Hierarchical Autoregressive Modeling for Neural Video Compression

Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt

Keywords: Compression, Video Compression, Generative Models, Autoregressive Models

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.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Code: [ buggyyang/youtube-nt](https://github.com/buggyyang/youtube-nt) + [ 2 community implementations](https://paperswithcode.com/paper/?openreview=TK_6nNb_C7q)

Data: [Vimeo90K](https://paperswithcode.com/dataset/vimeo90k-1)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2010.10258/code)