Perceptually Optimizing Deep Image Compression
This work addresses the issue of inefficient compression for visual media by improving perceptual quality, though it is incremental as it builds on existing deep compression models.
The paper tackles the problem of optimizing deep image compression networks for human perception rather than traditional error metrics, achieving a 28.7% bitrate reduction compared to MSE optimization at a specified perceptual quality level.
Mean squared error (MSE) and $\ell_p$ norms have largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess visual information loss, these simple norms are not highly consistent with human perception. Here, we propose a different proxy approach to optimize image analysis networks against quantitative perceptual models. Specifically, we construct a proxy network, 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 a modern deep image compression models, we are able to demonstrate an averaged bitrate reduction of $28.7\%$ over MSE optimization, given a specified perceptual quality (VMAF) level.