# PixelVAE++: Improved PixelVAE with Discrete Prior

arXiv: https://arxiv.org/abs/1908.09948 · HTML: https://mlsanity.com/paper/1908.09948/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2019.

## Built on by (most cited first, 15 of 15)

- [Score-based Generative Modeling in Latent Space](https://mlsanity.com/paper/2106.05931/) (2021)
- [GIVT: Generative Infinite-Vocabulary Transformers](https://mlsanity.com/paper/2312.02116/) (2023)
- [Bayesian Flow Networks](https://mlsanity.com/paper/2308.07037/) (2023)
- [Densely connected normalizing flows](https://mlsanity.com/paper/2106.04627/) (2021)
- [Efficient-VDVAE: Less is more](https://mlsanity.com/paper/2203.13751/) (2022)
- [Hierarchical VAE with a Diffusion-based VampPrior](https://mlsanity.com/paper/2412.01373/) (2024)
- [Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoders](https://mlsanity.com/paper/2209.15514/) (2022)
- [Entropy-Informed Weighting Channel Normalizing Flow for Deep Generative Models](https://mlsanity.com/paper/2407.04958/) (2024)
- [A Non-negative VAE:the Generalized Gamma Belief Network](https://mlsanity.com/paper/2408.03388/) (2024)
- [Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory](https://mlsanity.com/paper/2103.03905/) (2021)
- [FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion](https://mlsanity.com/paper/2209.11277/) (2022)
- [Efficient Mixture Learning in Black-Box Variational Inference](https://mlsanity.com/paper/2406.07083/) (2024)
- [Variational Autoencoding of Dental Point Clouds](https://mlsanity.com/paper/2307.10895/) (2023)
- [Level of agreement between emotions generated by Artificial Intelligence and human evaluation: a methodological proposal](https://mlsanity.com/paper/2410.08332/) (2024)
- [Implicit Variational Rejection Sampling](https://mlsanity.com/paper/2606.14235/) (2026)

## Abstract (arXiv)

Constructing powerful generative models for natural images is a challenging task. PixelCNN models capture details and local information in images very well but have limited receptive field. Variational autoencoders with a factorial decoder can capture global information easily, but they often fail to reconstruct details faithfully. PixelVAE combines the best features of the two models and constructs a generative model that is able to learn local and global structures. Here we introduce PixelVAE++, a VAE with three types of latent variables and a PixelCNN++ for the decoder. We introduce a novel architecture that reuses a part of the decoder as an encoder. We achieve the state of the art performance on binary data sets such as MNIST and Omniglot and achieve the state of the art performance on CIFAR-10 among latent variable models while keeping the latent variables informative.