Learning for Video Compression

One key challenge to learning-based video compression is that motion predictive coding, a very effective tool for video compression, can hardly be trained into a neural network. In this paper we propose the concept of VoxelCNN which includes motion extension and hybrid prediction networks. VoxelCNN can model spatiotemporal coherence to effectively perform predictive coding inside the learning network. On the basis of VoxelCNN, we further explore a learning based framework for video compression with additional components of iterative analysis/synthesis, binarization, etc. Experiment results demonstrate the effectiveness of the proposed scheme. Although entropy coding and complex configurations are not employed in this paper, we still demonstrate superior performance compared with MPEG-2 and achieve comparable results with H.264 codec. The proposed learning based scheme provides a possible new direction to further improve compression efficiency and functionalities of future video coding.