Extending Neural P-frame Codecs for B-frame Coding
This work addresses video compression efficiency for applications like streaming and storage, but it is incremental as it builds directly on existing P-frame codecs.
The paper tackles the problem of B-frame compression in neural video codecs by extending existing P-frame methods, achieving a 28.5% bit-rate saving on the UVG dataset while maintaining the same video quality.
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.