arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.09776eess.IVcs.ITcs.LGcs.MMmath.IT
收藏

用于基于神经网络的视频编解码器增强的可微分比特率估计

Differentiable bit-rate estimation for neural-based video codec enhancement

Qualcomm AI Research(高通人工智能研究院)

Amir Said, Manish Kumar Singh, Reza Pourreza

摘要:

神经网络(NN)可以通过对编码视频进行预处理和后处理来改进标准视频压缩。对于最佳NN训练,标准编解码器需要用编解码器代理替换,该编解码器代理可以提供估计的比特率和失真的导数,其用于梯度反向传播。由于标准编解码器的熵编码被设计为考虑变换系数之间的非线性依赖性,所以比特率不能用简单的每系数估计器很好地近似。本文提出了一种用于比特率估计的新方法,该方法类似于训练端到端神经编解码器中采用的类型,并且能够有效地考虑这些统计依赖性。它是从一个数学模型定义的,该模型提供了估计值及其梯度的封闭式公式,降低了计算复杂性。实验结果表明,该方法在估计HEVC/H.265编解码器的比特率的准确性。

英文摘要:

Neural networks (NN) can improve standard video compression by pre- and post-processing the encoded video. For optimal NN training, the standard codec needs to be replaced with a codec proxy that can provide derivatives of estimated bit-rate and distortion, which are used for gradient back-propagation. Since entropy coding of standard codecs is designed to take into account non-linear dependencies between transform coefficients, bit-rates cannot be well approximated with simple per-coefficient estimators. This paper presents a new approach for bit-rate estimation that is similar to the type employed in training end-to-end neural codecs, and able to efficiently take into account those statistical dependencies. It is defined from a mathematical model that provides closed-form formulas for the estimates and their gradients, reducing the computational complexity. Experimental results demonstrate the method's accuracy in estimating HEVC/H.265 codec bit-rates.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑