ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression

10/19/2019
by   Li-Heng Chen, et al.
11

The use of ℓ_p(p=1,2) norms has largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess the loss of visual information, these simple norms are not very consistent with human perception. Here, we describe a different "proximal" approach to optimize image analysis networks against quantitative perceptual models. Specifically, we construct a proxy network, broadly termed ProxIQA, which mimics the perceptual model while serving as a loss layer of the network. We experimentally demonstrate how this optimization framework can be applied to train an end-to-end optimized image compression network. By building on top of an existing deep image compression model, we are able to demonstrate a bitrate reduction of as much as 31% over MSE optimization, given a specified perceptual quality (VMAF) level.

READ FULL TEXT

page 1

page 4

page 5

page 8

page 9

research
07/03/2020

Perceptually Optimizing Deep Image Compression

Mean squared error (MSE) and ℓ_p norms have largely dominated the measur...
research
05/05/2021

Perceptual Gradient Networks

Many applications of deep learning for image generation use perceptual l...
research
05/12/2023

HFLIC: Human Friendly Perceptual Learned Image Compression with Reinforced Transform

In recent years, there has been rapid development in learned image compr...
research
07/18/2019

Deep Perceptual Compression

Several deep learned lossy compression techniques have been proposed in ...
research
05/10/2010

On Macroscopic Complexity and Perceptual Coding

The theoretical limits of 'lossy' data compression algorithms are consid...
research
05/20/2022

Compression ensembles quantify aesthetic complexity and the evolution of visual art

The quantification of visual aesthetics and complexity have a long histo...
research
01/31/2021

Towards Imperceptible Query-limited Adversarial Attacks with Perceptual Feature Fidelity Loss

Recently, there has been a large amount of work towards fooling deep-lea...

Please sign up or login with your details

Forgot password? Click here to reset