Papers › Neural Painters: A learned differentiable constraint for generating brushstroke paintings

Neural Painters: A learned differentiable constraint for generating brushstroke paintings

17 Apr 2019arXiv:1904.08410archive 2025-07-28

Reiichiro Nakano

We explore neural painters, a generative model for brushstrokes learned from a real non-differentiable and non-deterministic painting program. We show that when training an agent to "paint" images using brushstrokes, using a differentiable neural painter leads to much faster convergence. We propose a method for encouraging this agent to follow human-like strokes when reconstructing digits. We also explore the use of a neural painter as a differentiable image parameterization. By directly optimizing brushstrokes to activate neurons in a pre-trained convolutional network, we can directly visualize ImageNet categories and generate "ideal" paintings of each class. Finally, we present a new concept called intrinsic style transfer. By minimizing only the content loss from neural style transfer, we allow the artistic medium, in this case, brushstrokes, to naturally dictate the resulting style.

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 12 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 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: official repository: 9 samples from 1 repository, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 3 ran (2 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

reiinakano/neural-painters-pytorch officialmentioned on GitHubpytorchMITSyntology: 9 samples, 7 ran (0 instrument-failed) · 2 unverified report
libreai/neural-painters-x mentioned on GitHubtfMITSyntology: not harvested report
shauray8/Neural-Painter mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
t04glovern/neural-painters Syntology: 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.

Code Syntology ran Syntology

12 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 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
9ran
2unverified

Licence: 1 of the 12 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 2 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.

reiinakano/neural-painters-pytorch official repository 9 samples, 7 ran (0 instrument-failed) · 2 unverified
kl_loss_function neural_painters/vae_painter.py ran fingerprinted MIT (permissive) · cd6fdf76fd433706 · report fixture: signature mu:Tensor/2/float, logvar:Tensor/2/float, kl_tolerance:float/0/float, z_size:int/0/int · returned Tensor · level recorded 2026-09-25
load_from_latest_checkpoint neural_painters/gan_painter.py ran MIT (permissive) · 80a2288104dbb177 · report fixture: signature savedir:str/0/str, name:str/0/str, discriminator:callable/0/?, generator:callable/0/?, opt_disc:Adam/0/?, opt_gen:Adam/0/? · returned int · level recorded 2026-09-25
load_from_latest_checkpoint neural_painters/vae_painter.py ran MIT (permissive) · 480c317886270e1d · report fixture: signature savedir:str/0/str, name:str/0/str, encoder:callable/0/?, decoder:callable/0/?, predictor:callable/0/?, optimizer1:Adam/0/?, optimizer2:Adam/0/? · returned int · level recorded 2026-09-25
point_on_curve_1 neural_painters/mypaint_env.py ran MIT (permissive) · 1b08e1e68fe24bfe · report fixture: signature t:float/0/float, cx:float/0/float, cy:float/0/float, sx:float/0/float, sy:float/0/float, x1:float/0/float, y1:float/0/float, x2:float/0/float, y2:float/0/float · returned tuple · level recorded 2026-09-25
point_on_curve_2 neural_painters/mypaint_env.py ran MIT (permissive) · 943d47ec94e2ef34 · report fixture: signature t:float/0/float, cx:float/0/float, cy:float/0/float, sx:float/0/float, sy:float/0/float, kx:float/0/float, ky:float/0/float, x1:float/0/float, y1:float/0/float, x2:float/0/float, y2:float/0/float, x3:float/0/float, y3:float/0/float · returned tuple · level recorded 2026-09-25
reconstruction_loss_function neural_painters/common.py ran MIT (permissive) · 3ce4d1fe2505363f · report fixture: signature recon_x:Tensor/4/float, x:Tensor/4/float, mask_multiplier:float/0/float · returned tuple · level recorded 2026-09-25
starting_point_for_ellipse neural_painters/mypaint_env.py ran fingerprinted MIT (permissive) · fd1539c7b1eb5b85 · report fixture: signature x:float/0/float, y:float/0/float, rotate:float/0/float · returned tuple · level recorded 2026-09-25
calc_gradient_penalty in 16 papers neural_painters/gan_painter.py unverified MIT (permissive) · fd23c3d880c3e469 · report
paint_over_canvas neural_painters/canvas.py unverified MIT (permissive) · d30ffba968994297 · report
shauray8/Neural-Painter community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
get_style_model_and_losses stylized_NP/utils.py ran MIT (permissive) · 55ada60f4f779fd9 · report fixture: signature cnn:callable/0/?, normalization_mean:list/1/float, normalization_std:list/1/float, style_img:Tensor/4/float, content_img:Tensor/4/float, content_layers:list/1/str, style_layers:list/1/str · returned tuple · level recorded 2026-09-24
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
stylized_NP/utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 1090950b58e9358b · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
img_loader in 5 papers stylized_NP/utils.py ran MIT (permissive) · 2de30093c7a77a03 · report fixture: signature image_name:str/0/str, device:str/0/str, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-24

Tasks

Style Transfer

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