Papers › A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and...

A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint

27 Mar 2024CVPR 2024 1arXiv:2403.18548archive 2025-07-28

Xiaofeng Cong, Jie Gui, Jing Zhang, JunMing Hou, Hao Shen

Existing research based on deep learning has extensively explored the problem of daytime image dehazing. However, few studies have considered the characteristics of nighttime hazy scenes. There are two distinctions between nighttime and daytime haze. First, there may be multiple active colored light sources with lower illumination intensity in nighttime scenes, which may cause haze, glow and noise with localized, coupled and frequency inconsistent characteristics. Second, due to the domain discrepancy between simulated and real-world data, unrealistic brightness may occur when applying a dehazing model trained on simulated data to real-world data. To address the above two issues, we propose a semi-supervised model for real-world nighttime dehazing. First, the spatial attention and frequency spectrum filtering are implemented as a spatial-frequency domain information interaction module to handle the first issue. Second, a pseudo-label-based retraining strategy and a local window-based brightness loss for semi-supervised training process is designed to suppress haze and glow while achieving realistic brightness. Experiments on public benchmarks validate the effectiveness of the proposed method and its superiority over state-of-the-art methods. The source code and Supplementary Materials are placed in the https://github.com/Xiaofeng-life/SFSNiD.

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 24 code samples harvested from 1 repository linked to this paper: 18 ran (of which 10 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 24 samples from 1 repository, 18 ran (16 with no instrument failure; 2 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.

xiaofeng-life/sfsnid officialmentioned in paperpytorchSyntology: 24 samples, 18 ran (2 instrument-failed) · 6 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

24 samples harvested: 18 ran (of which 10 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 6 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.

2ran · honoured contract
1ran · our draft was wrong
1ran; the contract check could not run
14ran
6unverified

Licence: 24 of the 24 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 xiaofeng-life/sfsnid. “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 7 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.

xiaofeng-life/sfsnid official repository 24 samples, 18 ran (2 instrument-failed) · 6 unverified
BasicConv in 14 papers methods/MyNightDehazing/SFSNiD.py ran fingerprinted no licence file found · pointer only · cf777657fcd4a612 · report fixture: returned BasicConv · level recorded 2026-09-22
BidomainNonlinearMapping methods/MyNightDehazing/SFSNiD.py ran fingerprinted no licence file found · pointer only · 45a3ed308b72fa50 · report fixture: returned BidomainNonlinearMapping · level recorded 2026-09-22
BidomainNonlinearMapping_SinglePath methods/MyNightDehazing/SFSNiD.py ran fingerprinted no licence file found · pointer only · 87326e31813a4257 · report fixture: returned BidomainNonlinearMapping_SinglePath · level recorded 2026-09-22
ConvOut_withFFT methods/MyNightDehazing/SFSNiD.py ran no licence file found · pointer only · 875b657d463b5483 · report fixture: returned ConvOut_withFFT · level recorded 2026-09-22
FeatureMerge methods/MyNightDehazing/SFSNiD.py ran no licence file found · pointer only · d07c444c0d226166 · report fixture: returned FeatureMerge · level recorded 2026-09-22
Frequency_Spectrum_Dynamic_Aggregation methods/MyNightDehazing/SFSNiD.py ran no licence file found · pointer only · b2e3910a075de18c · report fixture: signature x:Tensor/4/complex · returned Tensor · level recorded 2026-09-24
ResBlock_Conv methods/MyNightDehazing/SFSNiD.py ran no licence file found · pointer only · 7b37be285043f2b0 · report fixture: returned ResBlock_Conv · level recorded 2026-09-22
SCM_withFFT methods/MyNightDehazing/SFSNiD.py ran fingerprinted no licence file found · pointer only · 454f7ad32b74b892 · report fixture: returned SCM_withFFT · level recorded 2026-09-22
SpaBlock methods/MyNightDehazing/SFSNiD.py ran fingerprinted no licence file found · pointer only · a4c4157fd5060c95 · report fixture: returned SpaBlock · level recorded 2026-09-22
TransformerBlock in 73 papers methods/MyNightDehazing/SFSNiD.py ran no licence file found · pointer only · 5a7a00261e5bfad2 · report fixture: returned TransformerBlock · level recorded 2026-09-22
WindowAttention in 50 papers methods/MyNightDehazing/SFSNiD.py ran no licence file found · pointer only · a6f8738670f038ed · report fixture: returned WindowAttention · level recorded 2026-09-22
dynamic_gamma_clear task_SFSNiD/Generate_Dark_UNREALNH.py ran fingerprinted no licence file found · pointer only · 06db7d462dba3a61 · report fixture: signature batch_clear:Tensor/2/float, mean_val_clear:float/0/float · returned Tensor · level recorded 2026-09-24
dynamic_gamma_hazy task_SFSNiD/Generate_Dark_UNREALNH.py ran fingerprinted no licence file found · pointer only · 7542148c703f6f59 · report fixture: signature batch_hazy:Tensor/4/float, mean_val_hazy:float/0/float · returned Tensor · level recorded 2026-09-24
get_ratio in 7 papers task_SFSNiD/train_SFSNiD_semi_supervised.py ran fingerprinted no licence file found · pointer only · 98b93da88040b6ab · report fixture: signature batch_tensor:Tensor/2/float, tar_size:int/0/int · returned Tensor · level recorded 2026-09-24
get_relative_positions in 8 papers methods/MyNightDehazing/SFSNiD.py ran · honoured contract no licence file found · pointer only · 2a53db1b6432ab8c · report fixture: signature window_size:int/0/int · returned Tensor · level recorded 2026-09-22
query in 11 papers task_SFSNiD/train_SFSNiD_semi_supervised.py ran · honoured contract fingerprinted no licence file found · pointer only · 71d44f079297c28a · report fixture: signature val:int/0/int · returned float · level recorded 2026-09-24
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
methods/MyNightDehazing/SFSNiD.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 751569c78a842e44 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers methods/MyNightDehazing/SFSNiD.py ran · our draft was wrong no licence file found · pointer only · 7b0d02f75bf6b439 · 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
DBlock in 7 papers methods/MyNightDehazing/SFSNiD.py unverified no licence file found · pointer only · 10f0475cf68882cf · report
EBlock in 5 papers methods/MyNightDehazing/SFSNiD.py unverified no licence file found · pointer only · 969613da960105c3 · report
SFSNiD methods/MyNightDehazing/SFSNiD.py unverified no licence file found · pointer only · 335ddb620cc7ba2f · report
get_network in 100 papers task_SFSNiD/Generate_PseudoLabel.py unverified no licence file found · pointer only · 216c12bf1913751d · 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 Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint (graph method: Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint). 20 bricks; individually on a fixture: 15 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. SFSNiD entry · level 0 · unverified · 335ddb620cc7ba2f
  2. BasicConv helper · level 1 · ran · cf777657fcd4a612
  3. ConvOut_withFFT model · level 1 · ran · 875b657d463b5483
  4. DBlock helper · level 0 · unverified · 10f0475cf68882cf
  5. EBlock helper · level 0 · unverified · 969613da960105c3
  6. FeatureMerge model · level 1 · ran · d07c444c0d226166
  7. SCM_withFFT model · level 1 · ran · 454f7ad32b74b892
  8. ResBlock_Conv model · level 1 · ran · 7b37be285043f2b0
  9. ResBlock helper · level 0 · unverified · 365db0298d2a2932
  10. TransformerBlock model · level 1 · ran · 5a7a00261e5bfad2
  11. Attention helper · level 0 · unverified · 3875f8f476e9b25a
  12. BidomainNonlinearMapping model · level 1 · ran · 45a3ed308b72fa50
  13. BidomainNonlinearMapping_SinglePath helper · level 1 · ran · 87326e31813a4257
  14. WindowAttention helper · level 1 · ran · a6f8738670f038ed
  15. window_partition helper · level 1 · ran; the contract check could not run (RAISES) · 751569c78a842e44
  16. window_reverse helper · level 1 · ran · our draft was wrong · 7b0d02f75bf6b439
  17. Frequency_Spectrum_Dynamic_Aggregation model · level 1 · ran · b2e3910a075de18c
  18. SpaBlock model · level 1 · ran · a4c4157fd5060c95
  19. get_relative_positions helper · level 1 · ran · honoured contract · 2a53db1b6432ab8c
  20. SELayer helper · level 1 · ran · 67adfee5b5d01e0c

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="2403.18548") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image DehazingPseudo Label

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Activation NormalizationAffine CouplingGLOWInvertible 1x1 ConvolutionNormalizing Flows

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