Papers › Pixel Recurrent Neural Networks

Pixel Recurrent Neural Networks

25 Jan 2016arXiv:1601.06759archive 2025-07-28

Aaron van den Oord, Nal Kalchbrenner, Koray Kavukcuoglu

Modeling the distribution of natural images is a landmark problem in unsupervised learning. This task requires an image model that is at once expressive, tractable and scalable. We present a deep neural network that sequentially predicts the pixels in an image along the two spatial dimensions. Our method models the discrete probability of the raw pixel values and encodes the complete set of dependencies in the image. Architectural novelties include fast two-dimensional recurrent layers and an effective use of residual connections in deep recurrent networks. We achieve log-likelihood scores on natural images that are considerably better than the previous state of the art. Our main results also provide benchmarks on the diverse ImageNet dataset. Samples generated from the model appear crisp, varied and globally coherent.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1601.06759")

Code

Syntology Ran 19 of 29 code samples harvested from 9 repositories linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 17 ran with no contract checked.

By repository: community (archive-listed): 28 samples from 9 repositories, 18 ran; 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.

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

anordertoreclaim/PixelCNN mentioned on GitHubpytorch report
apple/ml-tarflow mentioned on GitHubpytorch report
arcelien/hawc-deep-learning mentioned on GitHubpytorch report
ardapekis/pixel-rnn mentioned on GitHubpytorch report
davidemartinelli/PixelCNN mentioned on GitHubpytorch report
doiodl/pixelcnn-rnn mentioned on GitHubtf report
encoreus/gs-jacobi_for_tarflow mentioned on GitHubpytorch report
eyalbetzalel/pytorch-generative mentioned on GitHubpytorchMIT report
eyalbetzalel/pytorch-generative-v2 mentioned on GitHubpytorchMIT report
eyalbetzalel/pytorch-generative-v6 mentioned on GitHubpytorch report
guguguzi/PixelCNN-Paddle mentioned on GitHubpaddle report
jzbontar/pixelcnn-pytorch mentioned on GitHubpytorchMIT report
kamenbliznashki/pixel_models mentioned on GitHubpytorch report
rampage644/wavenet mentioned on GitHubtfApache-2.0 report
singh-hrituraj/PixelCNN-Pytorch mentioned on GitHubpytorch report
tccnchsu/Artifical_Intelegent mentioned on GitHubtf report
vocong25/gated_pixelcnn mentioned on GitHubtf 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

29 samples harvested; 19 ran; 1 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
17ran
10unverified

Licence: 18 of the 29 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 9 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

Attention encoreus/gs-jacobi_for_tarflow/GS_Jacobi_sampling.py community (archive-listed) ran Apache-2.0 (permissive) · ee4de74c78e0ecd2 · report
AttentionBlock apple/ml-tarflow/transformer_flow.py community (archive-listed) ran licence not identified · pointer only · aa9665d69388677d · report
AttentionBlock encoreus/gs-jacobi_for_tarflow/GS_Jacobi_sampling.py community (archive-listed) ran Apache-2.0 (permissive) · 6aef5991dfa3ccc8 · report
AutoregressiveConv2d davidemartinelli/PixelCNN/model.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 41a11662f8a6cbb5 · report
CausalBlock anordertoreclaim/PixelCNN/pixelcnn/model.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · a8017d58021d4dc8 · report
CroppedConv2d anordertoreclaim/PixelCNN/pixelcnn/model.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 593a9e5f68282f1d · report
DiagonalPixelLSTM ardapekis/pixel-rnn/model/pixel_lstm/pixel_lstm.py community (archive-listed) ran fingerprinted MIT (permissive) · adeb3b3f5a65c9a0 · report
GatedBlock anordertoreclaim/PixelCNN/pixelcnn/model.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · f64383cb16b99391 · report
GatedResidualLayer kamenbliznashki/pixel_models/pixelcnn.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 67b63a90ba65215a · report
MaskedCNN singh-hrituraj/PixelCNN-Pytorch/Model.py community (archive-listed) ran fingerprinted GPL-3.0 (copyleft) · pointer only · 9eee86fe94d2086a · report
MaskedConv2D sarus-tech/tf2-published-models/gated_pixelcnn/model.py community (archive-listed) ran Apache-2.0 (permissive) · fd12e6cc443d7970 · report
MaskedConv2d anordertoreclaim/PixelCNN/pixelcnn/model.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · f3742ce708e8768a · report
MaskedConv2d kamenbliznashki/pixel_models/pixelcnn.py community (archive-listed) ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 4b84e15d943e0dd1 · report
MetaBlock apple/ml-tarflow/transformer_flow.py community (archive-listed) ran licence not identified · pointer only · 4df96ba87d897b77 · report
PixelCNN singh-hrituraj/PixelCNN-Pytorch/Model.py community (archive-listed) ran GPL-3.0 (copyleft) · pointer only · a0639ec87bba3e75 · report
PixelCNN kamenbliznashki/pixel_models/pixelcnn.py community (archive-listed) ran fingerprinted no licence file found · pointer only · c3dfea750f64035b · report
skew ardapekis/pixel-rnn/model/pixel_lstm/pixel_lstm.py community (archive-listed) ran fingerprinted MIT (permissive) · 1e11b6acedaae400 · report
unskew ardapekis/pixel-rnn/model/pixel_lstm/pixel_lstm.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 0e0dc604aafd609a · report
Attention apple/ml-tarflow/transformer_flow.py community (archive-listed) unverified licence not identified · pointer only · 7eca12f0033fe394 · report
GatedPixelCNN sarus-tech/tf2-published-models/gated_pixelcnn/model.py community (archive-listed) unverified Apache-2.0 (permissive) · 641b0eb982592cc1 · report
MetaBlock encoreus/gs-jacobi_for_tarflow/GS_Jacobi_sampling.py community (archive-listed) unverified Apache-2.0 (permissive) · 7fc2dc61763b0f75 · report
Model apple/ml-tarflow/transformer_flow.py community (archive-listed) unverified licence not identified · pointer only · 55440bb0facb712e · report
Model encoreus/gs-jacobi_for_tarflow/GS_Jacobi_sampling.py community (archive-listed) unverified Apache-2.0 (permissive) · d605fe24beaa94bc · report
Network vocong25/gated_pixelcnn/network.py community (archive-listed) unverified Apache-2.0 (permissive) · 89a37aa23360cbd5 · report
PixelCNN davidemartinelli/PixelCNN/model.py community (archive-listed) unverified no licence file found · pointer only · faf32f2d8a81d283 · report
PixelCNN anordertoreclaim/PixelCNN/pixelcnn/model.py community (archive-listed) unverified no licence file found · pointer only · 54596247934223eb · report
ResidualBlock sarus-tech/tf2-published-models/gated_pixelcnn/model.py community (archive-listed) unverified Apache-2.0 (permissive) · 3dfb65c9576dbca8 · report
get_gpu_memory_map davidemartinelli/PixelCNN/model.py community (archive-listed) unverified no licence file found · pointer only · 347b676bc02e2b59 · report
pixelcnn_gate identical code first harvested elsewhere ran · honoured contract fingerprinted licence of this copy not recorded · 68cdfbf37a172d13 · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation Binarized MNIST PixelRNN nats 79.20 #5 of 10 Archive leaderboard report
Image Generation Binarized MNIST PixelCNN nats 81.30 #6 of 10 Archive leaderboard report
Image Generation ImageNet 32x32 PixelRNN bpd 3.86 #28 of 35 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: Masked Convolution, PixelCNN, PixelRNN

LSTMMasked ConvolutionPixelCNNPixelRNNSigmoid ActivationTanh Activation

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