mlsanityData to 7 Oct 2026

PixelVAE: A Latent Variable Model for Natural Images

arXiv 1611.05013 ↗First posted 15 Nov 2016cs.LGcited by 69

Not on the map. Why?

Abstract (arXiv)

Natural image modeling is a landmark challenge of unsupervised learning. Variational Autoencoders (VAEs) learn a useful latent representation and model global structure well but have difficulty capturing small details. PixelCNN models details very well, but lacks a latent code and is difficult to scale for capturing large structures. We present PixelVAE, a VAE model with an autoregressive decoder based on PixelCNN. Our model requires very few expensive autoregressive layers compared to PixelCNN and learns latent codes that are more compressed than a standard VAE while still capturing most non-trivial structure. Finally, we extend our model to a hierarchy of latent variables at different scales. Our model achieves state-of-the-art performance on binarized MNIST, competitive performance on 64x64 ImageNet, and high-quality samples on the LSUN bedrooms dataset.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 15; 2023: 15; 2024: 10; 2025: 11; 2026: 5.

69 papers.

Sort:

By area:

  1. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  2. 2021ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesiscited by 122
  3. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  4. 2023Posterior Collapse and Latent Variable Non-identifiabilitycited by 57
  5. 2024Autoregressive Models in Vision: A Surveycited by 39
  6. 2023Autoregressive Conditional Neural Processescited by 32
  7. 2024Rethinking Patch Dependence for Masked Autoencoderscited by 29
  8. 2021Creativity and Machine Learning: A Surveycited by 21
  9. 2022Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compressioncited by 21
  10. 2023Learning Manifold Dimensions with Conditional Variational Autoencoderscited by 20
  11. 2022CLUTR: Curriculum Learning via Unsupervised Task Representation Learningcited by 19
  12. 2023IRGen: Generative Modeling for Image Retrievalcited by 18
38 more
  1. 2025Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modelingcited by 14
  2. 2025Adapting Self-Supervised Representations as a Latent Space for Efficient Generationcited by 13
  3. 2021On Incorporating Inductive Biases into VAEscited by 11
  4. 2024DiffLM: Controllable Synthetic Data Generation via Diffusion Language Modelscited by 9
  5. 2022Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentificationcited by 8
  6. 2022Unsupervised Object Representation Learning using Translation and Rotation Group Equivariant VAEcited by 8
  7. 2024Hierarchical VAE with a Diffusion-based VampPriorcited by 8
  8. 2022Variational Laplace Autoencoderscited by 7
  9. 2023DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewardscited by 7
  10. 2023Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Networkcited by 7
  11. 2024Boosting Flow-based Generative Super-Resolution Models via Learned Priorcited by 7
  12. 2022Improving VAE-based Representation Learningcited by 6
  13. 2022Forget-me-not! Contrastive Critics for Mitigating Posterior Collapsecited by 6
  14. 2023Trading Information between Latents in Hierarchical Variational Autoencoderscited by 6
  15. 2023Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoderscited by 6
  16. 2023Learning Hierarchical Features with Joint Latent Space Energy-Based Priorcited by 6
  17. 2022Vision-Language Matching for Text-to-Image Synthesis via Generative Adversarial Networkscited by 5
  18. 2023Spatial and Modal Optimal Transport for Fast Cross-Modal MRI Reconstructioncited by 5
  19. 2022Parallel Neural Local Lossless Compressioncited by 4
  20. 2022Split Hierarchical Variational Compressioncited by 4
  21. 2023Synthesizing Environment-Specific People in Photographscited by 4
  22. 2025FaceID-6M: A Large-Scale, Open-Source FaceID Customization Datasetcited by 4
  23. 2025Posterior Collapse as a Phase Transition in Variational Autoencoderscited by 4
  24. 2021Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memorycited by 3
  25. 2022Structured Uncertainty in the Observation Space of Variational Autoencoderscited by 3
  26. 2022FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusioncited by 3
  27. 2022Improving Variational Autoencoders with Density Gap-based Regularizationcited by 3
  28. 2024Auto-Encoding Bayesian Inverse Gamescited by 3
  29. 2024Preventing Model Collapse in Gaussian Process Latent Variable Modelscited by 3
  30. 2021HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identificationcited by 2
  31. 2021ByPE-VAE: Bayesian Pseudocoresets Exemplar VAEcited by 2
  32. 2021Towards fast machine-learning-assisted Bayesian posterior inference of microseismic event location and source mechanismcited by 1
  33. 2021VAE^2: Preventing Posterior Collapse of Variational Video Predictions in the Wildcited by 1
  34. 2021Image Style Transfer and Content-Style Disentanglementcited by 1
  35. 2022Latent Variable Modelling Using Variational Autoencoders: A surveycited by 1
  36. 2023Unsupervised Denoising for Signal-Dependent and Row-Correlated Imaging Noisecited by 1
  37. 2023Predictive variational autoencoder for learning robust representations of time-series datacited by 1
  38. 2023Dynamic Topic Language Model on Heterogeneous Children's Mental Health Clinical Notescited by 1

50 most cited of 69 All 69 (JSON)