Differentiable bit-rate estimation for neural-based video codec enhancement
This work addresses the challenge of training neural networks for video compression enhancement, offering a more efficient and accurate bit-rate estimation method, though it appears incremental as it builds on existing neural codec training approaches.
The paper tackles the problem of accurately estimating bit-rates for neural network-based video codec enhancement, which is hindered by non-linear dependencies in standard codecs, and presents a new differentiable estimation method that reduces computational complexity and demonstrates accuracy with HEVC/H.265 codecs.
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.