ProxIQA : A Proxy Approach to Perceptual Optimization of Learned Image Compression
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 differe...
| Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 30(2021) vom: 13., Seite 360-373 |
|---|---|
| 1. Verfasser: | |
| Weitere Verfasser: | , , , |
| Format: | Online-Aufsatz |
| Sprache: | English |
| Veröffentlicht: |
2021
|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society |
| Schlagworte: | Journal Article |
| Zusammenfassung: | 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 "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 |
|---|---|
| Beschreibung: | Date Completed 20.05.2021 Date Revised 20.05.2021 published: Print-Electronic Citation Status MEDLINE |
| ISSN: | 1941-0042 |
| DOI: | 10.1109/TIP.2020.3036752 |