Video Compression based on Jointly Learned Down-Sampling and Super-Resolution Networks

With the blooming of deep learning technology in computer vision, the integration of deep learning and the traditional video coding has made significant improvements, especially applying the super-resolution neural network as the post-processing module in the down-sampling-based video compression framework. However, the pre-processing module lacks back-propagated gradients for jointly considering down-sampling and up-sampling due to the non-differentiability of the traditional video codec. In this paper, we propose an end- to-end down-sampling-based video compression framework applying convolutional neural networks both as down-sampling and upsampling. We use a virtual codec neural network to approximate the actual video codec so that the gradient can be effectively back-propagated for joint training. Experimental results show the superiority of our proposed framework compared with the predefined down-sampling-based video compression and various methods of joint training.