# Reducing The Mismatch Between Marginal and Learned Distributions in Neural Video Compression

arXiv: https://arxiv.org/abs/2210.06596 · HTML: https://mlsanity.com/paper/2210.06596/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 19 references that are in the map.
- First posted on arXiv 12 Oct 2022.

## Builds on (most cited first, 14 of 14)

- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [DVC: An End-to-end Deep Video Compression Framework](https://mlsanity.com/paper/1812.00101/) (2018)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [Inference Suboptimality in Variational Autoencoders](https://mlsanity.com/paper/1801.03558/) (2018)
- [Content Adaptive and Error Propagation Aware Deep Video Compression](https://mlsanity.com/paper/2003.11282/) (2020)
- [Content Adaptive Optimization for Neural Image Compression](https://mlsanity.com/paper/1906.01223/) (2019)
- [Overfitting for Fun and Profit: Instance-Adaptive Data Compression](https://mlsanity.com/paper/2101.08687/) (2021)
- [Extending Neural P-frame Codecs for B-frame Coding](https://mlsanity.com/paper/2104.00531/) (2021)
- [End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression](https://mlsanity.com/paper/2112.09529/) (2021)
- [Reducing The Amortization Gap of Entropy Bottleneck In End-to-End Image Compression](https://mlsanity.com/paper/2209.00964/) (2022)
- [AIVC: Artificial Intelligence based Video Codec](https://mlsanity.com/paper/2202.04365/) (2022)

## Built on by (most cited first, 2 of 2)

- [RQAT-INR: Improved Implicit Neural Image Compression](https://mlsanity.com/paper/2303.03028/) (2023)
- [Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimization](https://mlsanity.com/paper/2405.14221/) (2024)

## Abstract (arXiv)

During the last four years, we have witnessed the success of end-to-end trainable models for image compression. Compared to decades of incremental work, these machine learning (ML) techniques learn all the components of the compression technique, which explains their actual superiority. However, end-to-end ML models have not yet reached the performance of traditional video codecs such as VVC. Possible explanations can be put forward: lack of data to account for the temporal redundancy, or inefficiency of latent's density estimation in the neural model. The latter problem can be defined by the discrepancy between the latent's marginal distribution and the learned prior distribution. This mismatch, known as amortization gap of entropy model, enlarges the file size of compressed data. In this paper, we propose to evaluate the amortization gap for three state-of-the-art ML video compression methods. Second, we propose an efficient and generic method to solve the amortization gap and show that it leads to an improvement between 2% to 5% without impacting reconstruction quality.