Papers › DRAW: A Recurrent Neural Network For Image Generation

DRAW: A Recurrent Neural Network For Image Generation

16 Feb 2015arXiv:1502.04623archive 2025-07-28

Karol Gregor, Ivo Danihelka, Alex Graves, Danilo Jimenez Rezende, Daan Wierstra

This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential variational auto-encoding framework that allows for the iterative construction of complex images. The system substantially improves on the state of the art for generative models on MNIST, and, when trained on the Street View House Numbers dataset, it generates images that cannot be distinguished from real data with the naked eye.

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 18 code samples: 17 from 7 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 18: 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 17 samples from 7 repositories, 8 ran (2 with no instrument failure; 6 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 2 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. 1 of the 9 samples that ran has no recorded date.

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

MoustafaMeshry/draw mentioned on GitHubtfApache-2.0Syntology: 4 samples, 1 ran (0 instrument-failed) · 3 unverified report
Natsu6767/Generating-Devanagari-Using-DRAW mentioned on GitHubpytorchSyntology: not harvested report
csiki/v2a mentioned on GitHubtfSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
czm0/draw_pytorch mentioned on GitHubpytorchSyntology: not harvested report
deladurantayefrancis/DRAW_Architecture mentioned on GitHubpytorchSyntology: not harvested report
ericjang/draw mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
hrbigelow/draw mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Auto-Encoding Variational Bayes (arXiv:1312.6114; that paper's own run record: 140 ran (of which 52 constructed an object rather than computing a result; 120 with no instrument failure: 4 honoured, 2 violated, 114 with no contract checked; 20 where Syntology's instrument failed) · 59 unverified); nothing checks that they implement this paper's method. report
jameskokoska/rvl mentioned on GitHubSyntology: not harvested report
jbornschein/draw mentioned on GitHubMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
jlindsey15/DRAM mentioned on GitHubtfSyntology: 3 samples, 0 ran · 3 unverified report
nHeidelberg/Pytorch-Implementation-DRAW mentioned on GitHubpytorchSyntology: not harvested report
numberlearning/DRAM mentioned on GitHubtfSyntology: not harvested report
ptigas/gatsby-remark-bibliography mentioned on GitHubMITSyntology: not harvested report
seohuibae/VAE_DRAW mentioned on GitHubpytorchSyntology: not harvested report
simonamtoft/ml-library mentioned on GitHubpytorchSyntology: not harvested report
singhsidhukuldeep/Generating-Devanagari-Using-DRAW mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 0 ran · 1 unverified report
suhoy901/DRAW_pytorch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
unixpickle/vq-draw mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Neural Discrete Representation Learning (arXiv:1711.00937; that paper's own run record: 64 ran (of which 35 constructed an object rather than computing a result; 60 with no instrument failure: 0 honoured, 0 violated, 60 with no contract checked; 4 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
vivanov879/draw mentioned on GitHubtorchSyntology: not harvested report
yashkalani/DRAW mentioned on GitHubtfSyntology: not harvested 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: 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 9 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 · violated contract
6ran · our draft was wrong
2ran
9unverified

Licence: 9 of the 18 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 7 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. 1 sample is listed last, in a group without a repository. “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.

MoustafaMeshry/draw community (archive-listed) 4 samples, 1 ran (0 instrument-failed) · 3 unverified
xrecons_grid plot_data.py ran Apache-2.0 (permissive) · 99b9ef9642c40ab7 · report fixture: signature X:ndarray/2/float, B:int/0/int, A:int/0/int · returned ndarray · level recorded 2026-09-26
filter_response2histogram texture_loss.py unverified Apache-2.0 (permissive) · 1b185012743ad260 · report
filterbank draw.py unverified Apache-2.0 (permissive) · 0108c9c4f32a89d6 · report
im2filter_response texture_loss.py unverified Apache-2.0 (permissive) · 025b5b9515188170 · report
csiki/v2a community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
find_model in 25 papers config.py ran · our draft was wrong no licence file found · pointer only · 330f6334fb6a3c24 · report fixture: signature cfg_id:str/0/str, model_name_postfix:str/0/str · returned str · level recorded 2026-09-22
load_config in 389 papers config.py ran · our draft was wrong no licence file found · pointer only · 5e0281ad454dfda9 · report fixture: signature cfg_id:str/0/str · returned dict · level recorded 2026-09-22
ericjang/draw community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
xrecons_grid plot_data.py ran · our draft was wrong Apache-2.0 (permissive) · a240a4e67c3c2f4a · report fixture: signature X:ndarray/2/float, B:int/0/int, A:int/0/int · returned ndarray · level recorded 2026-09-22
jbornschein/draw community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
scale_norm sample.py ran fingerprinted MIT (permissive) · fa5a89b0a62ca754 · report fixture: signature arr:ndarray/1/float · returned ndarray · level recorded 2026-09-26
img_grid sample.py unverified MIT (permissive) · 52d20b4814d29ddf · report
my_batched_dot draw/attention.py unverified MIT (permissive) · c39a03ce39200cdf · report
jlindsey15/DRAM community (archive-listed) 3 samples, 0 ran · 3 unverified
add_distortions DRAMVAEGAN/DRAMLearnedMetric.py unverified no licence file found · pointer only · adc0d1230b0b39b0 · report
convertTranslated DRAMVAEGAN/DRAMLearnedMetric.py unverified no licence file found · pointer only · 18f407725809c356 · report
create_sample in 5 papers DRAMVAEGAN/DRAMLearnedMetric.py unverified no licence file found · pointer only · 0942eff650073076 · report
singhsidhukuldeep/Generating-Devanagari-Using-DRAW community (archive-listed) 1 sample, 0 ran · 1 unverified
get_data in 223 papers dataloader.py unverified Apache-2.0 (permissive) · 05b9fee23508018c · report
suhoy901/DRAW_pytorch community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
Variable utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · fa0f1cbd96734e5f · report fixture: signature data:Tensor/2/float, requires_grad:bool/0/bool · returned Tensor · level recorded 2026-09-22
align in 23 papers utils.py ran · our draft was wrong no licence file found · pointer only · 13490b546e6d33df · report fixture: signature x:Tensor/3/float, y:Tensor/3/float, start_dim:int/0/int · returned tuple · level recorded 2026-09-22
unit_prefix utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 070e898b844d8b61 · report fixture: signature x:Tensor/3/float, n:int/0/int · returned Tensor · level recorded 2026-09-22
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
str2bool in 533 papers repository not located ran · violated contract licence of this copy not recorded · 25c7475539e39da4 · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded

Tasks

FoveationImage Generation

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