论文标题
双向学习视频压缩的端到端率延伸优化
End-to-End Rate-Distortion Optimization for Bi-Directional Learned Video Compression
论文作者
论文摘要
传统的视频压缩方法采用线性变换和块运动模型，运动估计，模式和量化参数选择的步骤以及熵编码是由于端到端优化问题的组合性质而单独优化的。学习的视频压缩允许对所有非线性模块，量化参数和熵模型的端到端率延伸优化训练。虽然先前在学习视频压缩的工作考虑训练是基于对连续帧的端到端成本优化的顺序视频编解码器，但在传统的视频压缩中众所周知，层次结构，双向编码超过顺序压缩。在本文中，我们首次提出了通过在固定尺寸的图片组（GOP）上积累成本函数（GOP）来累积成本函数，从而首次提出了对分层的双向运动的端到端优化。实验结果表明，我们提出的学识渊博的双向{\ it GOP编码器}的速率降低性能优于预期的最先进的端到端优化学习的顺序压缩。
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.
