Papers › MAXIM: Multi-Axis MLP for Image Processing

MAXIM: Multi-Axis MLP for Image Processing

9 Jan 2022CVPR 2022 1arXiv:2201.02973archive 2025-07-28

Zhengzhong Tu, Hossein Talebi, Han Zhang, Feng Yang, Peyman Milanfar, Alan Bovik, Yinxiao Li

Recent progress on Transformers and multi-layer perceptron (MLP) models provide new network architectural designs for computer vision tasks. Although these models proved to be effective in many vision tasks such as image recognition, there remain challenges in adapting them for low-level vision. The inflexibility to support high-resolution images and limitations of local attention are perhaps the main bottlenecks. In this work, we present a multi-axis MLP based architecture called MAXIM, that can serve as an efficient and flexible general-purpose vision backbone for image processing tasks. MAXIM uses a UNet-shaped hierarchical structure and supports long-range interactions enabled by spatially-gated MLPs. Specifically, MAXIM contains two MLP-based building blocks: a multi-axis gated MLP that allows for efficient and scalable spatial mixing of local and global visual cues, and a cross-gating block, an alternative to cross-attention, which accounts for cross-feature conditioning. Both these modules are exclusively based on MLPs, but also benefit from being both global and `fully-convolutional', two properties that are desirable for image processing. Our extensive experimental results show that the proposed MAXIM model achieves state-of-the-art performance on more than ten benchmarks across a range of image processing tasks, including denoising, deblurring, deraining, dehazing, and enhancement while requiring fewer or comparable numbers of parameters and FLOPs than competitive models. The source code and trained models will be available at https://github.com/google-research/maxim.

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 46 code samples harvested from 3 repositories linked to this paper: 31 ran (of which 7 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 15 where Syntology's instrument failed) · 15 unverified. Where Syntology's instrument failed: 13 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 34 samples from 2 repositories, 24 ran (9 with no instrument failure; 15 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.

google-research/maxim officialmentioned in papermentioned on GitHubjaxSyntology: 12 samples, 7 ran (0 instrument-failed) · 5 unverified report
sayakpaul/maxim-tf mentioned on GitHubtfSyntology: 22 samples, 14 ran (11 instrument-failed) · 8 unverified report
vztu/maxim-pytorch mentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 10 ran (4 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.

Code Syntology ran Syntology

46 samples harvested: 31 ran (of which 7 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 15 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
13ran · our draft was wrong
2ran; the contract check could not run
15ran
15unverified

Licence: 6 of the 46 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 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.

google-research/maxim official repository 12 samples, 7 ran (0 instrument-failed) · 5 unverified
CALayer in 11 papers maxim/models/maxim.py ran Apache-2.0 (permissive) · 19b896e6c80f7746 · report fixture: returned CALayer · level recorded 2026-09-22
CrossGatingBlock maxim/models/maxim.py ran Apache-2.0 (permissive) · 766dd58d53750085 · report fixture: returned CrossGatingBlock · level recorded 2026-09-22
GetSpatialGatingWeights maxim/models/maxim.py ran Apache-2.0 (permissive) · 084dcbcab94aaf9e · report fixture: returned GetSpatialGatingWeights · level recorded 2026-09-22
MlpBlock in 9 papers maxim/models/maxim.py ran Apache-2.0 (permissive) · e60caa8706cbaa5e · report fixture: returned MlpBlock · level recorded 2026-09-22
RCAB in 6 papers maxim/models/maxim.py ran Apache-2.0 (permissive) · a848dc175add161e · report fixture: returned RCAB · level recorded 2026-09-22
RDCAB maxim/models/maxim.py ran Apache-2.0 (permissive) · 1fdc0576592cc66d · report fixture: returned RDCAB · level recorded 2026-09-22
UpSampleRatio maxim/models/maxim.py ran Apache-2.0 (permissive) · 42206e2f2fad7d53 · report fixture: returned UpSampleRatio · level recorded 2026-09-22
BottleneckBlock in 5 papers maxim/models/maxim.py unverified Apache-2.0 (permissive) · 1f82af068fbcb99b · report
MAXIM maxim/models/maxim.py unverified Apache-2.0 (permissive) · cf9ff379ec874bea · report
SAM in 25 papers maxim/models/maxim.py unverified Apache-2.0 (permissive) · 5677718f64cf57a1 · report
UNetDecoderBlock maxim/models/maxim.py unverified Apache-2.0 (permissive) · 368f5be0ac386cea · report
UNetEncoderBlock maxim/models/maxim.py unverified Apache-2.0 (permissive) · 65880b9a096f0b2e · report
sayakpaul/maxim-tf community (archive-listed) 22 samples, 14 ran (11 instrument-failed) · 8 unverified
BlockGatingUnit maxim/maxim.py ran · our draft was wrong Apache-2.0 (permissive) · 7ed1b7f6a7fca542 · report fixture: signature use_bias:bool/0/bool, name:str/0/str · returned function · level recorded 2026-09-22
BlockGmlpLayer maxim/maxim.py ran · our draft was wrong Apache-2.0 (permissive) · 9f6816f577e4daf7 · report fixture: signature block_size:tuple/1/int, use_bias:bool/0/bool, factor:int/0/int, dropout_rate:float/0/float, name:str/0/str · returned function · level recorded 2026-09-22
CALayer in 11 papers maxim/maxim.py ran · our draft was wrong Apache-2.0 (permissive) · 324d6a11c6374570 · report fixture: signature num_channels:int/0/int, reduction:int/0/int, use_bias:bool/0/bool, name:str/0/str · returned function · level recorded 2026-09-22
GetSpatialGatingWeights maxim/maxim.py ran · our draft was wrong Apache-2.0 (permissive) · 258edcba99050dce · report fixture: signature features:int/0/int, block_size:tuple/1/int, grid_size:tuple/1/int, input_proj_factor:int/0/int, dropout_rate:float/0/float, use_bias:bool/0/bool, name:str/0/str · returned function · level recorded 2026-09-22
GridGatingUnit maxim/maxim.py ran · our draft was wrong Apache-2.0 (permissive) · 9ec31f74d265cc86 · report fixture: signature use_bias:bool/0/bool, name:str/0/str · returned function · level recorded 2026-09-22
GridGmlpLayer maxim/maxim.py ran · our draft was wrong Apache-2.0 (permissive) · 05dca5627244f135 · report fixture: signature grid_size:tuple/1/int, use_bias:bool/0/bool, factor:int/0/int, dropout_rate:float/0/float, name:str/0/str · returned function · level recorded 2026-09-22
MlpBlock in 9 papers maxim/maxim.py ran · our draft was wrong Apache-2.0 (permissive) · 4cbc099a6c833993 · report fixture: signature mlp_dim:int/0/int, dropout_rate:float/0/float, use_bias:bool/0/bool, name:str/0/str · returned function · level recorded 2026-09-22
RCAB in 6 papers maxim/maxim.py ran · our draft was wrong Apache-2.0 (permissive) · 5333727b65d8f4e5 · report fixture: signature num_channels:int/0/int, reduction:int/0/int, lrelu_slope:float/0/float, use_bias:bool/0/bool, name:str/0/str · returned function · level recorded 2026-09-22
RDCAB maxim/maxim.py ran · our draft was wrong Apache-2.0 (permissive) · d3804c01fc7b2d0b · report fixture: signature num_channels:int/0/int, reduction:int/0/int, use_bias:bool/0/bool, dropout_rate:float/0/float, name:str/0/str · returned function · level recorded 2026-09-22
Resizing maxim/maxim.py ran fingerprinted Apache-2.0 (permissive) · 03c67e5e165e1da6 · report fixture: signature img:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-24
SAM in 25 papers maxim/maxim.py ran · our draft was wrong Apache-2.0 (permissive) · e1002ec72887a8e7 · report fixture: signature num_channels:int/0/int, output_channels:int/0/int, use_bias:bool/0/bool, name:str/0/str · returned function · level recorded 2026-09-22
SwapAxes maxim/maxim.py ran fingerprinted Apache-2.0 (permissive) · cc569d6b5f02b960 · report fixture: signature x:EagerTensor/4/float, axis_one:int/0/int, axis_two:int/0/int · returned EagerTensor · level recorded 2026-09-24
TFBlockImages maxim/maxim.py ran Apache-2.0 (permissive) · 61cbfaf1cb7f570e · report fixture: signature image:EagerTensor/4/float, patch_size:tuple/1/int · returned list · level recorded 2026-09-24
UpSampleRatio maxim/maxim.py ran · our draft was wrong Apache-2.0 (permissive) · 612b66e64a594d39 · report fixture: signature num_channels:int/0/int, ratio:float/0/float, use_bias:bool/0/bool, name:str/0/str · returned function · level recorded 2026-09-22
BottleneckBlock in 5 papers maxim/maxim.py unverified Apache-2.0 (permissive) · 8f3bf5e1e1ab7a8a · report
CrossGatingBlock maxim/maxim.py unverified Apache-2.0 (permissive) · ccc6692913775565 · report
MAXIM maxim/maxim.py unverified Apache-2.0 (permissive) · fa1baf06efa9af1a · report
ResidualSplitHeadMultiAxisGmlpLayer maxim/maxim.py unverified Apache-2.0 (permissive) · 2a2c1a868e2dcde6 · report
TFBlockImagesByGrid maxim/maxim.py unverified Apache-2.0 (permissive) · bfc4a56270266181 · report
TFUnblockImages maxim/maxim.py unverified Apache-2.0 (permissive) · bbe59c0f7d80a435 · report
UNetDecoderBlock maxim/maxim.py unverified Apache-2.0 (permissive) · 388ba9abc6d6edcf · report
UNetEncoderBlock maxim/maxim.py unverified Apache-2.0 (permissive) · 8cae04426d07cd86 · report
vztu/maxim-pytorch community (archive-listed) 12 samples, 10 ran (4 instrument-failed) · 2 unverified
block_images_einops maxim_pytorch/maxim_torch.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 8a67f23552a44d61 · report fixture: signature x:Tensor/4/float, patch_size:tuple/1/int · returned Tensor · level recorded 2026-09-22
calculate_psnr in 51 papers Deblurring/utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · d292dd965ab59629 · report fixture: signature img1:ndarray/2/int, img2:ndarray/2/int, border:int/0/int · returned float · level recorded 2026-09-24
calculate_ssim in 24 papers Deblurring/utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · a05b184dc6c264a0 · report fixture: signature img1:ndarray/3/int, img2:ndarray/3/int, border:int/0/int · returned float64 · level recorded 2026-09-24
compute_psnr in 30 papers Deblurring/evaluate_realblur.py ran Apache-2.0 (permissive) here; the stored copy is 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
get_params in 53 papers maxim_pytorch/jax2torch.py ran Apache-2.0 (permissive) · 1b0d800507b48241 · report fixture: signature ckpt_path:str/0/str · returned dict · level recorded 2026-09-24
modify_jax_params maxim_pytorch/jax2torch.py ran Apache-2.0 (permissive) · 24049a3abbb124a4 · report fixture: signature flat_jax_dict:dict/0/? · returned dict · level recorded 2026-09-24
nearest_downsample maxim_pytorch/maxim_torch.py ran fingerprinted Apache-2.0 (permissive) · ecee36a6f46993db · report fixture: signature x:Tensor/4/float, ratio:float/0/float · returned Tensor · level recorded 2026-09-24
recover_tree maxim_pytorch/jax2torch.py ran Apache-2.0 (permissive) · 2a480b42a952d169 · report fixture: signature keys:list/1/str, values:list/1/int · returned dict · level recorded 2026-09-24
ssim in 112 papers Deblurring/utils.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · ba721aeacc165234 · report fixture: signature img1:ndarray/2/int, img2:ndarray/2/int · returned float64 · level recorded 2026-09-24
unblock_images_einops maxim_pytorch/maxim_torch.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 627ea4c76565d927 · report fixture: signature x:Tensor/4/float, grid_size:tuple/1/int, patch_size:tuple/1/int · returned Tensor · level recorded 2026-09-22
compute_ssim in 15 papers Deblurring/evaluate_realblur.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 464c3d3b7a1eb4b3 · report
image_align in 8 papers Deblurring/evaluate_realblur.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 5aad1c1e328fd4ec · 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.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for MAXIM (graph method: MAXIM). 19 bricks; individually on a fixture: 12 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. MAXIM entry · level 0 · unverified · cf9ff379ec874bea
  2. BottleneckBlock model · level 0 · unverified · 1f82af068fbcb99b
  3. CrossGatingBlock model · level 1 · ran · 766dd58d53750085
  4. SAM model · level 0 · unverified · 5677718f64cf57a1
  5. UNetDecoderBlock model · level 0 · unverified · 368f5be0ac386cea
  6. UNetEncoderBlock model · level 0 · unverified · 65880b9a096f0b2e
  7. UpSampleRatio helper · level 1 · ran · 42206e2f2fad7d53
  8. RDCAB model · level 1 · ran · 1fdc0576592cc66d
  9. ResidualSplitHeadMultiAxisGmlpLayer model · level 0 · unverified · e7fa9568a4a28913
  10. GetSpatialGatingWeights helper · level 1 · ran · 084dcbcab94aaf9e
  11. RCAB helper · level 1 · ran · a848dc175add161e
  12. CALayer helper · level 1 · ran · 19b896e6c80f7746
  13. MlpBlock helper · level 1 · ran · e60caa8706cbaa5e
  14. BlockGmlpLayer helper · level 1 · ran · 325b31d5363dae7d
  15. GridGmlpLayer helper · level 0 · unverified · bcddd7996b51db67
  16. block_images_einops helper · level 1 · ran; the contract check could not run (RAISES) · 8a67f23552a44d61
  17. unblock_images_einops helper · level 1 · ran; the contract check could not run (RAISES) · 627ea4c76565d927
  18. BlockGatingUnit helper · level 1 · ran · d8da107e27ecbe28
  19. GridGatingUnit helper · level 1 · ran · 86d6d05360b6903b

harvested Assembly for MAXIM (graph method: MAXIM). 22 bricks; individually on a fixture: 14 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 11 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. MAXIM entry · level 0 · unverified · fa1baf06efa9af1a
  2. BottleneckBlock helper · level 0 · unverified · 8f3bf5e1e1ab7a8a
  3. CrossGatingBlock helper · level 0 · unverified · ccc6692913775565
  4. Resizing helper · level 1 · ran · 03c67e5e165e1da6
  5. SAM model · level 1 · ran · our draft was wrong · e1002ec72887a8e7
  6. UNetDecoderBlock model · level 0 · unverified · 388ba9abc6d6edcf
  7. UNetEncoderBlock model · level 0 · unverified · 8cae04426d07cd86
  8. UpSampleRatio helper · level 1 · ran · our draft was wrong · 612b66e64a594d39
  9. RDCAB model · level 1 · ran · our draft was wrong · d3804c01fc7b2d0b
  10. ResidualSplitHeadMultiAxisGmlpLayer helper · level 0 · unverified · 2a2c1a868e2dcde6
  11. GetSpatialGatingWeights helper · level 1 · ran · our draft was wrong · 258edcba99050dce
  12. RCAB model · level 1 · ran · our draft was wrong · 5333727b65d8f4e5
  13. CALayer model · level 1 · ran · our draft was wrong · 324d6a11c6374570
  14. MlpBlock helper · level 1 · ran · our draft was wrong · 4cbc099a6c833993
  15. BlockGmlpLayer helper · level 1 · ran · our draft was wrong · 9f6816f577e4daf7
  16. GridGmlpLayer helper · level 1 · ran · our draft was wrong · 05dca5627244f135
  17. SwapAxes helper · level 1 · ran · cc569d6b5f02b960
  18. TFBlockImages helper · level 1 · ran · 61cbfaf1cb7f570e
  19. TFBlockImagesByGrid helper · level 0 · unverified · bfc4a56270266181
  20. TFUnblockImages helper · level 0 · unverified · bbe59c0f7d80a435
  21. BlockGatingUnit helper · level 1 · ran · our draft was wrong · 7ed1b7f6a7fca542
  22. GridGatingUnit helper · level 1 · ran · our draft was wrong · 9ec31f74d265cc86

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="2201.02973") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DeblurringDenoisingImage DeblurringImage DehazingImage DenoisingImage RestorationLow-Light Image EnhancementPhoto RetouchingRain RemovalSingle Image Deraining

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Deblurring BASED MAXIM (REDS) PSNR 30.65728 #4 of 4 Archive leaderboard report
Deblurring GoPro MAXIM-3S PSNR 32.86 #30 of 56 Archive leaderboard report
Deblurring HIDE MAXIM-3S PSNR 32.83 #1 of 1 Archive leaderboard report
Deblurring HIDE (trained on GOPRO) MAXIM PSNR (sRGB) 32.83 #1 of 26 Archive leaderboard report
Deblurring HIDE (trained on GOPRO) MAXIM Params (M) 22.2 #1 of 26 Archive leaderboard report
Deblurring HIDE (trained on GOPRO) MAXIM SSIM (sRGB) 0.956 #1 of 26 Archive leaderboard report
Deblurring MSU BASED MAXIM (REDS) ERQAv2.0 0.74277 #5 of 11 Archive leaderboard report
Deblurring MSU BASED MAXIM (REDS) LPIPS 0.07836 #5 of 11 Archive leaderboard report
Deblurring MSU BASED MAXIM (REDS) SSIM 0.94959 #5 of 11 Archive leaderboard report
Deblurring MSU BASED MAXIM (REDS) Subjective 1.0081 #5 of 11 Archive leaderboard report
Deblurring MSU BASED MAXIM (REDS) VMAF 67.3502 #5 of 11 Archive leaderboard report
Deblurring MSU BASED MAXIM (GoPro) LPIPS 0.09188 #9 of 11 Archive leaderboard report
Deblurring MSU BASED MAXIM (GoPro) PSNR 31.36344 #9 of 11 Archive leaderboard report
Deblurring MSU BASED MAXIM (GoPro) SSIM 0.94386 #9 of 11 Archive leaderboard report
Deblurring MSU BASED MAXIM (GoPro) Subjective 0.2070 #9 of 11 Archive leaderboard report
Deblurring MSU BASED MAXIM (GoPro) VMAF 67.7557 #9 of 11 Archive leaderboard report
Deblurring RealBlur-J MAXIM PSNR (sRGB) 32.84 #8 of 17 Archive leaderboard report
Deblurring RealBlur-J MAXIM Params(M) 22.2 #8 of 17 Archive leaderboard report
Deblurring RealBlur-J MAXIM SSIM (sRGB) 0.935 #8 of 17 Archive leaderboard report
Deblurring RealBlur-J (trained on GoPro) MAXIM PSNR (sRGB) 28.83 #8 of 15 Archive leaderboard report
Deblurring RealBlur-J (trained on GoPro) MAXIM SSIM (sRGB) 0.875 #8 of 15 Archive leaderboard report
Deblurring RealBlur-R MAXIM PSNR (sRGB) 39.45 #13 of 17 Archive leaderboard report
Deblurring RealBlur-R MAXIM-3S SSIM (sRGB) 0.961 #17 of 17 Archive leaderboard report
Deblurring RealBlur-R (trained on GoPro) MAXIM PSNR (sRGB) 35.78 #10 of 19 Archive leaderboard report
Image Deblurring GoPro MAXIM-3S PSNR 32.86 #32 of 55 Archive leaderboard report
Image Deblurring HIDE MAXIM-3S SSIM 0.956 #5 of 5 Archive leaderboard report
Image Dehazing SOTS Indoor MAXIM-2S PSNR 38.11 #19 of 34 Archive leaderboard report
Image Dehazing SOTS Outdoor MAXIM-2S PSNR 34.19 #20 of 31 Archive leaderboard report
Image Denoising DND MAXIM-3S PSNR (sRGB) 39.84 #8 of 16 Archive leaderboard report
Image Denoising DND MAXIM-3S SSIM (sRGB) 0.954 #8 of 16 Archive leaderboard report
Image Denoising SIDD MAXIM-3S PSNR (sRGB) 39.96 #8 of 22 Archive leaderboard report
Image Denoising SIDD MAXIM-3S SSIM (sRGB) 0.960 #8 of 22 Archive leaderboard report
Low-Light Image Enhancement LOL MAXIM Average PSNR 23.43 #30 of 40 Archive leaderboard report
Low-Light Image Enhancement LOL MAXIM SSIM 0.863 #30 of 40 Archive leaderboard report
Photo Retouching MIT-Adobe 5k MAXIM PSNR 26.15 #1 of 5 Archive leaderboard report
Photo Retouching MIT-Adobe 5k MAXIM SSIM 0.945 #1 of 5 Archive leaderboard report
Single Image Deraining Rain100H MAXIM SSIM 0.903 #16 of 19 Archive leaderboard report
Single Image Deraining Rain100L MAXIM SSIM 0.977 #15 of 19 Archive leaderboard report
Single Image Deraining Test100 MAXIM PSNR 31.17 #4 of 12 Archive leaderboard report
Single Image Deraining Test100 MAXIM SSIM 0.922 #4 of 12 Archive leaderboard report
Single Image Deraining Test1200 MAXIM SSIM 0.922 #10 of 14 Archive leaderboard report
Single Image Deraining Test2800 MAXIM PSNR 33.80 #4 of 12 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