Methods › Computer Vision › 3D Face Mesh Models › VQ-VAE-2

VQ-VAE-2

7 papers tagged archive 2025-07-28

Introduced by Ali Razavi et al. in Generating Diverse High-Fidelity Images with VQ-VAE-2

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

VQ-VAE-2 is a type of variational autoencoder that combines a a two-level hierarchical VQ-VAE with a self-attention autoregressive model (PixelCNN) as a prior. The encoder and decoder architectures are kept simple and light-weight as in the original VQ-VAE, with the only difference that hierarchical multi-scale latent maps are used for increased resolution.

Paper Source

Papers archive 2025-07-28

7 shown of 7, 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
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
Phased Data Augmentation for Training a Likelihood-Based Generative Model with Limited Data
22 May 2023 · 0 repositories · arXiv:2305.12681
Hierarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generation
9 Aug 2022 · 1 repository · arXiv:2208.04554
An Unsupervised Video Game Playstyle Metric via State Discretization
3 Oct 2021 · 1 repository · arXiv:2110.00950
Generating Diverse High-Fidelity Images with VQ-VAE-2
2 Jun 2019 · 15 repositories · arXiv:1906.00446

Syntology ran 2 of 9 samples · 7 unverified · 4 pointer-only (licence)

Tasks archive 2025-07-28

20 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Decoder	2
Image Generation	2
Atari Games	1
Car Racing	1
Change Detection	1
Data Augmentation	1
Decision Making	1
Diversity	1
Image Reconstruction	1
Motion Planning	1
Object Detection	1
Object Tracking	1
Quantization	1
Representation Learning	1
Scene Change Detection	1
Scene Understanding	1
Text-to-Video Generation	1
Video Generation	1
Vocal Bursts Intensity Prediction	1
object-detection	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (7 dated). Bars are counts, not a trend claim.

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

3D Face Mesh Models Likelihood-Based Generative Models Generative Models

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