# Feedback Recurrent Autoencoder for Video Compression

arXiv: https://arxiv.org/abs/2004.04342 · HTML: https://mlsanity.com/paper/2004.04342/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2020.

## Built on by (most cited first, 30 of 30)

- [COIN++: Neural Compression Across Modalities](https://mlsanity.com/paper/2201.12904/) (2022)
- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [VCT: A Video Compression Transformer](https://mlsanity.com/paper/2206.07307/) (2022)
- [ELF-VC: Efficient Learned Flexible-Rate Video Coding](https://mlsanity.com/paper/2104.14335/) (2021)
- [Implicit Neural Video Compression](https://mlsanity.com/paper/2112.11312/) (2021)
- [CANF-VC: Conditional Augmented Normalizing Flows for Video Compression](https://mlsanity.com/paper/2207.05315/) (2022)
- [Perceptual Learned Video Compression with Recurrent Conditional GAN](https://mlsanity.com/paper/2109.03082/) (2021)
- [Neural Video Compression using GANs for Detail Synthesis and Propagation](https://mlsanity.com/paper/2107.12038/) (2021)
- [Contrastively Disentangled Sequential Variational Autoencoder](https://mlsanity.com/paper/2110.12091/) (2021)
- [Extending Neural P-frame Codecs for B-frame Coding](https://mlsanity.com/paper/2104.00531/) (2021)
- [Progressive Neural Image Compression with Nested Quantization and Latent Ordering](https://mlsanity.com/paper/2102.02913/) (2021)
- [MobileCodec: Neural Inter-frame Video Compression on Mobile Devices](https://mlsanity.com/paper/2207.08338/) (2022)
- [Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set](https://mlsanity.com/paper/2111.10302/) (2021)
- [B-CANF: Adaptive B-frame Coding with Conditional Augmented Normalizing Flows](https://mlsanity.com/paper/2209.01769/) (2022)
- [Advancing Learned Video Compression with In-loop Frame Prediction](https://mlsanity.com/paper/2211.07004/) (2022)
- [MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Device](https://mlsanity.com/paper/2310.01258/) (2023)
- [On the Choice of Perception Loss Function for Learned Video Compression](https://mlsanity.com/paper/2305.19301/) (2023)
- [Insights from Generative Modeling for Neural Video Compression](https://mlsanity.com/paper/2107.13136/) (2021)
- [Rate-Distortion-Perception Tradeoff Based on the Conditional-Distribution Perception Measure](https://mlsanity.com/paper/2401.12207/) (2024)
- [Reducing Redundancy in the Bottleneck Representation of the Autoencoders](https://mlsanity.com/paper/2202.04629/) (2022)
- [Boosting neural video codecs by exploiting hierarchical redundancy](https://mlsanity.com/paper/2208.04303/) (2022)
- [NU-Class Net: A Novel Approach for Video Quality Enhancement](https://mlsanity.com/paper/2401.01163/) (2024)
- [Region-of-Interest Based Neural Video Compression](https://mlsanity.com/paper/2203.01978/) (2022)
- [Low-Latency Neural Stereo Streaming](https://mlsanity.com/paper/2403.17879/) (2024)
- [Latent Discretization for Continuous-time Sequence Compression](https://mlsanity.com/paper/2212.13659/) (2022)
- [ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation](https://mlsanity.com/paper/2603.17812/) (2026)
- [Learned Hierarchical B-frame Coding with Adaptive Feature Modulation for YUV 4:2:0 Content](https://mlsanity.com/paper/2212.14187/) (2022)
- [MNeRV: A Multilayer Neural Representation for Videos](https://mlsanity.com/paper/2407.07347/) (2024)
- [Enhancing Video Understanding: Deep Neural Networks for Spatiotemporal Analysis](https://mlsanity.com/paper/2502.07277/) (2025)
- [On Self-Adaptive Perception Loss Function for Sequential Lossy Compression](https://mlsanity.com/paper/2502.10628/) (2025)

## Abstract (arXiv)

Recent advances in deep generative modeling have enabled efficient modeling of high dimensional data distributions and opened up a new horizon for solving data compression problems. Specifically, autoencoder based learned image or video compression solutions are emerging as strong competitors to traditional approaches. In this work, We propose a new network architecture, based on common and well studied components, for learned video compression operating in low latency mode. Our method yields state of the art MS-SSIM/rate performance on the high-resolution UVG dataset, among both learned video compression approaches and classical video compression methods (H.265 and H.264) in the rate range of interest for streaming applications. Additionally, we provide an analysis of existing approaches through the lens of their underlying probabilistic graphical models. Finally, we point out issues with temporal consistency and color shift observed in empirical evaluation, and suggest directions forward to alleviate those.