Skip to main content

Proxiqa: A Proxy Approach To Perceptual Optimization Of Learned Image Compression

Li-Heng Chen, Christos Bampis, Zhi Li, Andrey Norkin, Alan Bovik

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
    Length: 00:12:47
22 Sep 2021

The use of lp (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 ƒ??proximalƒ?� 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.

Value-Added Bundle(s) Including this Product

More Like This