Hierarchical Autoregressive Modeling for Neural Video Compression
Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/privateyoung/Youtube-NTOfficialIn papernone★ 14
- github.com/buggyyang/youtube-ntOfficialIn papernone★ 14
- github.com/buggyyang/hier-video-compressionOfficialIn paperpytorch★ 3
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.