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

@article{Chen2021ProxIQAAP,
title={ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression},
author={Li-Heng Chen and C. Bampis and Z. Li and A. Norkin and A. Bovik},
journal={IEEE Transactions on Image Processing},
year={2021},
volume={30},
pages={360-373}
}
• Li-Heng Chen, +2 authors A. Bovik
• Published 2021
• Computer Science, Medicine, Engineering
• IEEE Transactions on Image Processing
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… Expand
8 Citations

#### Figures, Tables, and Topics from this paper

UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
• Computer Science, Medicine
• IEEE Transactions on Image Processing
• 2021
Nonlinear Transform Coding
• Engineering, Computer Science
• IEEE Signal Processing Letters
• 2020
Learning to Distort Images Using Generative Adversarial Networks
• Computer Science
• IEEE Signal Processing Letters
• 2020

#### References

SHOWING 1-10 OF 71 REFERENCES
Variational image compression with a scale hyperprior
• Computer Science, Engineering
• ICLR
• 2018
Learning to generate images with perceptual similarity metrics
• Computer Science, Mathematics
• 2017 IEEE International Conference on Image Processing (ICIP)
• 2017
End-to-end Optimized Image Compression
• Computer Science, Mathematics
• ICLR
• 2017
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
• Computer Science
• 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
• 2018
Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks
• Nick Johnston, +6 authors G. Toderici
• Computer Science
• 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
• 2018
Generative Adversarial Networks for Extreme Learned Image Compression
• Computer Science
• 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
• 2019
Full Resolution Image Compression with Recurrent Neural Networks
• G. Toderici, +4 authors Michele Covell
• Computer Science
• 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
• 2017
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
• Computer Science
• 2017 IEEE International Conference on Computer Vision (ICCV)
• 2017
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
• C. Ledig, +6 authors W. Shi
• Computer Science, Mathematics
• 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
• 2017