Pioneer Networks: Progressively Growing Generative Autoencoder

Loading...
Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2019

Major/Subject

Mcode

Degree programme

Language

en

Pages

22-38

Series

Computer Vision – ACCV 2018, Lecture notes in computer science, Volume 11361

Abstract

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 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.

Description

Keywords

Autoencoder, Computer vision, Generative models

Other note

Citation

Heljakka, A, Solin, A & Kannala, J 2019, Pioneer Networks : Progressively Growing Generative Autoencoder . in G Mori, C V Jawahar, K Schindler & H Li (eds), Computer Vision – ACCV 2018 - 14th Asian Conference on Computer Vision, Revised Selected Papers . Lecture notes in computer science, vol. 11361, Springer, Springer, Cham, pp. 22-38, Asian Conference on Computer Vision, Perth, Western Australia, Australia, 02/12/2018 . https://doi.org/10.1007/978-3-030-20887-5_2