Optimized Convolutional Neural Networks for Video Intra Prediction

Based on a previously published neural network-based video intra prediction approach, this paper proposes and evaluates several extensions of both the training process as well as the network architectures. In particular, the influence of coding artifacts in the training samples as well as the effect of using different approximations of the residual coding costs as loss functions are investigated. In addition, the architecture is optimized and extended by final deconvolutional layers. Combined with the use of network pruning, it was not only possible to increase the achieved compression gain in comparison to the previous work, but also to decrease the needed number of floating point operations per pixel by more than 72% at the same time.