{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/pixelcnn","slug":"pixelcnn","name":"PixelCNN","full_name":"PixelCNN","full_name_withheld":false,"description_markdown":"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](https://paperswithcode.com/method/pixelrnn) because convolutions are inherently easier to parallelize; given the vast number of pixels present in large image datasets this is an important advantage.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Pixel Recurrent Neural Networks","paper":"/paper/pixel-recurrent-neural-networks","first_author":"Aaron van den Oord","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/pixel-recurrent-neural-networks"},"source":{"url":"http://arxiv.org/abs/1601.06759v3","title":"Pixel Recurrent Neural Networks","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/openai/pixel-cnn","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Likelihood-Based Generative Models","url":"/methods/category/likelihood-based-generative-models","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Models","url":"/methods/category/generative-models","pwc_aliases":[]}],"n_papers_tagged":45,"archive_num_papers":45,"papers_newest_first":[{"paper":null,"slug":"hitvideo-hierarchical-tokenizers-for","title":"HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models","date":"2025-03-14","arxiv_id":"2503.11513","n_code_links":0,"syntology":null},{"paper":"/paper/pixelbytes-catching-unified-representation","slug":"pixelbytes-catching-unified-representation","title":"PixelBytes: Catching Unified Representation for Multimodal Generation","date":"2024-09-16","arxiv_id":"2410.01820","n_code_links":1,"syntology":null},{"paper":"/paper/pixelbytes-catching-unified-embedding-for","slug":"pixelbytes-catching-unified-embedding-for","title":"PixelBytes: Catching Unified Embedding for Multimodal Generation","date":"2024-09-03","arxiv_id":"2409.15512","n_code_links":1,"syntology":null},{"paper":"/paper/sernet-former-semantic-segmentation-by","slug":"sernet-former-semantic-segmentation-by","title":"SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks","date":"2024-01-28","arxiv_id":"2401.15741","n_code_links":2,"syntology":null},{"paper":"/paper/an-attempt-to-generate-new-bridge-types-from-2","slug":"an-attempt-to-generate-new-bridge-types-from-2","title":"An attempt to generate new bridge types from latent space of PixelCNN","date":"2024-01-11","arxiv_id":"2401.05964","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-autoregressive-modeling-for-land-use","title":"Deep autoregressive modeling for land use land cover","date":"2024-01-02","arxiv_id":"2401.01395","n_code_links":0,"syntology":null},{"paper":null,"slug":"hq-vae-hierarchical-discrete-representation","title":"HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes","date":"2023-12-31","arxiv_id":"2401.00365","n_code_links":0,"syntology":null},{"paper":null,"slug":"seadsc-a-video-based-unsupervised-method-for","title":"SeaDSC: A video-based unsupervised method for dynamic scene change detection in unmanned surface vehicles","date":"2023-11-20","arxiv_id":"2311.11580","n_code_links":0,"syntology":null},{"paper":null,"slug":"s-hr-vqvae-sequential-hierarchical-residual","title":"S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction","date":"2023-07-13","arxiv_id":"2307.06701","n_code_links":0,"syntology":null},{"paper":null,"slug":"phased-data-augmentation-for-training","title":"Phased Data Augmentation for Training a Likelihood-Based Generative Model with Limited Data","date":"2023-05-22","arxiv_id":"2305.12681","n_code_links":0,"syntology":null},{"paper":"/paper/learning-with-miselbo-the-mixture-cookbook","slug":"learning-with-miselbo-the-mixture-cookbook","title":"Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoders","date":"2022-09-30","arxiv_id":"2209.15514","n_code_links":1,"syntology":null},{"paper":"/paper/hierarchical-residual-learning-based-vector","slug":"hierarchical-residual-learning-based-vector","title":"Hierarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generation","date":"2022-08-09","arxiv_id":"2208.04554","n_code_links":1,"syntology":null},{"paper":null,"slug":"information-entropy-initialized-concrete","title":"Information Entropy Initialized Concrete Autoencoder for Optimal Sensor Placement and Reconstruction of Geophysical Fields","date":"2022-06-28","arxiv_id":"2206.13968","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-measuring-domain-shift-in","title":"Towards Measuring Domain Shift in Histopathological Stain Translation in an Unsupervised Manner","date":"2022-05-09","arxiv_id":"2205.04368","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-model-of-semantic-completion-in-generative","title":"A model of semantic completion in generative episodic memory","date":"2021-11-26","arxiv_id":"2111.13537","n_code_links":0,"syntology":null},{"paper":"/paper/an-unsupervised-video-game-playstyle-metric","slug":"an-unsupervised-video-game-playstyle-metric","title":"An Unsupervised Video Game Playstyle Metric via State Discretization","date":"2021-10-03","arxiv_id":"2110.00950","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-generative-latent-variable-models-for","title":"Towards Generative Latent Variable Models for Speech","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/two-souls-in-an-adversarial-image-towards","slug":"two-souls-in-an-adversarial-image-towards","title":"Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistency","date":"2021-09-25","arxiv_id":"2109.12459","n_code_links":1,"syntology":null},{"paper":"/paper/cascaded-diffusion-models-for-high-fidelity","slug":"cascaded-diffusion-models-for-high-fidelity","title":"Cascaded Diffusion Models for High Fidelity Image Generation","date":"2021-05-30","arxiv_id":"2106.15282","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-representation-learning-from","slug":"unsupervised-representation-learning-from","title":"Unsupervised Representation Learning from Pathology Images with Multi-directional Contrastive Predictive Coding","date":"2021-05-11","arxiv_id":"2105.05345","n_code_links":1,"syntology":null},{"paper":"/paper/spectrogram-inpainting-for-interactive","slug":"spectrogram-inpainting-for-interactive","title":"Spectrogram Inpainting for Interactive Generation of Instrument Sounds","date":"2021-04-15","arxiv_id":"2104.07519","n_code_links":1,"syntology":null},{"paper":null,"slug":"context-based-image-segment-labeling-cbisl","title":"Context-based Image Segment Labeling (CBISL)","date":"2020-11-02","arxiv_id":"2011.00784","n_code_links":0,"syntology":null},{"paper":"/paper/nonlinear-equation-solving-a-faster","slug":"nonlinear-equation-solving-a-faster","title":"Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving","date":"2020-02-10","arxiv_id":"2002.03629","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-controller-for-generative-models","slug":"multimodal-controller-for-generative-models","title":"Multimodal Controller for Generative Models","date":"2020-02-07","arxiv_id":"2002.02572","n_code_links":1,"syntology":null},{"paper":"/paper/closing-the-dequantization-gap-pixelcnn-as-a","slug":"closing-the-dequantization-gap-pixelcnn-as-a","title":"Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow","date":"2020-02-06","arxiv_id":"2002.02547","n_code_links":1,"syntology":null},{"paper":null,"slug":"hilbert-based-generative-defense-for","title":"Hilbert-Based Generative Defense for Adversarial Examples","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pixelvae-improved-pixelvae-with-discrete","title":"PixelVAE++: Improved PixelVAE with Discrete Prior","date":"2019-08-26","arxiv_id":"1908.09948","n_code_links":0,"syntology":null},{"paper":"/paper/bayesian-volumetric-autoregressive-generative","slug":"bayesian-volumetric-autoregressive-generative","title":"Bayesian Volumetric Autoregressive generative models for better semisupervised learning","date":"2019-07-26","arxiv_id":"1907.11559","n_code_links":1,"syntology":null},{"paper":"/paper/190600446","slug":"190600446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","date":"2019-06-02","arxiv_id":"1906.00446","n_code_links":15,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["deepmind/sonnet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"shieldnets-defending-against-adversarial","title":"ShieldNets: Defending Against Adversarial Attacks Using Probabilistic Adversarial Robustness","date":"2019-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tree-tensor-networks-for-generative-modeling","title":"Tree Tensor Networks for Generative Modeling","date":"2019-01-08","arxiv_id":"1901.02217","n_code_links":0,"syntology":null},{"paper":"/paper/practical-full-resolution-learned-lossless","slug":"practical-full-resolution-learned-lossless","title":"Practical Full Resolution Learned Lossless Image Compression","date":"2018-11-30","arxiv_id":"1811.12817","n_code_links":4,"syntology":null},{"paper":"/paper/the-variational-homoencoder-learning-to-learn","slug":"the-variational-homoencoder-learning-to-learn","title":"The Variational Homoencoder: Learning to learn high capacity generative models from few examples","date":"2018-07-24","arxiv_id":"1807.08919","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["insperatum/vhe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/representation-learning-with-contrastive","slug":"representation-learning-with-contrastive","title":"Representation Learning with Contrastive Predictive Coding","date":"2018-07-10","arxiv_id":"1807.03748","n_code_links":28,"syntology":{"ran":35,"of":45,"n_ran_checked":30,"n_instrument":5,"unverified":10,"pointer_only":22,"phrase":"35 ran (of which 21 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified","official":null}},{"paper":null,"slug":"feature-map-variational-auto-encoders","title":"Feature Map Variational Auto-Encoders","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-variational-homoencoder-learning-to-infer","title":"The Variational Homoencoder: Learning to Infer High-Capacity Generative Models from Few Examples","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"spatial-pixelcnn-generating-images-from","title":"Spatial PixelCNN: Generating Images from Patches","date":"2017-12-03","arxiv_id":"1712.00714","n_code_links":0,"syntology":null},{"paper":null,"slug":"few-shot-autoregressive-density-estimation","title":"Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions","date":"2017-10-27","arxiv_id":"1710.10304","n_code_links":0,"syntology":null},{"paper":"/paper/pixcolor-pixel-recursive-colorization","slug":"pixcolor-pixel-recursive-colorization","title":"PixColor: Pixel Recursive Colorization","date":"2017-05-19","arxiv_id":"1705.07208","n_code_links":0,"syntology":null},{"paper":"/paper/parallel-multiscale-autoregressive-density","slug":"parallel-multiscale-autoregressive-density","title":"Parallel Multiscale Autoregressive Density Estimation","date":"2017-03-10","arxiv_id":"1703.03664","n_code_links":0,"syntology":null},{"paper":"/paper/count-based-exploration-with-neural-density","slug":"count-based-exploration-with-neural-density","title":"Count-Based Exploration with Neural Density Models","date":"2017-03-03","arxiv_id":"1703.01310","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/pixelcnn-models-with-auxiliary-variables-for","slug":"pixelcnn-models-with-auxiliary-variables-for","title":"PixelCNN Models with Auxiliary Variables for Natural Image Modeling","date":"2016-12-24","arxiv_id":"1612.08185","n_code_links":0,"syntology":null},{"paper":"/paper/pixelvae-a-latent-variable-model-for-natural","slug":"pixelvae-a-latent-variable-model-for-natural","title":"PixelVAE: A Latent Variable Model for Natural Images","date":"2016-11-15","arxiv_id":"1611.05013","n_code_links":1,"syntology":null},{"paper":"/paper/conditional-image-generation-with-pixelcnn","slug":"conditional-image-generation-with-pixelcnn","title":"Conditional Image Generation with PixelCNN Decoders","date":"2016-06-16","arxiv_id":"1606.05328","n_code_links":14,"syntology":{"ran":8,"of":14,"n_ran_checked":6,"n_instrument":2,"unverified":6,"pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":null}},{"paper":"/paper/pixel-recurrent-neural-networks","slug":"pixel-recurrent-neural-networks","title":"Pixel Recurrent Neural Networks","date":"2016-01-25","arxiv_id":"1601.06759","n_code_links":20,"syntology":{"ran":19,"of":29,"n_ran_checked":17,"n_instrument":2,"unverified":10,"pointer_only":18,"phrase":"19 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified","official":null}}],"papers_shown":45,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":45,"with_a_code_link":22,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":45,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/method/pixelcnn/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/pixelcnn/papers/ran/1","json":"/method/pixelcnn/papers/ran/1.json","rows":6}],"tasks":[{"task":"/task/image-generation","name":"Image Generation","papers":12},{"task":"/task/decoder","name":"Decoder","papers":6},{"task":"/task/representation-learning","name":"Representation Learning","papers":5},{"task":"/task/density-estimation","name":"Density Estimation","papers":3},{"task":"/task/classification","name":"General Classification","papers":3},{"task":"/task/video-generation","name":"Video Generation","papers":3},{"task":"/task/adversarial-robustness","name":"Adversarial Robustness","papers":2},{"task":"/task/atari-games","name":"Atari Games","papers":2},{"task":"/task/conditional-image-generation","name":"Conditional Image Generation","papers":2},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":2},{"task":"/task/image-compression","name":"Image Compression","papers":2},{"task":"/task/image-inpainting","name":"Image Inpainting","papers":2},{"task":"/task/mamba","name":"Mamba","papers":2},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/state-space-models","name":"State Space Models","papers":2},{"task":"/task/high","name":"Vocal Bursts Intensity Prediction","papers":2},{"task":"/task/multimodal-generation","name":"multimodal generation","papers":2},{"task":"/task/2d-semantic-segmentation","name":"2D Semantic Segmentation","papers":1},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":1}],"tasks_shown":20,"n_tasks":52,"usage_by_year":[{"year":"2016","papers":4},{"year":"2017","papers":5},{"year":"2018","papers":5},{"year":"2019","papers":6},{"year":"2020","papers":4},{"year":"2021","papers":7},{"year":"2022","papers":4},{"year":"2023","papers":4},{"year":"2024","papers":5},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/pixelcnn"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=PixelCNN","read_at":"2026-10-05T01:00:20+00:00","query":"PixelCNN","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1601.06759","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'PixelCNN' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"efb037011a901fb49e5738caf914348b444b86f96809fa09845fe204d407ea6b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}