Papers › End-to-end Optimized Image Compression

End-to-end Optimized Image Compression

5 Nov 2016arXiv:1611.01704archive 2025-07-28

Johannes Ballé, Valero Laparra, Eero P. Simoncelli

We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation. The transforms are constructed in three successive stages of convolutional linear filters and nonlinear activation functions. Unlike most convolutional neural networks, the joint nonlinearity is chosen to implement a form of local gain control, inspired by those used to model biological neurons. Using a variant of stochastic gradient descent, we jointly optimize the entire model for rate-distortion performance over a database of training images, introducing a continuous proxy for the discontinuous loss function arising from the quantizer. Under certain conditions, the relaxed loss function may be interpreted as the log likelihood of a generative model, as implemented by a variational autoencoder. Unlike these models, however, the compression model must operate at any given point along the rate-distortion curve, as specified by a trade-off parameter. Across an independent set of test images, we find that the optimized method generally exhibits better rate-distortion performance than the standard JPEG and JPEG 2000 compression methods. More importantly, we observe a dramatic improvement in visual quality for all images at all bit rates, which is supported by objective quality estimates using MS-SSIM.

PaperPDFCodeCode Syntology ran

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 4 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 20 samples from 4 repositories, 14 ran (12 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.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 14 samples that ran have no recorded date.

14 repositories listed; official and paper-mentioned ones first.

FireFYF/SlimCAE mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Slimmable Compressive Autoencoders for Practical Neural Image Compression (arXiv:2103.15726; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
FireFYF/modulatedautoencoder mentioned on GitHubtfSyntology: not harvested report
faymek/compression mentioned on GitHubtfnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
gergely-flamich/relative-entropy-coding mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ipc-lab/DWSIC mentioned on GitHubpytorchMITSyntology: not harvested report
ipc-lab/NDIC mentioned on GitHubpytorchMITSyntology: not harvested report
ipc-lab/ndic-cam mentioned on GitHubpytorchSyntology: not harvested report
jorge-pessoa/pytorch-gdn mentioned on GitHubpytorchMITSyntology: not harvested report
liujiaheng/iclr_17_compression mentioned on GitHubpytorchMITSyntology: 12 samples, 6 ran (0 instrument-failed) · 6 unverified report
tensorflow/compression mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Introduction to Neural Data Compression (arXiv:2202.06533; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
treammm/Compression mentioned on GitHubtfApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
InterDigitalInc/CompressAI pytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
zhuyuhua1/contrib mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Density Adaptive Attention is All You Need: Robust Parameter-Efficient Fine-Tuning... (arXiv:2401.11143; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

20 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 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 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.

2ran · violated contract
2ran · our draft was wrong
10ran
6unverified

Licence: 4 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 4 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. 4 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another 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. 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.

gergely-flamich/relative-entropy-coding community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
print_dict in 7 papers examples/lossless/train_generative_model.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 73b28d07dc4d8995 · report fixture: signature d:dict/0/? · returned str · level recorded, date not recorded
liujiaheng/iclr_17_compression community (archive-listed) 12 samples, 6 ran (0 instrument-failed) · 6 unverified
CalcuPSNR models/basics.py ran fingerprinted MIT (permissive) · c9947c33e3a54f62 · report fixture: signature target:ndarray/2/float, ref:ndarray/2/float · returned float · level recorded 2026-09-24
gaussian_filter in 21 papers models/ms_ssim_torch.py ran MIT (permissive) · 569f86999a28550f · report fixture: signature input:Tensor/4/float, win:Tensor/4/float · returned Tensor · level recorded 2026-09-25
get_loader in 62 papers datasets.py ran MIT (permissive) · 330dd4378c3e3a35 · report fixture: signature train_data_dir:str/0/str, test_data_dir:str/0/str, image_size:int/0/int, batch_size:int/0/int · returned tuple · level recorded 2026-09-24
get_train_loader in 12 papers datasets.py ran MIT (permissive) · 4e3ec336e202299e · report fixture: signature train_data_dir:str/0/str, image_size:int/0/int, batch_size:int/0/int · returned tuple · level recorded 2026-09-24
relu in 58 papers
census: 8 implementations from 11 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
models/basics.py ran fingerprinted MIT (permissive) · ba24f201a717509b · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
ssim in 112 papers models/ms_ssim_torch.py ran MIT (permissive) · d9e269e86cc2b394 · report fixture: signature X:Tensor/4/float, Y:Tensor/4/float, win_size:int/0/int, win_sigma:float/0/float, win:NoneType/0/?, data_range:int/0/int, size_average:bool/0/bool, full:bool/0/bool · returned Tensor · level recorded 2026-09-24
MultiScaleSSIM in 5 papers metric.py unverified MIT (permissive) · a5a05f863cc1b904 · report
load_model in 479 papers model.py unverified MIT (permissive) · 67b83d1f47e01c3f · report
ms_ssim in 10 papers models/ms_ssim_torch.py unverified MIT (permissive) · 7ea107a5705e6f95 · report
msssim metric.py unverified MIT (permissive) · c46a2076f53009e8 · report
yuv_import_444 models/basics.py unverified MIT (permissive) · 2784ebaef09c1269 · report
treammm/Compression community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
irdft_matrix tensorflow_compression/python/ops/spectral_ops.py ran Apache-2.0 (permissive) · e1be96227f48724d · report fixture: signature shape:tuple/1/int, dtype:DType/0/? · returned EagerTensor · level recorded 2026-09-26
lower_bound tensorflow_compression/python/ops/math_ops.py ran Apache-2.0 (permissive) · a863fa9d143a5fb3 · report fixture: signature inputs:EagerTensor/2/float, bound:EagerTensor/0/float, gradient:str/0/str, name:str/0/str · returned EagerTensor · level recorded 2026-09-26
same_padding_for_kernel tensorflow_compression/python/ops/padding_ops.py ran Apache-2.0 (permissive) · 680ff131d22fbc0b · report fixture: signature shape:tuple/1/int, corr:bool/0/bool, strides_up:tuple/1/int · returned list · level recorded 2026-09-26
upper_bound tensorflow_compression/python/ops/math_ops.py ran Apache-2.0 (permissive) · fc9f7ea55d17f349 · report fixture: signature inputs:EagerTensor/2/float, bound:EagerTensor/0/float, gradient:str/0/str, name:str/0/str · returned EagerTensor · level recorded 2026-09-26
InterDigitalInc/CompressAI community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
Average in 8 papers examples/codec.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · violated contract fingerprinted licence of this copy not recorded · 390aec91fdddfcac · report fixture: signature lst:list/1/int · returned float · level recorded, date not recorded
BoolConvert examples/codec.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · violated contract fingerprinted licence of this copy not recorded · d729e65bfe314ae3 · report fixture: signature a:int/0/int · returned bool · level recorded, date not recorded
inverse_dict in 5 papers examples/codec.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 5dff248eb7143d81 · report fixture: signature d:dict/0/? · returned dict · level recorded, date not recorded

Tasks

Image CompressionMS-SSIMSSIM

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