DeepAI
Log In Sign Up

High-Fidelity Generative Image Compression

06/17/2020
by   Fabian Mentzer, et al.
3

We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system. In particular, we investigate normalization layers, generator and discriminator architectures, training strategies, as well as perceptual losses. In contrast to previous work, i) we obtain visually pleasing reconstructions that are perceptually similar to the input, ii) we operate in a broad range of bitrates, and iii) our approach can be applied to high-resolution images. We bridge the gap between rate-distortion-perception theory and practice by evaluating our approach both quantitatively with various perceptual metrics and a user study. The study shows that our method is preferred to previous approaches even if they use more than 2x the bitrate.

READ FULL TEXT

page 2

page 8

page 12

page 13

page 16

04/09/2018

Generative Adversarial Networks for Extreme Learned Image Compression

We propose a framework for extreme learned image compression based on Ge...
01/26/2023

Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models

Lossy image compression aims to represent images in as few bits as possi...
08/24/2020

Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networks

We propose a GAN-based image compression method working at extremely low...
07/26/2021

Towards Generative Video Compression

We present a neural video compression method based on generative adversa...
12/28/2022

Multi-Realism Image Compression with a Conditional Generator

By optimizing the rate-distortion-realism trade-off, generative compress...
06/19/2021

Reversible Colour Density Compression of Images using cGANs

Image compression using colour densities is historically impractical to ...
12/03/2020

How to Exploit the Transferability of Learned Image Compression to Conventional Codecs

Lossy image compression is often limited by the simplicity of the chosen...