Conditional Coding for Flexible Learned Video Compression

Abstract

This paper introduces a novel framework for end-to-end learned video coding. Image compression is generalized through conditional coding to exploit information from reference frames, allowing to process intra and inter frames with the same coder. The system is trained through the minimization of a rate-distortion cost, with no pre-training or proxy loss. Its flexibility is assessed under three coding configurations (All Intra, Low-delay P and Random Access), where it is shown to achieve performance competitive with the state-of-the-art video codec HEVC.

Cite

Text

Ladune et al. "Conditional Coding for Flexible Learned Video Compression." ICLR 2021 Workshops: Neural_Compression, 2021.

Markdown

[Ladune et al. "Conditional Coding for Flexible Learned Video Compression." ICLR 2021 Workshops: Neural_Compression, 2021.](https://mlanthology.org/iclrw/2021/ladune2021iclrw-conditional/)

BibTeX

@inproceedings{ladune2021iclrw-conditional,
  title     = {{Conditional Coding for Flexible Learned Video Compression}},
  author    = {Ladune, Théo and Philippe, Pierrick and Hamidouche, Wassim and Zhang, Lu and Déforges, Olivier},
  booktitle = {ICLR 2021 Workshops: Neural_Compression},
  year      = {2021},
  url       = {https://mlanthology.org/iclrw/2021/ladune2021iclrw-conditional/}
}