# Adversarial Distortion for Learned Video Compression

arXiv: https://arxiv.org/abs/2004.09508 · HTML: https://mlsanity.com/paper/2004.09508/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2020.

## Built on by (most cited first, 8 of 8)

- [Perceptual Learned Video Compression with Recurrent Conditional GAN](https://mlsanity.com/paper/2109.03082/) (2021)
- [DVC-P: Deep Video Compression with Perceptual Optimizations](https://mlsanity.com/paper/2109.10849/) (2021)
- [On the Choice of Perception Loss Function for Learned Video Compression](https://mlsanity.com/paper/2305.19301/) (2023)
- [Extreme Video Compression with Pre-trained Diffusion Models](https://mlsanity.com/paper/2402.08934/) (2024)
- [Microdosing: Knowledge Distillation for GAN based Compression](https://mlsanity.com/paper/2201.02624/) (2022)
- [On Self-Adaptive Perception Loss Function for Sequential Lossy Compression](https://mlsanity.com/paper/2502.10628/) (2025)
- [A Mamba-based Perceptual Loss Function for Learning-based UGC Transcoding](https://mlsanity.com/paper/2603.25566/) (2026)
- [Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion](https://mlsanity.com/paper/2605.02849/) (2026)

## Abstract (arXiv)

In this paper, we present a novel adversarial lossy video compression model. At extremely low bit-rates, standard video coding schemes suffer from unpleasant reconstruction artifacts such as blocking, ringing etc. Existing learned neural approaches to video compression have achieved reasonable success on reducing the bit-rate for efficient transmission and reduce the impact of artifacts to an extent. However, they still tend to produce blurred results under extreme compression. In this paper, we present a deep adversarial learned video compression model that minimizes an auxiliary adversarial distortion objective. We find this adversarial objective to correlate better with human perceptual quality judgement relative to traditional quality metrics such as MS-SSIM and PSNR. Our experiments using a state-of-the-art learned video compression system demonstrate a reduction of perceptual artifacts and reconstruction of detail lost especially under extremely high compression.