# Pioneer Networks: Progressively Growing Generative Autoencoder

arXiv: https://arxiv.org/abs/1807.03026 · HTML: https://mlsanity.com/paper/1807.03026/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2018.

## Built on by (most cited first, 4 of 4)

- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [Self-Supervised Representation Learning using Visual Field Expansion on Digital Pathology](https://mlsanity.com/paper/2109.03299/) (2021)
- [Generative Models for 3D Point Clouds](https://mlsanity.com/paper/2302.13408/) (2023)
- [Towards Highly Expressive Machine Learning Models of Non-Melanoma Skin Cancer](https://mlsanity.com/paper/2207.05749/) (2022)

## Abstract (arXiv)

We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial networks (GANs) are known for their ability to simulate random high-quality images, but they cannot reconstruct existing images. Previous works have attempted to extend GANs to support such inference but, so far, have not delivered satisfactory high-quality results. Instead, we propose the Progressively Growing Generative Autoencoder (PIONEER) network which achieves high-quality reconstruction with 128×128 images without requiring a GAN discriminator. We merge recent techniques for progressively building up the parts of the network with the recently introduced adversarial encoder-generator network. The ability to reconstruct input images is crucial in many real-world applications, and allows for precise intelligent manipulation of existing images. We show promising results in image synthesis and inference, with state-of-the-art results in CelebA inference tasks.