Papers › Spectrum Translation for Refinement of Image Generation (STIG) Based on Contrastive...

Spectrum Translation for Refinement of Image Generation (STIG) Based on Contrastive Learning and Spectral Filter Profile

8 Mar 2024arXiv:2403.05093archive 2025-07-28

SeokJun Lee, Seung-Won Jung, Hyunseok Seo

Currently, image generation and synthesis have remarkably progressed with generative models. Despite photo-realistic results, intrinsic discrepancies are still observed in the frequency domain. The spectral discrepancy appeared not only in generative adversarial networks but in diffusion models. In this study, we propose a framework to effectively mitigate the disparity in frequency domain of the generated images to improve generative performance of both GAN and diffusion models. This is realized by spectrum translation for the refinement of image generation (STIG) based on contrastive learning. We adopt theoretical logic of frequency components in various generative networks. The key idea, here, is to refine the spectrum of the generated image via the concept of image-to-image translation and contrastive learning in terms of digital signal processing. We evaluate our framework across eight fake image datasets and various cutting-edge models to demonstrate the effectiveness of STIG. Our framework outperforms other cutting-edges showing significant decreases in FID and log frequency distance of spectrum. We further emphasize that STIG improves image quality by decreasing the spectral anomaly. Additionally, validation results present that the frequency-based deepfake detector confuses more in the case where fake spectrums are manipulated by STIG.

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 20 code samples harvested from 1 repository linked to this paper: 18 ran (of which 8 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 18 ran (11 with no instrument failure; 7 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.

ykykyk112/STIG officialpytorchSyntology: 20 samples, 18 ran (7 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

20 samples harvested: 18 ran (of which 8 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 2 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.

1ran · honoured contract
1ran · violated contract
7ran · our draft was wrong
9ran
2unverified

Licence: 20 of the 20 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 ykykyk112/STIG. “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.

ykykyk112/STIG official repository 20 samples, 18 ran (7 instrument-failed) · 2 unverified
Dis_block model/stig_model.py ran fingerprinted no licence file found · pointer only · bc08847f1f14b16a · report fixture: returned Dis_block · level recorded 2026-09-22
LFLoss model/stig_model.py ran fingerprinted no licence file found · pointer only · d2430db1bcbe36b4 · report fixture: signature src_magnitude:Tensor/4/float, tgt_magnitude:Tensor/4/float · returned Tensor · level recorded 2026-09-24
NestedUNet model/stig_model.py ran no licence file found · pointer only · d57261e37a47d29a · report fixture: returned NestedUNet · level recorded 2026-09-22
PatchDiscriminator model/stig_model.py ran no licence file found · pointer only · ac50b6e3b07f7b21 · report fixture: returned PatchDiscriminator · level recorded 2026-09-22
PatchNCELoss model/stig_model.py ran fingerprinted no licence file found · pointer only · dbe3805241714b39 · report fixture: returned PatchNCELoss · level recorded 2026-09-22
PatchSampleF model/stig_model.py ran no licence file found · pointer only · 33105c2f7e3b2eaa · report fixture: returned PatchSampleF · level recorded 2026-09-22
RectAverage model/stig_model.py ran no licence file found · pointer only · bed91f63e5ea38ce · report fixture: returned RectAverage · level recorded 2026-09-22
SSIM in 17 papers model/stig_model.py ran fingerprinted no licence file found · pointer only · 601a8fd30557fb04 · report fixture: returned SSIM · level recorded 2026-09-22
VGGBlock model/stig_model.py ran fingerprinted no licence file found · pointer only · 9213dc7a6ef0f1fa · report fixture: returned VGGBlock · level recorded 2026-09-22
fft2polar model/stig_model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · b94669b3298f1041 · report fixture: signature fft:Tensor/2/complex · returned tuple · level recorded 2026-09-22
get_magnitude model/stig_model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 0324dfc33fe509e2 · report fixture: signature img:Tensor/4/float · returned Tensor · level recorded 2026-09-22
get_norm_layer in 111 papers model/stig_model.py ran · our draft was wrong no licence file found · pointer only · 02554999a2d262c8 · report fixture: signature norm_type:str/0/str · returned partial · level recorded 2026-09-22
image_normalize model/stig_model.py ran · violated contract fingerprinted no licence file found · pointer only · 6cb3bd42770435d6 · report fixture: signature image:Tensor/4/float · returned Tensor · level recorded 2026-09-22
img2fft model/stig_model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 5c36ba8cd2e75e93 · report fixture: signature img:Tensor/4/float · returned Tensor · level recorded 2026-09-22
init_net in 47 papers model/stig_model.py ran · our draft was wrong no licence file found · pointer only · 761ab5993058b5ed · report fixture: signature net:callable/0/?, init_type:str/0/str, init_gain:float/0/float, debug:bool/0/bool, initialize_weights:bool/0/bool · returned SimpleNet · level recorded 2026-09-22
inverse_normalize in 5 papers model/stig_model.py ran · honoured contract fingerprinted no licence file found · pointer only · 65d0fbc5be44d148 · report fixture: signature tensor:Tensor/2/float, v_max:float/0/float, v_min:float/0/float · returned Tensor · level recorded 2026-09-22
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
model/stig_model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 11ed20dd1b6821cc · report fixture: signature tensor:Tensor/2/float · returned tuple · level recorded 2026-09-22
polar2img model/stig_model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 485009e439d42988 · report fixture: signature magnitude:Tensor/3/float, phase:Tensor/3/float · returned Tensor · level recorded 2026-09-22
STIG model/stig_model.py unverified no licence file found · pointer only · 8f35e19d434ddfe9 · report
init_weights in 109 papers model/stig_model.py unverified no licence file found · pointer only · 7d2a877dc81eba70 · 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 Spectrum Translation for Refinement of Image Generation (STIG) (graph method: Spectrum Translation for Refinement of Image Generation (STIG)). 25 bricks; individually on a fixture: 23 ran (of which 9 constructed an object rather than computing a result; 15 with no instrument failure: 3 honoured, 1 violated, 11 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. STIG entry · level 0 · unverified · 8f35e19d434ddfe9
  2. LFLoss loss · level 1 · ran · d2430db1bcbe36b4
  3. NestedUNet helper · level 1 · ran · d57261e37a47d29a
  4. PatchDiscriminator helper · level 1 · ran · ac50b6e3b07f7b21
  5. PatchNCELoss helper · level 1 · ran · dbe3805241714b39
  6. PatchSampleF helper · level 1 · ran · 33105c2f7e3b2eaa
  7. RectAverage helper · level 1 · ran · bed91f63e5ea38ce
  8. SSIM helper · level 1 · ran · 601a8fd30557fb04
  9. fft2polar helper · level 1 · ran · our draft was wrong · b94669b3298f1041
  10. get_magnitude helper · level 1 · ran · our draft was wrong · 0324dfc33fe509e2
  11. get_norm_layer helper · level 1 · ran · our draft was wrong · 02554999a2d262c8
  12. image_normalize helper · level 1 · ran · violated contract · 6cb3bd42770435d6
  13. img2fft helper · level 1 · ran · our draft was wrong · 5c36ba8cd2e75e93
  14. init_net helper · level 1 · ran · our draft was wrong · 761ab5993058b5ed
  15. inverse_normalize helper · level 1 · ran · honoured contract · 65d0fbc5be44d148
  16. normalize helper · level 1 · ran · our draft was wrong · 11ed20dd1b6821cc
  17. polar2img helper · level 1 · ran · our draft was wrong · 485009e439d42988
  18. VGGBlock helper · level 1 · ran · 9213dc7a6ef0f1fa
  19. Dis_block helper · level 1 · ran · bc08847f1f14b16a
  20. Normalize helper · level 1 · ran · c48872b4c38c1e7a
  21. _ssim helper · level 1 · ran · our draft was wrong · 3f9ebae7bfc1584d
  22. create_window helper · level 1 · ran · honoured contract · 6154e3744ece5728
  23. Identity helper · level 1 · ran · cefafcb412701ad5
  24. init_weights helper · level 0 · unverified · 7d2a877dc81eba70
  25. gaussian helper · level 1 · ran · honoured contract · c56b7ef16f309a45

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="2403.05093") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningFace SwappingImage GenerationImage-to-Image TranslationTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive LearningDiffusion

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