Flow incorporated neural network based lightweight video compression architecture

Abstract

The sudden surge in the video transmission over internet motivated the exploration of more promising and potent video compression architectures. Though the frame prediction based hand designed techniques are performing well and widely used but the recent deep learning based researches in this domain provided further directions of pure deep learning based next generation codecs. As the bandwidth over the internet is varying, adaptive bit rate representation is more suitable for video quality adjustment in tune with bandwidth variation. The proposed architecture comprises of end to end trainable video compression network consisting of majorly three modules namely-motion extension network, flow autoencoder and frame autoencoder. Frame autoencoder generates the individual compressed frames, flow autoencoder is used for optical flow based motion compensation chore and next frame is predicted by the motion extension network. The network is designed and evaluated in incremental manner. The analysis of the outcomes demonstrates the promising performance of the network quantitatively and qualitatively. Moreover, the results reveal that inclusion of optical flow based motion compensation network to the MotionNet architecture has enhanced the performance.