Papers › AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring

AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring

13 Jun 2024CVPR 2024 1arXiv:2406.09135archive 2025-07-28

Xintian Mao, Qingli Li, Yan Wang

Despite the recent progress in enhancing the efficacy of image deblurring, the limited decoding capability constrains the upper limit of State-Of-The-Art (SOTA) methods. This paper proposes a pioneering work, Adaptive Patch Exiting Reversible Decoder (AdaRevD), to explore their insufficient decoding capability. By inheriting the weights of the well-trained encoder, we refactor a reversible decoder which scales up the single-decoder training to multi-decoder training while remaining GPU memory-friendly. Meanwhile, we show that our reversible structure gradually disentangles high-level degradation degree and low-level blur pattern (residual of the blur image and its sharp counterpart) from compact degradation representation. Besides, due to the spatially-variant motion blur kernels, different blur patches have various deblurring difficulties. We further introduce a classifier to learn the degradation degree of image patches, enabling them to exit at different sub-decoders for speedup. Experiments show that our AdaRevD pushes the limit of image deblurring, e.g., achieving 34.60 dB in PSNR on GoPro dataset.

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 50 code samples harvested from 3 repositories linked to this paper: 36 ran (of which 16 constructed an object rather than computing a result; 27 with no instrument failure: 5 honoured, 2 violated, 20 with no contract checked; 9 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 8 ran (5 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 41 samples from 2 repositories, 28 ran (22 with no instrument failure; 6 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.

INVOKERer/AdaRevD officialpytorchNOASSERTIONSyntology: 9 samples, 8 ran (3 instrument-failed) · 1 unverified report
deepmed-lab-ecnu/single-image-deblur mentioned in papermentioned on GitHubpytorchSyntology: not harvested report
INVOKERer/LoFormer mentioned on GitHubpytorchSyntology: 30 samples, 21 ran (3 instrument-failed) · 9 unverified report
invokerer/deeprft mentioned on GitHubpytorchNOASSERTIONSyntology: 11 samples, 7 ran (3 instrument-failed) · 4 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

50 samples harvested: 36 ran (of which 16 constructed an object rather than computing a result; 27 with no instrument failure: 5 honoured, 2 violated, 20 with no contract checked; 9 where Syntology's instrument failed) · 14 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.

5ran · honoured contract
2ran · violated contract
4ran · our draft was wrong
5ran; the contract check could not run
20ran
14unverified

Licence: 50 of the 50 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 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”. For 9 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.

INVOKERer/AdaRevD official repository 9 samples, 8 ran (3 instrument-failed) · 1 unverified
centering in 17 papers CKA-Centered-Kernel-Alignment/CKA.py ran · honoured contract fingerprinted no licence file found · pointer only · 5c273c526536356d · report fixture: signature K:ndarray/2/float · returned ndarray · level recorded 2026-09-22
centering_torch CKA-Centered-Kernel-Alignment/CKA.py ran · honoured contract fingerprinted licence not identified · pointer only · f2c02d3df4002f2c · report fixture: signature K:Tensor/2/float · returned Tensor · level recorded 2026-09-24
compute_ccas in 7 papers CKA-Centered-Kernel-Alignment/cca_core.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 01472465bed8b268 · report fixture: signature sigma_xx:ndarray/2/float, sigma_xy:ndarray/2/float, sigma_yx:ndarray/2/float, sigma_yy:ndarray/2/float, epsilon:float/0/float, verbose:bool/0/bool · returned tuple · level recorded 2026-09-22
compute_psnr in 30 papers Motion_Deblurring/evaluate_gopro.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · 0564c7d12ea86b30 · report fixture: signature image_true:ndarray/2/int, image_test:ndarray/2/int · returned float64 · level recorded 2026-09-24
get_effective_receptive_field Motion_Deblurring/erf.py ran licence not identified · pointer only · b3204ca67e2d32f4 · report fixture: signature input:Tensor/4/float, output:Tensor/4/float, log:bool/0/bool, grad:int/0/int · returned ndarray · level recorded 2026-09-24
positivedef_matrix_sqrt in 8 papers CKA-Centered-Kernel-Alignment/cca_core.py ran · honoured contract fingerprinted no licence file found · pointer only · ea98389a1755bb3f · report fixture: signature array:ndarray/2/float · returned ndarray · level recorded 2026-09-22
rbf in 19 papers
census: 4 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 3 of 3, arg 1: rank 2, kind float, dtype float64
CKA-Centered-Kernel-Alignment/CKA.py ran · honoured contract fingerprinted no licence file found · pointer only · 0f137cab706f1953 · report fixture: signature X:ndarray/2/float, sigma:NoneType/0/? · returned ndarray · level recorded 2026-09-22
remove_small in 8 papers CKA-Centered-Kernel-Alignment/cca_core.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · ffcbd13c7094948e · report fixture: signature sigma_xx:ndarray/2/float, sigma_xy:ndarray/2/float, sigma_yx:ndarray/2/float, sigma_yy:ndarray/2/float, epsilon:float/0/float · returned tuple · level recorded 2026-09-22
image_align in 8 papers Motion_Deblurring/evaluate_gopro.py unverified licence not identified · pointer only · 5aad1c1e328fd4ec · report
INVOKERer/LoFormer community (archive-listed) 30 samples, 21 ran (3 instrument-failed) · 9 unverified
BatchNorm in 19 papers basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · aa30d63064354a0f · report fixture: returned BatchNorm · level recorded 2026-09-22
Classifier in 72 papers basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 54b4cb2b28654156 · report fixture: returned Classifier · level recorded 2026-09-22
KernelPrior basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic licence not identified · pointer only · 2adab08083a9624a · report fixture: returned KernelPrior · level recorded 2026-09-22
LayerNorm2d in 18 papers basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 26e0e3b2df966dee · report fixture: returned LayerNorm2d · level recorded 2026-09-22
LinearMaskedCoupling basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic licence not identified · pointer only · 3a18b572b6b1e5ad · report fixture: returned LinearMaskedCoupling · level recorded 2026-09-22
NAFBlock in 5 papers basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · ab6a31f934b01390 · report fixture: returned NAFBlock · level recorded 2026-09-22
NAFBlock_kernel basicsr/models/archs/AdaRevID_arch.py ran licence not identified · pointer only · 027f7863abb8f85d · report fixture: returned NAFBlock_kernel · level recorded 2026-09-22
NAFNet basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic licence not identified · pointer only · d033cd39f61aec96 · report fixture: returned NAFNet · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · a5c971c79279e4c9 · report fixture: returned ResBlock · level recorded 2026-09-22
ReverseFunction basicsr/models/archs/AdaRevID_arch.py ran licence not identified · pointer only · 0e436a8df9e0385f · report fixture: returned ReverseFunction · level recorded 2026-09-22
SimpleGate basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 19826953d6d91066 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
code_extra_mean_var basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · d65cc58b327e770c · report fixture: returned code_extra_mean_var · level recorded 2026-09-22
conv_bench basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 5915a0dcd991fd39 · report fixture: returned conv_bench · level recorded 2026-09-22
detach_and_grad basicsr/models/archs/AdaRevID_arch.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 66607a81e9dce986 · report fixture: signature inputs:tuple/1/Tensor · returned tuple · level recorded 2026-09-22
generate_k basicsr/models/archs/AdaRevID_arch.py ran · our draft was wrong licence not identified · pointer only · edcc2d839bbe7b62 · report fixture: signature model:callable/0/?, code:Tensor/2/float, n_row:int/0/int · returned Tensor · level recorded 2026-09-22
get_cpu_and_gpu_states basicsr/models/archs/AdaRevID_arch.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 298ef15d9028ac53 · report fixture: signature gpu_devices:list/1/empty · returned tuple · level recorded 2026-09-22
kernel_attention basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic licence not identified · pointer only · f0c04361fd77de5d · report fixture: returned kernel_attention · level recorded 2026-09-22
kernel_extra_Decoding_Block basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic licence not identified · pointer only · efcbb8d5303a9dde · report fixture: returned kernel_extra_Decoding_Block · level recorded 2026-09-22
kernel_extra_Encoding_Block basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 1c61356d1f70ebdf · report fixture: returned kernel_extra_Encoding_Block · level recorded 2026-09-22
kernel_extra_conv_mid basicsr/models/archs/AdaRevID_arch.py ran fingerprinted licence not identified · pointer only · ff5339d531bd8ec5 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
kernel_extra_conv_tail_mean_var basicsr/models/archs/AdaRevID_arch.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · effbd87d7309d611 · report fixture: returned kernel_extra_conv_tail_mean_var · level recorded 2026-09-22
AdaRevID basicsr/models/archs/AdaRevID_arch.py unverified licence not identified · pointer only · 35c1fb15cf9c2a3c · report
FCNAFBlock basicsr/models/archs/AdaRevID_arch.py unverified licence not identified · pointer only · 719313e70c1ce9cc · report
Fusion_DecoderV1 basicsr/models/archs/AdaRevID_arch.py unverified licence not identified · pointer only · 3fb2ae8418a9650d · report
Level_Decoder basicsr/models/archs/AdaRevID_arch.py unverified licence not identified · pointer only · ad5c1c85d29e898d · report
UFPNet basicsr/models/archs/AdaRevID_arch.py unverified licence not identified · pointer only · 526f252c65b7794a · report
UniDecoder basicsr/models/archs/AdaRevID_arch.py unverified licence not identified · pointer only · f827e2156483181c · report
get_gpu_device basicsr/models/archs/AdaRevID_arch.py unverified licence not identified · pointer only · ba9068d857e12c4d · report
get_gpu_states basicsr/models/archs/AdaRevID_arch.py unverified licence not identified · pointer only · dd9e76dff65e161f · report
set_device_states basicsr/models/archs/AdaRevID_arch.py unverified licence not identified · pointer only · 1d10fd4faaf7d98b · report
invokerer/deeprft community (archive-listed) 11 samples, 7 ran (3 instrument-failed) · 4 unverified
compute_psnr in 30 papers evaluate_RealBlur.py ran licence not identified · pointer only · 91fa50e293bf2fde · report fixture: signature image_true:ndarray/2/float, image_test:ndarray/2/float, image_mask:ndarray/2/float, data_range:float/0/float · returned float64 · level recorded 2026-09-24
is_frozen in 10 papers utils/model_utils.py ran · violated contract licence not identified · pointer only · 930cddf0a4d80ab1 · report fixture: signature model:callable/0/? · returned bool · level recorded 2026-09-24
is_image_file in 157 papers dataset_RGB.py ran · violated contract licence not identified · pointer only · 91fca7a2b44569ad · report fixture: signature filename:str/0/str · returned bool · level recorded 2026-09-24
load_start_epoch in 9 papers utils/model_utils.py ran · honoured contract licence not identified · pointer only · c3bea8c4ee6bef4a · report fixture: signature weights:str/0/str · returned int · level recorded 2026-09-24
window_partitions layers.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · f14419333447d8d6 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-24
window_partitionx layers.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · da27ca0f6f887544 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned tuple · level recorded 2026-09-24
window_reverses layers.py ran · our draft was wrong licence not identified · pointer only · 8d587d6910a0319d · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-24
compute_ssim in 15 papers evaluate_RealBlur.py unverified licence not identified · pointer only · 464c3d3b7a1eb4b3 · report
get_test_data in 10 papers data_RGB.py unverified licence not identified · pointer only · b3e783979d8b03ec · report
get_training_data data_RGB.py unverified licence not identified · pointer only · 2bd77b7b9be25add · report
get_validation_data data_RGB.py unverified licence not identified · pointer only · c4feda9e4dc1f1a3 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for AdaRevD (graph method: AdaRevD). 32 bricks; individually on a fixture: 22 ran (of which 17 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

  1. AdaRevID entry · level 0 · unverified · 35c1fb15cf9c2a3c
  2. Classifier model · level 1 · ran · 54b4cb2b28654156
  3. NAFBlock model · level 1 · ran · ab6a31f934b01390
  4. NAFNet helper · level 1 · ran · d033cd39f61aec96
  5. UFPNet helper · level 0 · unverified · 526f252c65b7794a
  6. UniDecoder model · level 0 · unverified · f827e2156483181c
  7. LayerNorm2d helper · level 1 · ran · 26e0e3b2df966dee
  8. SimpleGate helper · level 1 · ran · 19826953d6d91066
  9. KernelPrior helper · level 1 · ran · 2adab08083a9624a
  10. NAFBlock_kernel helper · level 1 · ran · 027f7863abb8f85d
  11. code_extra_mean_var helper · level 1 · ran · d65cc58b327e770c
  12. generate_k helper · level 1 · ran · our draft was wrong · edcc2d839bbe7b62
  13. Level_Decoder model · level 0 · unverified · ad5c1c85d29e898d
  14. ReverseFunction helper · level 1 · ran · 0e436a8df9e0385f
  15. LayerNormFunction helper · level 1 · ran · e0c7c3f6540a28db
  16. BatchNorm helper · level 1 · ran · aa30d63064354a0f
  17. FlowSequential helper · level 0 · unverified · 213315d48b01e0a7
  18. LinearMaskedCoupling helper · level 1 · ran · 3a18b572b6b1e5ad
  19. kernel_attention helper · level 1 · ran · f0c04361fd77de5d
  20. kernel_extra_Decoding_Block helper · level 1 · ran · efcbb8d5303a9dde
  21. kernel_extra_Encoding_Block helper · level 1 · ran · 1c61356d1f70ebdf
  22. kernel_extra_conv_mid helper · level 1 · ran · ff5339d531bd8ec5
  23. kernel_extra_conv_tail_mean_var helper · level 1 · ran · effbd87d7309d611
  24. FCNAFBlock model · level 0 · unverified · 719313e70c1ce9cc
  25. Fusion_DecoderV1 model · level 0 · unverified · 3fb2ae8418a9650d
  26. detach_and_grad helper · level 1 · ran · our draft was wrong · 66607a81e9dce986
  27. get_cpu_and_gpu_states helper · level 1 · ran · our draft was wrong · 298ef15d9028ac53
  28. get_gpu_device helper · level 0 · unverified · ba9068d857e12c4d
  29. set_device_states helper · level 0 · unverified · 1d10fd4faaf7d98b
  30. ResBlock helper · level 1 · ran · a5c971c79279e4c9
  31. get_gpu_states helper · level 0 · unverified · dd9e76dff65e161f
  32. conv_bench helper · level 1 · ran · 5915a0dcd991fd39

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="2406.09135") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DeblurringDecoderImage Deblurring

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Deblurring GoPro AdaRevD PSNR 34.6 #7 of 56 Archive leaderboard report
Deblurring GoPro AdaRevD SSIM 0.972 #7 of 56 Archive leaderboard report
Deblurring HIDE (trained on GOPRO) AdaRevD PSNR (sRGB) 32.35 #2 of 26 Archive leaderboard report
Deblurring HIDE (trained on GOPRO) AdaRevD SSIM (sRGB) 0.953 #2 of 26 Archive leaderboard report
Deblurring RealBlur-J AdaRevD PSNR (sRGB) 33.96 #1 of 17 Archive leaderboard report
Deblurring RealBlur-J AdaRevD SSIM (sRGB) 0.944 #1 of 17 Archive leaderboard report
Deblurring RealBlur-J (trained on GoPro) AdaRevD PSNR (sRGB) 30.12 #1 of 15 Archive leaderboard report
Deblurring RealBlur-J (trained on GoPro) AdaRevD SSIM (sRGB) 0.894 #1 of 15 Archive leaderboard report
Deblurring RealBlur-R AdaRevD PSNR (sRGB) 41.19 #1 of 17 Archive leaderboard report
Deblurring RealBlur-R AdaRevD SSIM (sRGB) 0.979 #1 of 17 Archive leaderboard report
Deblurring RealBlur-R (trained on GoPro) AdaRevD PSNR (sRGB) 36.53 #1 of 19 Archive leaderboard report
Deblurring RealBlur-R (trained on GoPro) AdaRevD SSIM (sRGB) 0.957 #1 of 19 Archive leaderboard report
Image Deblurring GoPro AdaRevD PSNR 34.6 #1 of 55 Archive leaderboard report
Image Deblurring GoPro AdaRevD SSIM 0.972 #1 of 55 Archive leaderboard report
Image Deblurring HIDE AdaRevD PSNR 32.35 #1 of 5 Archive leaderboard report
Image Deblurring HIDE AdaRevD SSIM 0.953 #1 of 5 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.

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