Pioneer Networks: Progressively Growing Generative Autoencoder

By Ari Heljakka, Arno Solin, Juho Kannala. 2018

41 citations recorded by the source corpus.

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 \(128\times 128\) 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.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Taming Transformers for High-Resolution Image Synthesis (2020, neutral): “) [21] 39.”
Adversarial Latent Autoencoders (2020, background): “PIONEER [15] and IntroVAE [20] followed this line, with the latter providing the best generation results in this category.”
LIA: Latently Invertible Autoencoder with Adversarial Learning (2019, background): “There is an intriguing attempt of training VAE in the adversarial manner, in the sense that the adversarial learning is established between the encoder and the decoder [40, 14].”
Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders (2019, methodology): “In this paper, we build upon P IONEER [13], based on the adversarial generator–encoder (AGE) [40].”
Disentangled Inference for GANs With Latently Invertible Autoencoder (2019, background): “Besides, there is an intriguing attempt of training VAE in the adversarial manner (Ulyanov et al., 2017; Heljakka et al., 2018).”