Papers › Instance Normalization: The Missing Ingredient for Fast Stylization

Instance Normalization: The Missing Ingredient for Fast Stylization

27 Jul 2016arXiv:1607.08022archive 2025-07-28

Dmitry Ulyanov, Andrea Vedaldi, Victor Lempitsky

It this paper we revisit the fast stylization method introduced in Ulyanov et. al. (2016). We show how a small change in the stylization architecture results in a significant qualitative improvement in the generated images. The change is limited to swapping batch normalization with instance normalization, and to apply the latter both at training and testing times. The resulting method can be used to train high-performance architectures for real-time image generation. The code will is made available on github at https://github.com/DmitryUlyanov/texture_nets. Full paper can be found at arXiv:1701.02096.

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

The archive's official repository (DmitryUlyanov/texture_nets) was not harvested; the 18 samples below come from 3 community repositories.

Syntology 18 code samples harvested from 3 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 2 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): 18 samples from 3 repositories, 16 ran (15 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.

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

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

DmitryUlyanov/texture_nets officialmentioned in papertorchApache-2.0Syntology: not harvested report
Chad4545/styletransfer mentioned on GitHubpytorchSyntology: not harvested report
HarmanDotpy/Normalizations-in-Deep-Learning mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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) and Layer Normalization (arXiv:1607.06450; that paper's own run record: 7 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
MarvinLavechin/imagetranslation-tensorflow mentioned on GitHubtfSyntology: not harvested report
Net-Mist/style-transfer-tf2 mentioned on GitHubtfMITSyntology: 11 samples, 11 ran (0 instrument-failed) · 0 unverified report
aryan-mann/style-transfer mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Neural Algorithm of Artistic Style (arXiv:1508.06576; that paper's own run record: 76 ran (of which 0 constructed an object rather than computing a result; 44 with no instrument failure: 7 honoured, 3 violated, 34 with no contract checked; 32 where Syntology's instrument failed) · 34 unverified); nothing checks that they implement this paper's method. report
brightyoun/Video-Style-Transfer mentioned on GitHubpytorchMITSyntology: 4 samples, 3 ran (1 instrument-failed) · 1 unverified report
buddly27/stylish mentioned on GitHubSyntology: not harvested report
cryu854/FastStyle mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Perceptual Losses for Real-Time Style Transfer and Super-Resolution (arXiv:1603.08155; that paper's own run record: 34 ran (of which 0 constructed an object rather than computing a result; 26 with no instrument failure: 2 honoured, 2 violated, 22 with no contract checked; 8 where Syntology's instrument failed) · 12 unverified); nothing checks that they implement this paper's method. report
cryu854/SinGAN mentioned on GitHubtfSyntology: not harvested report
etttttte/mayfest2018 mentioned on GitHubpytorchSyntology: not harvested report
hollygrimm/cyclegan-keras-art-attrs mentioned on GitHubMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
jcjohnson/fast-neural-style mentioned on GitHubtorchSyntology: not harvested report
lengstrom/fast-style-transfer mentioned on GitHubtfSyntology: not harvested report
milmor/perceptual-losses-neural-style mentioned on GitHubtfSyntology: not harvested report
riven314/PerceptualLoss-FastAI mentioned on GitHubpytorchSyntology: not harvested report
sundogai/style-transfer mentioned on GitHubtfSyntology: not harvested report
tbullmann/imagetranslation-tensorflow mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
the-super-toys/glimpse-models mentioned on GitHubpytorchSyntology: not harvested report
yakhyo/Fast-Neural-Style-Transfer mentioned on GitHubpytorchSyntology: not harvested report
labmlai/annotated_deep_learning_paper_implementations pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified), Adam: A Method for Stochastic Optimization (arXiv:1412.6980; that paper's own run record: 27 ran (of which 7 constructed an object rather than computing a result; 23 with no instrument failure: 4 honoured, 2 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified), 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) and 12 more (every one in this page's JSON twin); 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

18 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 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 · our draft was wrong
15ran
2unverified

Licence: 1 of the 18 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 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. “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.

Net-Mist/style-transfer-tf2 community (archive-listed) 11 samples, 11 ran (0 instrument-failed) · 0 unverified
abs_criterion src/losses.py ran MIT (permissive) · 54e8627bef847403 · report fixture: signature logits:EagerTensor/2/float, target:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26
bytes_feature in 12 papers src/tfrecord.py ran MIT (permissive) · d682a9593710857e · report fixture: signature value:bytes/0/? · returned Feature · level recorded 2026-09-25
discriminator_loss in 38 papers src/losses.py ran MIT (permissive) · 4d3711e216e605bf · report fixture: signature discriminate_encoded_picture:list/1/EagerTensor, discriminate_picture:list/1/EagerTensor, discriminate_art:list/1/EagerTensor · returned tuple · level recorded 2026-09-26
image_postprocess src/inference.py ran MIT (permissive) · 35d23f8a7f5739a1 · report fixture: signature image:ndarray/4/float · returned ndarray · level recorded 2026-09-26
image_preprocess in 7 papers src/inference.py ran MIT (permissive) · 4ad5af47aa088209 · report fixture: signature image:ndarray/3/int, resized_shape:tuple/1/int · returned ndarray · level recorded 2026-09-26
int64_feature in 12 papers src/tfrecord.py ran MIT (permissive) · 328d17201d9a0e68 · report fixture: signature value:int/0/int · returned Feature · level recorded 2026-09-25
int64_list_feature in 6 papers src/tfrecord.py ran MIT (permissive) · f6d735872f4495ed · report fixture: returned Feature · level recorded 2026-09-25
inverted_res_block src/model.py ran MIT (permissive) · f169004dc49d5433 · report fixture: signature inputs:EagerTensor/4/float, stride:int/0/int, in_channels:int/0/int, out_channels:int/0/int, norm_layer:callable/0/?, expansion:int/0/int · returned SymbolicTensor · level recorded 2026-09-26
make_encoder_model_adaptive_style_transfer src/model.py ran MIT (permissive) · 4cd71027cd44ac18 · report fixture: signature norm_layer:callable/0/? · returned Sequential · level recorded 2026-09-26
mse_criterion src/losses.py ran MIT (permissive) · 25abb9d374dd012a · report fixture: signature logits:SymbolicTensor/2/float, target:SymbolicTensor/2/float · returned EagerTensor · level recorded 2026-09-26
relu6 in 14 papers src/model.py ran fingerprinted MIT (permissive) · 4ab5b6864f23abf4 · report fixture: signature x:EagerTensor/2/float · returned SymbolicTensor · level recorded 2026-09-26
brightyoun/Video-Style-Transfer community (archive-listed) 4 samples, 3 ran (1 instrument-failed) · 1 unverified
gram_matrix in 45 papers
census: 7 implementations from 9 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 430c582cd8bbb1df · report fixture: signature y:Tensor/4/float · returned Tensor · level recorded 2026-09-22
load_image in 273 papers utils.py ran MIT (permissive) · 698dca7627594fdb · report fixture: signature filename:str/0/str, size:NoneType/0/?, scale:NoneType/0/? · returned PngImageFile · level recorded 2026-09-26
normalize_batch in 9 papers utils.py ran fingerprinted MIT (permissive) · 844101ff39c69346 · report fixture: signature batch:Tensor/4/float · returned Tensor · level recorded 2026-09-26
stylize_onnx_caffe2 neural_style.py unverified MIT (permissive) · 33bdd8217a2859e8 · report
hollygrimm/cyclegan-keras-art-attrs community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
get_config_from_json in 6 papers utils/utils.py ran MIT (permissive) · f31979b7dfe88d5e · report fixture: signature json_file:str/0/str · returned dict · level recorded 2026-09-26
process_config in 13 papers utils/utils.py ran MIT (permissive) · 7081cbaca5dca320 · report fixture: signature json_file:str/0/str · returned dict · level recorded 2026-09-26
create_dirs in 6 papers utils/utils.py unverified MIT (permissive) · 83c24e1bbc6c05f7 · report

Tasks

Image GenerationImage StylizationStyle Transfer

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Instance Normalization

Batch NormalizationInstance Normalization

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