# Modeling Image Quantization Tradeoffs for Optimal Compression

arXiv: https://arxiv.org/abs/2112.07207 · HTML: https://mlsanity.com/paper/2112.07207/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 20 references that are in the map.
- First posted on arXiv 14 Dec 2021.

## Builds on (most cited first, 5 of 5)

- [DeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Framework](https://mlsanity.com/paper/1803.05788/) (2018)
- [Semantic Perceptual Image Compression using Deep Convolution Networks](https://mlsanity.com/paper/1612.08712/) (2016)
- [Guetzli: Perceptually Guided JPEG Encoder](https://mlsanity.com/paper/1703.04421/) (2017)
- [Quality assessment metrics for edge detection and edge-aware filtering: A tutorial review](https://mlsanity.com/paper/1801.00454/) (2018)
- [Towards improved lossy image compression: Human image reconstruction with public-domain images](https://mlsanity.com/paper/1810.11137/) (2018)

## Abstract (arXiv)

All Lossy compression algorithms employ similar compression schemes -- frequency domain transform followed by quantization and lossless encoding schemes. They target tradeoffs by quantizating high frequency data to increase compression rates which come at the cost of higher image distortion. We propose a new method of optimizing quantization tables using Deep Learning and a minimax loss function that more accurately measures the tradeoffs between rate and distortion parameters (RD) than previous methods. We design a convolutional neural network (CNN) that learns a mapping between image blocks and quantization tables in an unsupervised manner. By processing images across all channels at once, we can achieve stronger performance by also measuring tradeoffs in information loss between different channels. We initially target optimization on JPEG images but feel that this can be expanded to any lossy compressor.