Hierarchical Autoregressive Modeling for Neural Video Compression
Abstract
Domain fit: AI-adjacent · Paper appears method- or tooling-adjacent to AI workflows with partial ecosystem coverage.
Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models. We draw a connection between such autoregressive generative models and the task of lossy video compression. Specifically, we view recent neural video compression methods (Lu et al., 2019; Yang et al., 2020b; Agustssonet al., 2020) as instances of a generalized stochastic temporal autoregressive transform, and propose avenues for enhancement based on this insight. Comprehensive evaluations on large-scale video data show improved rate-distortion performance over both state-of-the-art neural and conventional video compression methods.
Results and benchmarks
Recent work by Marino et al.
Benchmark evidence is limited
Evidence graph: 3 refs, 3 links.
Utility signals: depth 50/100, grounding 75/100, status medium.
Implementation
No direct implementation yet
Maintained implementation evidence is not confirmed for this paper yet.
Use the implementation status and reproduction sections for the current action plan.
No verified maintained repo yet
There is no verified maintained implementation yet. Use this baseline plan to decide whether to prototype now or defer.
- No maintained paper-verified implementation was found; start with the closest related repositories below.
- Compare repo methods against the paper equations/algorithm before trusting metrics.
- Create a minimal baseline implementation from the paper and use adjacent repos as references.
Time to first repro: a few days
lucidrains/metacontroller is the closest maintained adjacent implementation (Matches contextual method/domain keyword: autoregressive model). It is not paper-verified; validate algorithm and evaluation setup against the paper before trusting reported metrics. Community adoption signal: 105 GitHub stars.
- Adjacent implementations are not paper-verified
- Recommended repository is adjacent and not paper-verified.
- Adjacent implementation match confidence is low.
Reproduction readiness
No repo
No verified implementation available
- No maintained repository has been identified for this paper. Check adjacent implementations or HF artifacts below.
Hardware requirements
- Expect multi-day setup/compute for meaningful reproduction based on current guidance.
Validation caveat
Repositories and ecosystem
Closest related implementations
These are not paper-verified. Use them as reference points when no direct implementation is available.
- lucidrains/metacontroller Adjacent · Confidence: Low · 105 stars
Matches contextual method/domain keyword: autoregressive model
No additional verified repositories beyond the primary recommendation.
Hugging Face artifacts
No trustworthy direct or curated related Hugging Face artifacts were found yet. Use targeted searches to quickly locate candidate models, datasets, and demos.
Tip: start with models, then check datasets and spaces if you need evaluation data or demos.
Research context
6
Citations
48
References
Tasks
Computer science, Lossy compression, Data compression, Latent variable, Pattern recognition (psychology), Generative grammar, Physical Sciences
Methods
Autoregressive model, STAR model, Generative model
Domains
Compression (physics), Artificial intelligence, Computer Vision and Pattern Recognition
Related papers
- Insights from Generative Modeling for Neural Video CompressionSearch on Paper2Code
2021 · Semantic similarity
- Deep Learning in Latent Space for Video Prediction and CompressionSearch on Paper2Code
2021 · Semantic similarity
- Deep Generative Video CompressionSearch on Paper2Code
2018 · Semantic similarity
- Feedback Recurrent Autoencoder for Video CompressionSearch on Paper2Code
2021 · Semantic similarity
- Deep hierarchical attention network for video descriptionSearch on Paper2Code
2018 · Semantic similarity
- From Deterministic to Generative: Multimodal Stochastic RNNs for Video CaptioningSearch on Paper2Code
2018 · Semantic similarity
Open this paper in HFEPX to review benchmark signals, evaluation modes, and human-feedback protocol context.
Open in HFEPXJump to Paper2Code search queries derived from this paper's research context.