# Slimmable Video Codec

arXiv: https://arxiv.org/abs/2205.06754 · HTML: https://mlsanity.com/paper/2205.06754/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 12 references that are in the map.
- First posted on arXiv 13 May 2022.

## Builds on (most cited first, 9 of 9)

- [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)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [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)
- [Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement](https://mlsanity.com/paper/2003.01966/) (2020)
- [Slimmable Compressive Autoencoders for Practical Neural Image Compression](https://mlsanity.com/paper/2103.15726/) (2021)
- [Spatiotemporal Entropy Model is All You Need for Learned Video Compression](https://mlsanity.com/paper/2104.06083/) (2021)

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

- [Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillation](https://mlsanity.com/paper/2312.02605/) (2023)
- [Scalable Neural Video Representation Compression](https://mlsanity.com/paper/2609.04273/) (2026)

## Abstract (arXiv)

Neural video compression has emerged as a novel paradigm combining trainable multilayer neural networks and machine learning, achieving competitive rate-distortion (RD) performances, but still remaining impractical due to heavy neural architectures, with large memory and computational demands. In addition, models are usually optimized for a single RD tradeoff. Recent slimmable image codecs can dynamically adjust their model capacity to gracefully reduce the memory and computation requirements, without harming RD performance. In this paper we propose a slimmable video codec (SlimVC), by integrating a slimmable temporal entropy model in a slimmable autoencoder. Despite a significantly more complex architecture, we show that slimming remains a powerful mechanism to control rate, memory footprint, computational cost and latency, all being important requirements for practical video compression.