Apache-2.0 (permissive) · 13721b7fb0c3449e · report
SwinIR models/network_swinir.py unverified Apache-2.0 (permissive) · a8c3f25f547b1cd4 · report
mv-lab/swin2sr community (archive-listed) 12 samples, 8 ran (3 instrument-failed) · 4 unverified
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
models/network_swin2sr.py ran fingerprinted Apache-2.0 (permissive) · f1109f9b1b73dca7 · report fixture: returned PatchEmbed · level recorded 2026-09-22
PatchUnEmbed in 15 papers models/network_swin2sr.py ran Apache-2.0 (permissive) · 926e8d276bb28da7 · report fixture: returned PatchUnEmbed · level recorded 2026-09-22
UpsampleOneStep in 9 papers models/network_swin2sr.py ran Apache-2.0 (permissive) · ffe7885c0403a8ad · report fixture: returned UpsampleOneStep · level recorded 2026-09-22
Upsample_hf models/network_swin2sr.py ran Apache-2.0 (permissive) · d32e066d4cc1a4ce · report fixture: returned Upsample_hf · level recorded 2026-09-22
WindowAttention in 50 papers models/network_swin2sr.py ran Apache-2.0 (permissive) · 0b773949f1dbd046 · report fixture: returned WindowAttention · level recorded 2026-09-22
setup in 24 papers main_test_swin2sr.py ran · our draft was wrong Apache-2.0 (permissive) · c1dd0848500dd803 · report fixture: signature args:Args/0/? · returned tuple · level recorded 2026-09-22
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/network_swin2sr.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · f9fd6241d935f07b · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers models/network_swin2sr.py ran · our draft was wrong Apache-2.0 (permissive) · fb32094c6dbece71 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
BasicLayer in 56 papers models/network_swin2sr.py unverified Apache-2.0 (permissive) · 4b45c8b3f6e06e21 · report
RSTB in 9 papers models/network_swin2sr.py unverified Apache-2.0 (permissive) · 5b79ebccea629915 · report
Swin2SR models/network_swin2sr.py unverified Apache-2.0 (permissive) · eeeeae50440c5756 · report
SwinTransformerBlock in 35 papers models/network_swin2sr.py unverified Apache-2.0 (permissive) · f09171fe10737272 · report
rami0205/ngramswin community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
my_model/ngswin_model/win_partition.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 2e2b1611530d7466 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned tuple · level recorded 2026-09-22
skchen1993/SwinIR community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
RSTB in 9 papers models/network_swinir.py ran no licence file found · pointer only · c9ad6c972cd89083 · report fixture: returned RSTB · level recorded 2026-09-22
BasicLayer in 56 papers models/network_swinir.py unverified no licence file found · pointer only · c0fa116516c7281e · report
SwinIR models/network_swinir.py unverified no licence file found · pointer only · d59939ffe142f76f · report
XPixelGroup/BasicSR community (archive-listed) 12 samples, 7 ran (5 instrument-failed) · 5 unverified
PatchUnEmbed in 15 papers basicsr/archs/swinir_arch.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 1ca0dd483faa6682 · report fixture: signature x:Tensor/3/float, x_size:tuple/1/int · returned Tensor · level recorded 2026-09-22
WindowAttention in 50 papers basicsr/archs/swinir_arch.py ran Apache-2.0 (permissive) · a79acfc7f5245c04 · report fixture: signature x:Tensor/3/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
_no_grad_trunc_normal_ in 16 papers
census: 16 implementations from 16 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
basicsr/archs/swinir_arch.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · c30c007e9c6365e0 · report fixture: signature tensor:Tensor/2/float, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float · returned Tensor · level recorded 2026-09-22
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
basicsr/archs/swinir_arch.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 52d96aa31ed74a56 · report fixture: signature x:Tensor/4/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
trunc_normal_ in 154 papers
census: 37 implementations from 54 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
basicsr/archs/swinir_arch.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 0af416f19e3851c1 · report fixture: signature tensor:Tensor/2/float, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float · returned Tensor · level recorded 2026-09-22
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
basicsr/archs/swinir_arch.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 60363d0620f5778d · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers basicsr/archs/swinir_arch.py ran · our draft was wrong Apache-2.0 (permissive) · 4f003e9ad9b7a7cb · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, h:int/0/int, w:int/0/int · returned Tensor · level recorded 2026-09-22
BasicLayer in 56 papers basicsr/archs/swinir_arch.py unverified Apache-2.0 (permissive) · b03980f33707e7ed · report
RSTB in 9 papers basicsr/archs/swinir_arch.py unverified Apache-2.0 (permissive) · f56a662c7641524f · report
SwinIR basicsr/archs/swinir_arch.py unverified Apache-2.0 (permissive) · b6fd49729a87480e · report
SwinTransformerBlock in 35 papers basicsr/archs/swinir_arch.py unverified Apache-2.0 (permissive) · 16d322e629d07ccc · report
pilot7747/sldl community (archive-listed) 12 samples, 10 ran (2 instrument-failed) · 2 unverified
Mlp in 102 papers sldl/image/swinir.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 9b7e99667d6f97b5 · report fixture: returned Mlp · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
sldl/image/swinir.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · c3d1df420e59f005 · report fixture: returned PatchEmbed · level recorded 2026-09-22
PatchUnEmbed in 15 papers sldl/image/swinir.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 2d3ebe5f83f401e2 · report fixture: returned PatchUnEmbed · level recorded 2026-09-22
RSTB in 9 papers sldl/image/swinir.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 83d329df57a93e38 · report fixture: returned RSTB · level recorded 2026-09-22
SwinIR sldl/image/swinir.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 15fea014fc69f0c6 · report fixture: returned SwinIR · level recorded 2026-09-22
Upsample in 77 papers sldl/image/swinir.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · d4fd867e299aa381 · report fixture: returned Upsample · level recorded 2026-09-22
UpsampleOneStep in 9 papers sldl/image/swinir.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 66093c479a99786e · report fixture: returned UpsampleOneStep · level recorded 2026-09-22
WindowAttention in 50 papers sldl/image/swinir.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 6184e406e3b12051 · report fixture: returned WindowAttention · level recorded 2026-09-22
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
sldl/image/swinir.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · def274ea4faeed8e · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers sldl/image/swinir.py ran · our draft was wrong Apache-2.0 (permissive) · f424ec76ee33ee41 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
BasicLayer in 56 papers sldl/image/swinir.py unverified Apache-2.0 (permissive) · b8c4b72467b45853 · report
SwinTransformerBlock in 35 papers sldl/image/swinir.py unverified Apache-2.0 (permissive) · 21b564ba0365248a · 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 SwinIR (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for SwinIR (graph method: SwinIR). 12 bricks; individually on a fixture: 10 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; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. SwinIR entry · level 1 · ran · 15fea014fc69f0c6
  2. PatchEmbed model · level 1 · ran · c3d1df420e59f005
  3. PatchUnEmbed model · level 1 · ran · 2d3ebe5f83f401e2
  4. RSTB model · level 1 · ran · 83d329df57a93e38
  5. Upsample model · level 1 · ran · d4fd867e299aa381
  6. UpsampleOneStep model · level 1 · ran · 66093c479a99786e
  7. BasicLayer model · level 0 · unverified · b8c4b72467b45853
  8. SwinTransformerBlock model · level 0 · unverified · 21b564ba0365248a
  9. Mlp helper · level 1 · ran · 9b7e99667d6f97b5
  10. WindowAttention model · level 1 · ran · 6184e406e3b12051
  11. window_partition helper · level 1 · ran; the contract check could not run (RAISES) · def274ea4faeed8e
  12. window_reverse helper · level 1 · ran · our draft was wrong · f424ec76ee33ee41

harvested Assembly for SwinIR (graph method: SwinIR). 13 bricks; individually on a fixture: 9 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. Swin2SR entry · level 0 · unverified · eeeeae50440c5756
  2. PatchEmbed model · level 1 · ran · f1109f9b1b73dca7
  3. PatchUnEmbed model · level 1 · ran · 926e8d276bb28da7
  4. RSTB model · level 0 · unverified · 5b79ebccea629915
  5. Upsample model · level 1 · ran · ed05c8ce2b7bd1c7
  6. UpsampleOneStep model · level 1 · ran · ffe7885c0403a8ad
  7. Upsample_hf model · level 1 · ran · d32e066d4cc1a4ce
  8. BasicLayer model · level 0 · unverified · 4b45c8b3f6e06e21
  9. SwinTransformerBlock model · level 0 · unverified · f09171fe10737272
  10. Mlp helper · level 1 · ran · a1715055832f71fd
  11. WindowAttention model · level 1 · ran · 0b773949f1dbd046
  12. window_partition helper · level 1 · ran; the contract check could not run (RAISES) · f9fd6241d935f07b
  13. window_reverse helper · level 1 · ran · our draft was wrong · fb32094c6dbece71

harvested Assembly for SwinIR (graph method: SwinIR). 12 bricks; individually on a fixture: 9 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 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. SwinIR entry · level 0 · unverified · d59939ffe142f76f
  2. PatchEmbed helper · level 1 · ran · 4f9f06f42470582c
  3. PatchUnEmbed helper · level 1 · ran · 926e8d276bb28da7
  4. RSTB helper · level 1 · ran · c9ad6c972cd89083
  5. Upsample helper · level 1 · ran · ed05c8ce2b7bd1c7
  6. UpsampleOneStep helper · level 1 · ran · ffe7885c0403a8ad
  7. BasicLayer helper · level 0 · unverified · c0fa116516c7281e
  8. SwinTransformerBlock helper · level 0 · unverified · fc7e70cd159637ab
  9. Mlp helper · level 1 · ran · a1715055832f71fd
  10. WindowAttention helper · level 1 · ran · f9d5ef7b9fad38f8
  11. window_partition helper · level 2 · ran; the contract check could not run (RAISES) · 144d10b49baeb8a6
  12. window_reverse helper · level 1 · ran · our draft was wrong · 61bf152e6a42a184

harvested Assembly for SwinIR (graph method: SwinIR). 12 bricks; individually on a fixture: 8 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. SwinIR entry · level 0 · unverified · a8c3f25f547b1cd4
  2. PatchEmbed model · level 1 · ran · 4f9f06f42470582c
  3. PatchUnEmbed model · level 1 · ran · 926e8d276bb28da7
  4. RSTB model · level 0 · unverified · 13721b7fb0c3449e
  5. Upsample model · level 1 · ran · ed05c8ce2b7bd1c7
  6. UpsampleOneStep model · level 1 · ran · ffe7885c0403a8ad
  7. BasicLayer model · level 0 · unverified · 9b96895c7f3abd02
  8. SwinTransformerBlock model · level 0 · unverified · fc7e70cd159637ab
  9. Mlp helper · level 1 · ran · a1715055832f71fd
  10. WindowAttention model · level 1 · ran · f9d5ef7b9fad38f8
  11. window_partition helper · level 2 · ran; the contract check could not run (RAISES) · 144d10b49baeb8a6
  12. window_reverse helper · level 1 · ran · our draft was wrong · 61bf152e6a42a184

harvested Assembly for SwinIR (graph method: SwinIR). 18 bricks; individually on a fixture: 13 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; 6 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. SwinIR entry · level 0 · unverified · b6fd49729a87480e
  2. PatchEmbed helper · level 0 · unverified · 0ad2bdf7da7fee45
  3. PatchUnEmbed helper · level 1 · ran · 1ca0dd483faa6682
  4. RSTB helper · level 0 · unverified · f56a662c7641524f
  5. Upsample helper · level 1 · ran · ed05c8ce2b7bd1c7
  6. UpsampleOneStep helper · level 1 · ran · 1d46d5b0b06b85ea
  7. trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) · 0af416f19e3851c1
  8. BasicLayer helper · level 0 · unverified · b03980f33707e7ed
  9. drop_path helper · level 1 · ran; the contract check could not run (RAISES) · 52d96aa31ed74a56
  10. _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) · c30c007e9c6365e0
  11. SwinTransformerBlock helper · level 0 · unverified · 16d322e629d07ccc
  12. DropPath helper · level 1 · ran · 2c28ad5498af1d70
  13. Mlp helper · level 1 · ran · a1715055832f71fd
  14. WindowAttention helper · level 1 · ran · a79acfc7f5245c04
  15. window_partition helper · level 1 · ran; the contract check could not run (RAISES) · 60363d0620f5778d
  16. window_reverse helper · level 1 · ran · our draft was wrong · 4f003e9ad9b7a7cb
  17. Registry helper · level 1 · ran · ed2e0002a150698b
  18. _ntuple helper · level 1 · ran · our draft was wrong · 019554bbb3a9809d

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="2108.10257") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Color Image DenoisingDenoisingGrayscale Image DenoisingImage DenoisingImage ReconstructionImage RestorationImage Super-ResolutionJpeg Compression Artifact ReductionSuper-ResolutionVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Color Image Denoising Kodak24 sigma50 SwinIR PSNR 29.79 #6 of 9 Archive leaderboard report
Color Image Denoising Urban100 sigma10 SwinIR PSNR 35.13 #2 of 2 Archive leaderboard report
Color Image Denoising Urban100 sigma25 SwinIR PSNR 32.9 #5 of 6 Archive leaderboard report
Color Image Denoising Urban100 sigma50 SwinIR PSNR 29.82 #6 of 9 Archive leaderboard report
Color Image Denoising urban100 sigma15 SwinIR Average PSNR 35.13 #5 of 8 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma15 SwinIR PSNR 31.97 #3 of 16 Archive leaderboard report
Grayscale Image Denoising Urban100 sigma15 SwinIR PSNR 33.70 #2 of 7 Archive leaderboard report
Grayscale Image Denoising Urban100 sigma25 SwinIR PSNR 31.3 #5 of 10 Archive leaderboard report
Grayscale Image Denoising Urban100 sigma50 SwinIR PSNR 27.98 #5 of 10 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling SwinIR PSNR 32.22 #16 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling SwinIR SSIM 0.9273 #16 of 50 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling SwinIR PSNR 29.15 #22 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling SwinIR SSIM 0.7958 #22 of 104 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling SwinIR PSNR 27.45 #15 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling SwinIR SSIM 0.8254 #15 of 65 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + x264 BSQ-rate over ERQA 0.76 #3 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + x264 BSQ-rate over LPIPS 0.559 #3 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + x264 BSQ-rate over MS-SSIM 0.736 #3 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + x264 BSQ-rate over PSNR 6.268 #3 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + x264 BSQ-rate over Subjective Score 0.304 #3 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + x264 BSQ-rate over VMAF 0.642 #3 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + x265 BSQ-rate over ERQA 1.575 #5 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + x265 BSQ-rate over LPIPS 1.474 #5 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + x265 BSQ-rate over MS-SSIM 4.641 #5 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + x265 BSQ-rate over PSNR 8.13 #5 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + x265 BSQ-rate over Subjective Score 0.346 #5 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + x265 BSQ-rate over VMAF 1.304 #5 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + uavs3e BSQ-rate over ERQA 6.803 #9 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + uavs3e BSQ-rate over LPIPS 1.671 #9 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + uavs3e BSQ-rate over MS-SSIM 4.411 #9 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + uavs3e BSQ-rate over PSNR 15.144 #9 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + uavs3e BSQ-rate over Subjective Score 0.639 #9 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + uavs3e BSQ-rate over VMAF 1.848 #9 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + aomenc BSQ-rate over ERQA 10.854 #14 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + aomenc BSQ-rate over LPIPS 4.566 #14 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + aomenc BSQ-rate over MS-SSIM 7.105 #14 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + aomenc BSQ-rate over PSNR 15.144 #14 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + aomenc BSQ-rate over Subjective Score 0.835 #14 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + aomenc BSQ-rate over VMAF 3.32 #14 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + vvenc BSQ-rate over ERQA 6.624 #20 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + vvenc BSQ-rate over LPIPS 1.552 #20 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + vvenc BSQ-rate over MS-SSIM 5.758 #20 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + vvenc BSQ-rate over PSNR 8.971 #20 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + vvenc BSQ-rate over Subjective Score 1.35 #20 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression SwinIR + vvenc BSQ-rate over VMAF 0.887 #20 of 85 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration SwinIR 1 - LPIPS 0.895 #23 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration SwinIR ERQAv1.0 0.618 #23 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration SwinIR FPS 0.407 #23 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration SwinIR PSNR 25.12 #23 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration SwinIR QRCRv1.0 0 #23 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration SwinIR SSIM 0.782 #23 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration SwinIR Subjective score 4.799 #23 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement SwinIR-Real-B LPIPS 0.183 #4 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement SwinIR-Real-B PSNR 28.86 #4 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement SwinIR-Real-B SSIM 0.830 #4 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement SwinIR-Real-S LPIPS 0.189 #7 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement SwinIR-Real-S PSNR 28.55 #7 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement SwinIR-Real-S SSIM 0.845 #7 of 48 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxStochastic DepthSwin TransformerTransformer

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