English

End-to-End Rate-Distortion Optimization for Bi-Directional Learned Video Compression

Image and Video Processing 2021-05-28 v2 Computer Vision and Pattern Recognition

Abstract

Conventional video compression methods employ a linear transform and block motion model, and the steps of motion estimation, mode and quantization parameter selection, and entropy coding are optimized individually due to combinatorial nature of the end-to-end optimization problem. Learned video compression allows end-to-end rate-distortion optimized training of all nonlinear modules, quantization parameter and entropy model simultaneously. While previous work on learned video compression considered training a sequential video codec based on end-to-end optimization of cost averaged over pairs of successive frames, it is well-known in conventional video compression that hierarchical, bi-directional coding outperforms sequential compression. In this paper, we propose for the first time end-to-end optimization of a hierarchical, bi-directional motion compensated learned codec by accumulating cost function over fixed-size groups of pictures (GOP). Experimental results show that the rate-distortion performance of our proposed learned bi-directional {\it GOP coder} outperforms the state-of-the-art end-to-end optimized learned sequential compression as expected.

Keywords

Cite

@article{arxiv.2008.05028,
  title  = {End-to-End Rate-Distortion Optimization for Bi-Directional Learned Video Compression},
  author = {M. Akin Yilmaz and A. Murat Tekalp},
  journal= {arXiv preprint arXiv:2008.05028},
  year   = {2021}
}

Comments

This work is accepted for publication in IEEE ICIP 2020

R2 v1 2026-06-23T17:47:35.861Z