Performance analysis of generated predictive frames using PredNet with multiple convolution kernels
Kanato Sakama, Shun-ichi Sekiguchi, Wataru Kameyama · 2023
DNN-based video frame prediction can be a powerful tool to improve performance of motion-compensated prediction in video coding. In this paper, we propose a method applying multiple convolution kernels with different sizes to PredNet, which is one of the DNN-based video prediction schemes, to enhance the prediction accuracy by incorporating context adaptivity in its convolutional LSTM layers. We analyze the prediction performance of the proposal, and the results show that applying multiple-size kernels is effective than applying a single-size kernel in terms of prediction error reduction.