The reviewed record of science sign in
Pith

arxiv: 1910.08845 · v2 · pith:QPEHR5MM · submitted 2019-10-19 · eess.IV · cs.CV· cs.LG

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

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:QPEHR5MMrecord.jsonopen to challenge →

classification eess.IV cs.CVcs.LG
keywords imageperceptualcompressionlossnetworkoptimizationapproachdemonstrate
0
0 comments X
read the original abstract

The use of $\ell_p$ $(p=1,2)$ 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.