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.
@article{arxiv.2010.10258,
title = {Hierarchical Autoregressive Modeling for Neural Video Compression},
author = {Ruihan Yang and Yibo Yang and Joseph Marino and Stephan Mandt},
journal= {arXiv preprint arXiv:2010.10258},
year = {2023}
}