# Spatiotemporal Entropy Model is All You Need for Learned Video Compression

arXiv: https://arxiv.org/abs/2104.06083 · HTML: https://mlsanity.com/paper/2104.06083/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 13 Apr 2021.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [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)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [Optical Flow Estimation using a Spatial Pyramid Network](https://mlsanity.com/paper/1611.00850/) (2016)
- [DVC: An End-to-end Deep Video Compression Framework](https://mlsanity.com/paper/1812.00101/) (2018)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [Full Resolution Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1608.05148/) (2016)
- [Variable Rate Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06085/) (2015)
- [Video Compression through Image Interpolation](https://mlsanity.com/paper/1804.06919/) (2018)
- [Context-adaptive Entropy Model for End-to-end Optimized Image Compression](https://mlsanity.com/paper/1809.10452/) (2018)
- [Variable Rate Deep Image Compression With a Conditional Autoencoder](https://mlsanity.com/paper/1909.04802/) (2019)
- [M-LVC: Multiple Frames Prediction for Learned Video Compression](https://mlsanity.com/paper/2004.10290/) (2020)
- [Video Compression With Rate-Distortion Autoencoders](https://mlsanity.com/paper/1908.05717/) (2019)
- [Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks](https://mlsanity.com/paper/1703.10114/) (2017)
- [Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement](https://mlsanity.com/paper/2003.01966/) (2020)
- [Content Adaptive and Error Propagation Aware Deep Video Compression](https://mlsanity.com/paper/2003.11282/) (2020)
- [Learning Accurate Entropy Model with Global Reference for Image Compression](https://mlsanity.com/paper/2010.08321/) (2020)
- [Learned Video Compression via Joint Spatial-Temporal Correlation Exploration](https://mlsanity.com/paper/1912.06348/) (2019)

## Built on by (most cited first, 4 of 4)

- [Bit Allocation using Optimization](https://mlsanity.com/paper/2209.09422/) (2022)
- [Slimmable Video Codec](https://mlsanity.com/paper/2205.06754/) (2022)
- [Accelerating Learned Video Compression via Low-Resolution Representation Learning](https://mlsanity.com/paper/2407.16418/) (2024)
- [Error-Propagation-Free Learned Video Compression With Dual-Domain Progressive Temporal Alignment](https://mlsanity.com/paper/2512.10450/) (2025)

## Abstract (arXiv)

The framework of dominant learned video compression methods is usually composed of motion prediction modules as well as motion vector and residual image compression modules, suffering from its complex structure and error propagation problem. Approaches have been proposed to reduce the complexity by replacing motion prediction modules with implicit flow networks. Error propagation aware training strategy is also proposed to alleviate incremental reconstruction errors from previously decoded frames. Although these methods have brought some improvement, little attention has been paid to the framework itself. Inspired by the success of learned image compression through simplifying the framework with a single deep neural network, it is natural to expect a better performance in video compression via a simple yet appropriate framework. Therefore, we propose a framework to directly compress raw-pixel frames (rather than residual images), where no extra motion prediction module is required. Instead, an entropy model is used to estimate the spatiotemporal redundancy in a latent space rather than pixel level, which significantly reduces the complexity of the framework. Specifically, the whole framework is a compression module, consisting of a unified auto-encoder which produces identically distributed latents for all frames, and a spatiotemporal entropy estimation model to minimize the entropy of these latents. Experiments showed that the proposed method outperforms state-of-the-art (SOTA) performance under the metric of multiscale structural similarity (MS-SSIM) and achieves competitive results under the metric of PSNR.