arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.00531eess.IVcs.CVcs.LG
收藏

用于B帧编码的扩展神经网络P帧编解码器

Extending Neural P-frame Codecs for B-frame Coding

Qualcomm AI Research(高通人工智能研究院)

Reza Pourreza, Taco S Cohen

摘要:

虽然大多数神经视频编解码器解决P帧编码(从过去的帧预测每一帧),但在本文中,我们解决B帧压缩(使用过去和未来的参考帧预测帧)。我们的B-框架解决方案是基于现有的P-框架方法。因此,B帧编码能力可以很容易地添加到现有的神经编解码器。我们的B帧编码方法的基本思想是内插的两个参考帧,以产生一个单一的参考帧,然后使用它与现有的P帧编解码器编码的输入B帧。我们的研究表明,内插帧是一个更好的参考P帧编解码器相比,使用前一帧通常是这样做。我们的结果表明,使用所提出的方法与现有的P帧编解码器可以导致28.5%的节省比特率的UVG数据集相比,P帧编解码器,同时产生相同的视频质量。

英文摘要:

While most neural video codecs address P-frame coding (predicting each frame from past ones), in this paper we address B-frame compression (predicting frames using both past and future reference frames). Our B-frame solution is based on the existing P-frame methods. As a result, B-frame coding capability can easily be added to an existing neural codec. The basic idea of our B-frame coding method is to interpolate the two reference frames to generate a single reference frame and then use it together with an existing P-frame codec to encode the input B-frame. Our studies show that the interpolated frame is a much better reference for the P-frame codec compared to using the previous frame as is usually done. Our results show that using the proposed method with an existing P-frame codec can lead to 28.5%saving in bit-rate on the UVG dataset compared to the P-frame codec while generating the same video quality.

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。

↑