Deep Generative Models for Distribution-Preserving Lossy Compression

05/28/2018
by   Michael Tschannen, et al.
2

We propose and study the problem of distribution-preserving lossy compression. Motivated by the recent advances in extreme image compression which allow to maintain artifact-free reconstructions even at very low bitrates, we propose to optimize the rate-distortion tradeoff under the constraint that the reconstructed samples follow the distribution of the training data. Such a compression system recovers both ends of the spectrum: On one hand, at zero bitrate it learns a generative model of the data, and at high enough bitrates it achieves perfect reconstruction. Furthermore, for intermediate bitrates it smoothly interpolates between matching the distribution of the training data and perfectly reconstructing the training samples. We study several methods to approximately solve the proposed optimization problem, including a novel combination of Wasserstein GAN and Wasserstein Autoencoder, and present strong theoretical and empirical results for the proposed compression system.

READ FULL TEXT

Authors

page 15

page 16

page 17

page 18

page 20

page 22

page 23

page 24

04/05/2018

Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model

In this paper we study generative modeling via autoencoders while using ...
04/08/2019

Extreme Image Compression via Multiscale Autoencoders With Generative Adversarial Optimization

We propose a MultiScale AutoEncoder(MSAE) based extreme image compressio...
02/25/2019

Wasserstein-Wasserstein Auto-Encoders

To address the challenges in learning deep generative models (e.g.,the b...
04/09/2020

Feedback Recurrent Autoencoder for Video Compression

Recent advances in deep generative modeling have enabled efficient model...
08/24/2020

Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networks

We propose a GAN-based image compression method working at extremely low...
09/30/2019

Towards Diverse Paraphrase Generation Using Multi-Class Wasserstein GAN

Paraphrase generation is an important and challenging natural language p...
03/29/2022

Neural Face Video Compression using Multiple Views

Recent advances in deep generative models led to the development of neur...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.