Methods › Computer Vision › Likelihood-Based Generative Models › PixelCNN
PixelCNN
Introduced by Aaron van den Oord et al. in Pixel Recurrent Neural Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A PixelCNN is a generative model that uses autoregressive connections to model images pixel by pixel, decomposing the joint image distribution as a product of conditionals. PixelCNNs are much faster to train than PixelRNNs because convolutions are inherently easier to parallelize; given the vast number of pixels present in large image datasets this is an important advantage.
Papers archive 2025-07-28
30 shown of 45, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models 14 Mar 2025 · 0 repositories · arXiv:2503.11513
-
PixelBytes: Catching Unified Representation for Multimodal Generation 16 Sep 2024 · 1 repository · arXiv:2410.01820
-
PixelBytes: Catching Unified Embedding for Multimodal Generation 3 Sep 2024 · 1 repository · arXiv:2409.15512
-
SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks 28 Jan 2024 · 2 repositories · arXiv:2401.15741
-
An attempt to generate new bridge types from latent space of PixelCNN 11 Jan 2024 · 1 repository · arXiv:2401.05964
-
Deep autoregressive modeling for land use land cover 2 Jan 2024 · 0 repositories · arXiv:2401.01395
-
HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes 31 Dec 2023 · 0 repositories · arXiv:2401.00365
-
SeaDSC: A video-based unsupervised method for dynamic scene change detection in unmanned surface vehicles 20 Nov 2023 · 0 repositories · arXiv:2311.11580
-
S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction 13 Jul 2023 · 0 repositories · arXiv:2307.06701
-
Phased Data Augmentation for Training a Likelihood-Based Generative Model with Limited Data 22 May 2023 · 0 repositories · arXiv:2305.12681
-
Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoders 30 Sep 2022 · 1 repository · arXiv:2209.15514
-
Hierarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generation 9 Aug 2022 · 1 repository · arXiv:2208.04554
-
Information Entropy Initialized Concrete Autoencoder for Optimal Sensor Placement and Reconstruction of Geophysical Fields 28 Jun 2022 · 0 repositories · arXiv:2206.13968
-
Towards Measuring Domain Shift in Histopathological Stain Translation in an Unsupervised Manner 9 May 2022 · 0 repositories · arXiv:2205.04368
-
A model of semantic completion in generative episodic memory 26 Nov 2021 · 0 repositories · arXiv:2111.13537
-
An Unsupervised Video Game Playstyle Metric via State Discretization 3 Oct 2021 · 1 repository · arXiv:2110.00950
-
Towards Generative Latent Variable Models for Speech 29 Sep 2021 · 0 repositories
-
Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistency 25 Sep 2021 · 1 repository · arXiv:2109.12459
-
Cascaded Diffusion Models for High Fidelity Image Generation 30 May 2021 · 0 repositories · arXiv:2106.15282
-
Unsupervised Representation Learning from Pathology Images with Multi-directional Contrastive Predictive Coding 11 May 2021 · 1 repository · arXiv:2105.05345
-
Spectrogram Inpainting for Interactive Generation of Instrument Sounds 15 Apr 2021 · 1 repository · arXiv:2104.07519
-
Context-based Image Segment Labeling (CBISL) 2 Nov 2020 · 0 repositories · arXiv:2011.00784
-
Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving 10 Feb 2020 · 1 repository · arXiv:2002.03629
-
Multimodal Controller for Generative Models 7 Feb 2020 · 1 repository · arXiv:2002.02572
-
Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow 6 Feb 2020 · 1 repository · arXiv:2002.02547
-
Hilbert-Based Generative Defense for Adversarial Examples 1 Oct 2019 · 0 repositories
-
PixelVAE++: Improved PixelVAE with Discrete Prior 26 Aug 2019 · 0 repositories · arXiv:1908.09948
-
Bayesian Volumetric Autoregressive generative models for better semisupervised learning 26 Jul 2019 · 1 repository · arXiv:1907.11559
-
Generating Diverse High-Fidelity Images with VQ-VAE-2 2 Jun 2019 · 15 repositories · arXiv:1906.00446Syntology ran 2 of 9 samples · 7 unverified · 4 pointer-only (licence)
-
ShieldNets: Defending Against Adversarial Attacks Using Probabilistic Adversarial Robustness 1 Jun 2019 · 0 repositories
Tasks archive 2025-07-28
20 shown of 52 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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