# Deep Hierarchical Video Compression

arXiv: https://arxiv.org/abs/2312.07126 · HTML: https://mlsanity.com/paper/2312.07126/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2023.

## Built on by (most cited first, 9 of 9)

- [Towards Practical Real-Time Neural Video Compression](https://mlsanity.com/paper/2502.20762/) (2025)
- [Bi-Directional Deep Contextual Video Compression](https://mlsanity.com/paper/2408.08604/) (2024)
- [NVC-1B: A Large Neural Video Coding Model](https://mlsanity.com/paper/2407.19402/) (2024)
- [High-Efficiency Neural Video Compression via Hierarchical Predictive Learning](https://mlsanity.com/paper/2410.02598/) (2024)
- [Att2CPC: Attention-Guided Lossy Attribute Compression of Point Clouds](https://mlsanity.com/paper/2410.17823/) (2024)
- [P-GSVC: Layered Progressive 2D Gaussian Splatting for Scalable Image and Video](https://mlsanity.com/paper/2603.10551/) (2026)
- [A Causal Diffusion Model for Video Reconstruction from Ultra-Low-Bitrate Representations](https://mlsanity.com/paper/2602.13837/) (2026)
- [Geometric Transformation-Embedded Mamba for Learned Video Compression](https://mlsanity.com/paper/2603.07912/) (2026)
- [Scalable Neural Video Representation Compression](https://mlsanity.com/paper/2609.04273/) (2026)

## Abstract (arXiv)

Recently, probabilistic predictive coding that directly models the conditional distribution of latent features across successive frames for temporal redundancy removal has yielded promising results. Existing methods using a single-scale Variational AutoEncoder (VAE) must devise complex networks for conditional probability estimation in latent space, neglecting multiscale characteristics of video frames. Instead, this work proposes hierarchical probabilistic predictive coding, for which hierarchal VAEs are carefully designed to characterize multiscale latent features as a family of flexible priors and posteriors to predict the probabilities of future frames. Under such a hierarchical structure, lightweight networks are sufficient for prediction. The proposed method outperforms representative learned video compression models on common testing videos and demonstrates computational friendliness with much less memory footprint and faster encoding/decoding. Extensive experiments on adaptation to temporal patterns also indicate the better generalization of our hierarchical predictive mechanism. Furthermore, our solution is the first to enable progressive decoding that is favored in networked video applications with packet loss.