Hierarchical Autoregressive Modeling for Neural Video Compression
Abstract
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.
Cite
Text
Yang et al. "Hierarchical Autoregressive Modeling for Neural Video Compression." International Conference on Learning Representations, 2021.Markdown
[Yang et al. "Hierarchical Autoregressive Modeling for Neural Video Compression." International Conference on Learning Representations, 2021.](https://mlanthology.org/iclr/2021/yang2021iclr-hierarchical/)BibTeX
@inproceedings{yang2021iclr-hierarchical,
title = {{Hierarchical Autoregressive Modeling for Neural Video Compression}},
author = {Yang, Ruihan and Yang, Yibo and Marino, Joseph and Mandt, Stephan},
booktitle = {International Conference on Learning Representations},
year = {2021},
url = {https://mlanthology.org/iclr/2021/yang2021iclr-hierarchical/}
}