# AIVC: Artificial Intelligence based Video Codec

arXiv: https://arxiv.org/abs/2202.04365 · HTML: https://mlsanity.com/paper/2202.04365/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2022.

## Built on by (most cited first, 6 of 6)

- [Video Event Restoration Based on Keyframes for Video Anomaly Detection](https://mlsanity.com/paper/2304.05112/) (2023)
- [IBVC: Interpolation-driven B-frame Video Compression](https://mlsanity.com/paper/2309.13835/) (2023)
- [Latent-Shift: Gradient of Entropy Helps Neural Codecs](https://mlsanity.com/paper/2308.00725/) (2023)
- [Reducing The Mismatch Between Marginal and Learned Distributions in Neural Video Compression](https://mlsanity.com/paper/2210.06596/) (2022)
- [NN-VVC: Versatile Video Coding boosted by self-supervisedly learned image coding for machines](https://mlsanity.com/paper/2401.10761/) (2024)
- [Exploiting Latent Properties to Optimize Neural Codecs](https://mlsanity.com/paper/2501.01231/) (2025)

## Abstract (arXiv)

This paper introduces AIVC, an end-to-end neural video codec. It is based on two conditional autoencoders MNet and CNet, for motion compensation and coding. AIVC learns to compress videos using any coding configurations through a single end-to-end rate-distortion optimization. Furthermore, it offers performance competitive with the recent video coder HEVC under several established test conditions. A comprehensive ablation study is performed to evaluate the benefits of the different modules composing AIVC. The implementation is made available at https://orange-opensource.github.io/AIVC/.