English

Conditional Coding and Variable Bitrate for Practical Learned Video Coding

Neural and Evolutionary Computing 2021-04-21 v2 Image and Video Processing Signal Processing

Abstract

This paper introduces a practical learned video codec. Conditional coding and quantization gain vectors are used to provide flexibility to a single encoder/decoder pair, which is able to compress video sequences at a variable bitrate. The flexibility is leveraged at test time by choosing the rate and GOP structure to optimize a rate-distortion cost. Using the CLIC21 video test conditions, the proposed approach shows performance on par with HEVC.

Keywords

Cite

@article{arxiv.2104.09103,
  title  = {Conditional Coding and Variable Bitrate for Practical Learned Video Coding},
  author = {Théo Ladune and Pierrick Philippe and Wassim Hamidouche and Lu Zhang and Olivier Déforges},
  journal= {arXiv preprint arXiv:2104.09103},
  year   = {2021}
}