Learning for Video Compression
This work addresses the problem of improving video compression efficiency for applications like streaming and storage by introducing a novel learning-based approach, though it is incremental as it builds on existing compression methods.
The paper tackles the challenge of integrating motion predictive coding into neural networks for video compression by proposing PixelMotionCNN (PMCNN), which models spatiotemporal coherence to enable predictive coding within a learning-based framework. Experimental results show superior performance compared to MPEG-2 and comparable results with H.264, even without entropy coding or complex configurations.
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 PixelMotionCNN (PMCNN) which includes motion extension and hybrid prediction networks. PMCNN can model spatiotemporal coherence to effectively perform predictive coding inside the learning network. On the basis of PMCNN, we further explore a learning-based framework for video compression with additional components of iterative analysis/synthesis, binarization, etc. Experimental 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.