English

Insights from Generative Modeling for Neural Video Compression

Image and Video Processing 2024-10-28 v2 Computer Vision and Pattern Recognition Machine Learning

Abstract

While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images. In a similar spirit, we view recently proposed neural video coding algorithms through the lens of deep autoregressive and latent variable modeling. We present these codecs as instances of a generalized stochastic temporal autoregressive transform, and propose new avenues for further improvements inspired by normalizing flows and structured priors. We propose several architectures that yield state-of-the-art video compression performance on high-resolution video and discuss their tradeoffs and ablations. In particular, we propose (i) improved temporal autoregressive transforms, (ii) improved entropy models with structured and temporal dependencies, and (iii) variable bitrate versions of our algorithms. Since our improvements are compatible with a large class of existing models, we provide further evidence that the generative modeling viewpoint can advance the neural video coding field.

Keywords

Cite

@article{arxiv.2107.13136,
  title  = {Insights from Generative Modeling for Neural Video Compression},
  author = {Ruihan Yang and Yibo Yang and Joseph Marino and Stephan Mandt},
  journal= {arXiv preprint arXiv:2107.13136},
  year   = {2024}
}

Comments

This work has been submitted to the IEEE for publication as an extension work of arXiv:2010.10258. arXiv admin note: text overlap with arXiv:2010.10258

R2 v1 2026-06-24T04:34:57.339Z