Papers › Empowering Low-Light Image Enhancer through Customized Learnable Priors

Empowering Low-Light Image Enhancer through Customized Learnable Priors

5 Sep 2023ICCV 2023 1arXiv:2309.01958archive 2025-07-28

Naishan Zheng, Man Zhou, Yanmeng Dong, Xiangyu Rui, Jie Huang, Chongyi Li, Feng Zhao

Deep neural networks have achieved remarkable progress in enhancing low-light images by improving their brightness and eliminating noise. However, most existing methods construct end-to-end mapping networks heuristically, neglecting the intrinsic prior of image enhancement task and lacking transparency and interpretability. Although some unfolding solutions have been proposed to relieve these issues, they rely on proximal operator networks that deliver ambiguous and implicit priors. In this work, we propose a paradigm for low-light image enhancement that explores the potential of customized learnable priors to improve the transparency of the deep unfolding paradigm. Motivated by the powerful feature representation capability of Masked Autoencoder (MAE), we customize MAE-based illumination and noise priors and redevelop them from two perspectives: 1) structure flow: we train the MAE from a normal-light image to its illumination properties and then embed it into the proximal operator design of the unfolding architecture; and m2) optimization flow: we train MAE from a normal-light image to its gradient representation and then employ it as a regularization term to constrain noise in the model output. These designs improve the interpretability and representation capability of the model.Extensive experiments on multiple low-light image enhancement datasets demonstrate the superiority of our proposed paradigm over state-of-the-art methods. Code is available at https://github.com/zheng980629/CUE.

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 18 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 18 samples from 1 repository, 13 ran (13 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

zheng980629/cue officialmentioned in papermentioned on GitHubpytorchSyntology: 18 samples, 13 ran (0 instrument-failed) · 5 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

18 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 5 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.

13ran
5unverified

Licence: 18 of the 18 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 zheng980629/cue. “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.

zheng980629/cue official repository 18 samples, 13 ran (0 instrument-failed) · 5 unverified
BasicUnit basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 8ee2440798eabe67 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
CALayer in 11 papers basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py ran · metamorphic tier: invariant no licence file found · pointer only · 7ecf52b7a2d5bf5d · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ChannelFuse basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py ran fingerprinted no licence file found · pointer only · a4878cb890d08d03 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
FreBlockCha basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py ran · metamorphic tier: well formed no licence file found · pointer only · 800e1ede4974d91e · report fixture: signature x:Tensor/4/complex · returned Tensor · level recorded 2026-09-22
FreBlockSpa basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py ran · metamorphic tier: well formed no licence file found · pointer only · 692ece12ca443901 · report fixture: signature x:Tensor/4/complex · returned Tensor · level recorded 2026-09-22
InvBlock in 5 papers basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py ran no licence file found · pointer only · 09828605b5df4e22 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
NoiseBlock basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py ran fingerprinted no licence file found · pointer only · 76b9673dfdfb7580 · report fixture: signature low_light:Tensor/4/float, illu:Tensor/4/float, refl:Tensor/4/float, mu:float/0/float · returned Tensor · level recorded 2026-09-24
ReflectanceBlock basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 8707d92b40d0bc99 · report fixture: signature low_light:Tensor/4/float, illu:Tensor/4/float, noise:Tensor/4/float, refl:Tensor/4/float, beta:Tensor/0/float, mu:Tensor/0/float · returned Tensor · level recorded 2026-09-22
SpaBlock basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 23bb1fc45e5c5c60 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
SpatialFuse basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py ran fingerprinted no licence file found · pointer only · 007acfd749aebeb1 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
UNetConvBlock in 5 papers basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 4f7bbfa1161eb18c · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
UNetConvBlock_fre basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · bea493cdea1186e8 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
UNet_BilateralFilter_mask basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py ran · metamorphic tier: deterministic no licence file found · pointer only · c9e0b98c54bdd2b0 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-22
IlluminationBlock basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py unverified no licence file found · pointer only · 254d70c745b46dfc · report
InteractNet basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py unverified no licence file found · pointer only · 6fee00ee6cc0f312 · report
LearnablePriorEnhanceNet basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py unverified no licence file found · pointer only · 284764d0b6cab796 · report
ProcessBlock basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py unverified no licence file found · pointer only · e63b4cd4b28e5361 · report
ProcessNet basicsr/archs/LearnablePriorsCondUNetFreReflRestore_arch.py unverified no licence file found · pointer only · f5e35c4fcfe04e42 · 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 Customized Learnable Priors (graph method: Customized Learnable Priors). 19 bricks; individually on a fixture: 14 ran (of which 1 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. LearnablePriorEnhanceNet entry · level 0 · unverified · 284764d0b6cab796
  2. IlluminationBlock model · level 0 · unverified · 254d70c745b46dfc
  3. InteractNet model · level 0 · unverified · 6fee00ee6cc0f312
  4. NoiseBlock model · level 1 · ran · 76b9673dfdfb7580
  5. ReflectanceBlock model · level 1 · ran · 8707d92b40d0bc99
  6. UNet_BilateralFilter_mask model · level 1 · ran · c9e0b98c54bdd2b0
  7. ProcessNet model · level 0 · unverified · f5e35c4fcfe04e42
  8. BasicUnit model · level 1 · ran · 8ee2440798eabe67
  9. CALayer helper · level 1 · ran · 7ecf52b7a2d5bf5d
  10. UNetConvBlock helper · level 1 · ran · 4f7bbfa1161eb18c
  11. ProcessBlock helper · level 0 · unverified · e63b4cd4b28e5361
  12. ChannelFuse helper · level 1 · ran · a4878cb890d08d03
  13. SpatialFuse helper · level 1 · ran · 007acfd749aebeb1
  14. FreBlockCha helper · level 1 · ran · 800e1ede4974d91e
  15. SpaBlock helper · level 1 · ran · 23bb1fc45e5c5c60
  16. FreBlockSpa helper · level 1 · ran · 692ece12ca443901
  17. InvBlock helper · level 1 · ran · 09828605b5df4e22
  18. UNetConvBlock_fre helper · level 1 · ran · bea493cdea1186e8
  19. Registry helper · level 1 · ran · 2cd4dd2a6360b684

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="2309.01958") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image EnhancementLow-Light Image Enhancement

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

MAE

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