# Optimized learned entropy coding parameters for practical neural-based image and video compression

arXiv: https://arxiv.org/abs/2301.08752 · HTML: https://mlsanity.com/paper/2301.08752/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 18 references that are in the map.
- First posted on arXiv 20 Jan 2023.

## Builds on (most cited first, 6 of 6)

- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [Data-Free Quantization Through Weight Equalization and Bias Correction](https://mlsanity.com/paper/1906.04721/) (2019)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [Image and Video Compression with Neural Networks: A Review](https://mlsanity.com/paper/1904.03567/) (2019)
- [Advances In Video Compression System Using Deep Neural Network: A Review And Case Studies](https://mlsanity.com/paper/2101.06341/) (2021)

## Built on by (most cited first, 1 of 1)

- [MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Device](https://mlsanity.com/paper/2310.01258/) (2023)

## Abstract (arXiv)

Neural-based image and video codecs are significantly more power-efficient when weights and activations are quantized to low-precision integers. While there are general-purpose techniques for reducing quantization effects, large losses can occur when specific entropy coding properties are not considered. This work analyzes how entropy coding is affected by parameter quantizations, and provides a method to minimize losses. It is shown that, by using a certain type of coding parameters to be learned, uniform quantization becomes practically optimal, also simplifying the minimization of code memory requirements. The mathematical properties of the new representation are presented, and its effectiveness is demonstrated by coding experiments, showing that good results can be obtained with precision as low as 4~bits per network output, and practically no loss with 8~bits.