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

arXiv: https://arxiv.org/abs/1910.08845 · HTML: https://mlsanity.com/paper/1910.08845/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2019.

## Built on by (most cited first, 24 of 24)

- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content](https://mlsanity.com/paper/2101.10955/) (2021)
- [Video Quality Assessment: A Comprehensive Survey](https://mlsanity.com/paper/2412.04508/) (2024)
- [Robust Unsupervised StyleGAN Image Restoration](https://mlsanity.com/paper/2302.06733/) (2023)
- [FAVER: Blind Quality Prediction of Variable Frame Rate Videos](https://mlsanity.com/paper/2201.01492/) (2022)
- [Hacking VMAF and VMAF NEG: vulnerability to different preprocessing methods](https://mlsanity.com/paper/2107.04510/) (2021)
- [Pik-Fix: Restoring and Colorizing Old Photos](https://mlsanity.com/paper/2205.01902/) (2022)
- [Semantically Video Coding: Instill Static-Dynamic Clues into Structured Bitstream for AI Tasks](https://mlsanity.com/paper/2201.10162/) (2022)
- [On the Computation of the Gaussian Rate-Distortion-Perception Function](https://mlsanity.com/paper/2311.09190/) (2023)
- [Regression or Classification? New Methods to Evaluate No-Reference Picture and Video Quality Models](https://mlsanity.com/paper/2102.00155/) (2021)
- [Learning-Based Video Coding with Joint Deep Compression and Enhancement](https://mlsanity.com/paper/2111.14474/) (2021)
- [VMAF Re-implementation on PyTorch: Some Experimental Results](https://mlsanity.com/paper/2310.15578/) (2023)
- [Image Quality Assessment: Investigating Causal Perceptual Effects with Abductive Counterfactual Inference](https://mlsanity.com/paper/2412.16939/) (2024)
- [Scale-Consistent Fusion: from Heterogeneous Local Sampling to Global Immersive Rendering](https://mlsanity.com/paper/2106.09548/) (2021)
- [HLIC: Harmonizing Optimization Metrics in Learned Image Compression by Reinforcement Learning](https://mlsanity.com/paper/2109.14863/) (2021)
- [Self-Supervised Learning of Perceptually Optimized Block Motion Estimates for Video Compression](https://mlsanity.com/paper/2110.01805/) (2021)
- [ACC-ViT : Atrous Convolution's Comeback in Vision Transformers](https://mlsanity.com/paper/2403.04200/) (2024)
- [QMRNet: Quality Metric Regression for EO Image Quality Assessment and Super-Resolution](https://mlsanity.com/paper/2210.06618/) (2022)
- [Applicability limitations of differentiable full-reference image-quality](https://mlsanity.com/paper/2212.05499/) (2022)
- [Perceptual Learned Image Compression via End-to-End JND-Based Optimization](https://mlsanity.com/paper/2402.02836/) (2024)
- [A Sharpness Based Loss Function for Removing Out-of-Focus Blur](https://mlsanity.com/paper/2408.06014/) (2024)
- [Predicting Eye Fixations Under Distortion Using Bayesian Observers](https://mlsanity.com/paper/2102.03675/) (2021)
- [ROMNet: Renovate the Old Memories](https://mlsanity.com/paper/2202.02606/) (2022)

## Abstract (arXiv)

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.