{"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/vq-vae-2","slug":"vq-vae-2","name":"VQ-VAE-2","full_name":"VQ-VAE-2","full_name_withheld":false,"description_markdown":"**VQ-VAE-2** is a type of variational autoencoder that combines a a two-level hierarchical VQ-[VAE](https://paperswithcode.com/method/vae) with a self-attention autoregressive model ([PixelCNN](https://paperswithcode.com/method/pixelcnn)) as a prior. The encoder and decoder architectures are kept simple and light-weight as in the original [VQ-VAE](https://paperswithcode.com/method/vq-vae), with the only difference that hierarchical multi-scale latent maps are used for increased resolution.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","paper":"/paper/190600446","first_author":"Ali Razavi","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/190600446"},"source":{"url":"https://arxiv.org/abs/1906.00446v1","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"3D Face Mesh Models","url":"/methods/category/3d-face-mesh-models","pwc_aliases":[]},{"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":7,"archive_num_papers":7,"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":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":"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/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":"/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":"/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"]}}}],"papers_shown":7,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":7,"with_a_code_link":3,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":7,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"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":1,"papers_where_code_ran_first_page":"/method/vq-vae-2/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/vq-vae-2/papers/ran/1","json":"/method/vq-vae-2/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/image-generation","name":"Image Generation","papers":2},{"task":"/task/atari-games","name":"Atari Games","papers":1},{"task":"/task/car-racing","name":"Car Racing","papers":1},{"task":"/task/change-detection","name":"Change Detection","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/decision-making","name":"Decision Making","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/image-reconstruction","name":"Image Reconstruction","papers":1},{"task":"/task/motion-planning","name":"Motion Planning","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/object-tracking","name":"Object Tracking","papers":1},{"task":"/task/quantization","name":"Quantization","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1},{"task":"/task/scene-change-detection","name":"Scene Change Detection","papers":1},{"task":"/task/scene-understanding","name":"Scene Understanding","papers":1},{"task":"/task/text-to-video-generation","name":"Text-to-Video Generation","papers":1},{"task":"/task/video-generation","name":"Video Generation","papers":1},{"task":"/task/high","name":"Vocal Bursts Intensity Prediction","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1}],"tasks_shown":20,"n_tasks":20,"usage_by_year":[{"year":"2019","papers":1},{"year":"2021","papers":1},{"year":"2022","papers":1},{"year":"2023","papers":3},{"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/vq-vae-2"},"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=VQ-VAE-2","read_at":"2026-10-05T01:03:48+00:00","query":"VQ-VAE-2","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":"1906.00446","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 'VQ-VAE-2' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["VQ-VAE","CVQ-VAE","ArcVQ-VAE","TCaS-VQ-VAE","Class-Partitioned VQ-VAE","Clustering VQ-VAE (CVQ-VAE)","Vector Quantised-Variational AutoEncoder (VQ-VAE)","Decomposed Vector-Quantized Variational Autoencoder (DVQ-VAE)"],"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":"2c6c117b68054ab7b5afd1a12dbc26fdb89bd0ed52edc59be17059e85a22a8bd","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}