Papers › Neural Data-Dependent Transform for Learned Image Compression

Neural Data-Dependent Transform for Learned Image Compression

9 Mar 2022CVPR 2022 1arXiv:2203.04963archive 2025-07-28

Dezhao Wang, Wenhan Yang, Yueyu Hu, Jiaying Liu

Learned image compression has achieved great success due to its excellent modeling capacity, but seldom further considers the Rate-Distortion Optimization (RDO) of each input image. To explore this potential in the learned codec, we make the first attempt to build a neural data-dependent transform and introduce a continuous online mode decision mechanism to jointly optimize the coding efficiency for each individual image. Specifically, apart from the image content stream, we employ an additional model stream to generate the transform parameters at the decoder side. The presence of a model stream enables our model to learn more abstract neural-syntax, which helps cluster the latent representations of images more compactly. Beyond the transform stage, we also adopt neural-syntax based post-processing for the scenarios that require higher quality reconstructions regardless of extra decoding overhead. Moreover, the involvement of the model stream further makes it possible to optimize both the representation and the decoder in an online way, i.e. RDO at the testing time. It is equivalent to a continuous online mode decision, like coding modes in the traditional codecs, to improve the coding efficiency based on the individual input image. The experimental results show the effectiveness of the proposed neural-syntax design and the continuous online mode decision mechanism, demonstrating the superiority of our method in coding efficiency compared to the latest conventional standard Versatile Video Coding (VVC) and other state-of-the-art learning-based methods.

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 22 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 22 samples from 1 repository, 15 ran (14 with no instrument failure; 1 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.

dezhao-wang/neural-syntax-code mentioned on GitHubpytorchSyntology: 22 samples, 15 ran (1 instrument-failed) · 7 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

22 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 7 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 · our draft was wrong
14ran
7unverified

Licence: 22 of the 22 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 dezhao-wang/neural-syntax-code. “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.

dezhao-wang/neural-syntax-code community (archive-listed) 22 samples, 15 ran (1 instrument-failed) · 7 unverified
BlockSample model/net.py ran fingerprinted no licence file found · pointer only · d1e2a6293193620c · report fixture: signature inputs:Tensor/4/float · returned Tensor · level recorded 2026-09-24
CALayer in 11 papers model/net.py ran · metamorphic tier: invariant no licence file found · pointer only · d39eb12b1ecc9aa1 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
CSAM_Module model/net.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 88a9fe0f1292122b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
GDN in 5 papers model/net.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 95cdc4e6ef366f42 · report fixture: signature inputs:Tensor/4/float · returned Tensor · level recorded 2026-09-22
GaussianModel model/net.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 8993c243d7e6e2cd · report fixture: signature inputs:Tensor/2/float, hyper_sigma:Tensor/2/float, hyper_mu:Tensor/2/float · returned Tensor · level recorded 2026-09-22
IGDN model/net.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 2d943519d3acba11 · report fixture: signature inputs:Tensor/4/float · returned Tensor · level recorded 2026-09-22
LAM_Module model/net.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 4c0eb9d9eb46358d · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-22
MeanShift in 7 papers model/net.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 5327003e645d395b · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
RCAB in 6 papers model/net.py ran no licence file found · pointer only · 2a604395051e714e · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
ResidualGroup in 10 papers model/net.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · cec18c5555b8c1aa · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Syntax_Model model/net.py ran no licence file found · pointer only · 282fbe7ce908105b · report fixture: signature syntax:Tensor/4/float · returned Tensor · level recorded 2026-09-24
conv_generator model/net.py ran no licence file found · pointer only · c4e6a11cf4164bb7 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
default_conv in 70 papers model/net.py ran · our draft was wrong no licence file found · pointer only · f7b46e83381fed48 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, bias:bool/0/bool · returned Conv2d · level recorded 2026-09-22
h_analysisTransformModel model/net.py ran no licence file found · pointer only · 765ab977d8d2d905 · report fixture: signature inputs:Tensor/4/float · returned Tensor · level recorded 2026-09-24
h_synthesisTransformModel model/net.py ran no licence file found · pointer only · c7f3b710e8f97e06 · report fixture: signature inputs:Tensor/4/float · returned Tensor · level recorded 2026-09-24
BypassRound model/net.py unverified no licence file found · pointer only · 96c7b860d7bc39b1 · report
LowerBound model/net.py unverified no licence file found · pointer only · 166e353930e98bf5 · report
Net in 54 papers model/net.py unverified no licence file found · pointer only · b8637678e67f9f87 · report
PredictionModel_Context model/net.py unverified no licence file found · pointer only · 18fe91435083b6c8 · report
PredictionModel_Syntax model/net.py unverified no licence file found · pointer only · cfcda6675123b7ba · report
analysisTransformModel model/net.py unverified no licence file found · pointer only · ec6227460005226b · report
synthesisTransformModel model/net.py unverified no licence file found · pointer only · 425a4c231d1d6714 · 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 Neural Data-Dependent Transform (graph method: Neural Data-Dependent Transform). 22 bricks; individually on a fixture: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. Net entry · level 0 · unverified · b8637678e67f9f87
  2. BlockSample helper · level 1 · ran · d1e2a6293193620c
  3. GaussianModel model · level 1 · ran · 8993c243d7e6e2cd
  4. MeanShift helper · level 1 · ran · 5327003e645d395b
  5. PredictionModel_Context model · level 0 · unverified · 18fe91435083b6c8
  6. PredictionModel_Syntax model · level 0 · unverified · cfcda6675123b7ba
  7. Syntax_Model helper · level 1 · ran · 282fbe7ce908105b
  8. analysisTransformModel model · level 0 · unverified · ec6227460005226b
  9. conv_generator helper · level 1 · ran · c4e6a11cf4164bb7
  10. h_analysisTransformModel model · level 1 · ran · 765ab977d8d2d905
  11. h_synthesisTransformModel model · level 1 · ran · c7f3b710e8f97e06
  12. synthesisTransformModel model · level 0 · unverified · 425a4c231d1d6714
  13. GDN model · level 1 · ran · 95cdc4e6ef366f42
  14. IGDN model · level 1 · ran · 2d943519d3acba11
  15. BypassRound helper · level 0 · unverified · 96c7b860d7bc39b1
  16. CALayer helper · level 1 · ran · d39eb12b1ecc9aa1
  17. CSAM_Module helper · level 1 · ran · 88a9fe0f1292122b
  18. LAM_Module helper · level 1 · ran · 4c0eb9d9eb46358d
  19. LowerBound helper · level 0 · unverified · 166e353930e98bf5
  20. RCAB helper · level 1 · ran · 2a604395051e714e
  21. ResidualGroup helper · level 1 · ran · cec18c5555b8c1aa
  22. default_conv helper · level 1 · ran · our draft was wrong · f7b46e83381fed48

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="2203.04963") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderImage Compression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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