Learning for Video Compression
Abstract
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 and binarization. The 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.
- Publication:
-
IEEE Transactions on Circuits and Systems for Video Technology
- Pub Date:
- February 2020
- DOI:
- arXiv:
- arXiv:1804.09869
- Bibcode:
- 2020ITCSV..30..566C
- Keywords:
-
- Image coding;
- Video compression;
- Spatiotemporal phenomena;
- Image reconstruction;
- Transform coding;
- Codecs;
- Video coding;
- learning;
- PixelMotionCNN;
- Computer Science - Multimedia;
- Electrical Engineering and Systems Science - Image and Video Processing
- E-Print:
- Accepted by IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)