Side Information Improvement Algorithm Based on Denoising Algorithm for Distributed Video Coding

Distributed Video Coding (DVC) is a new video coding scheme that mainly uses the availability of decoder side information to reduce the complexity of the encoder. The quality of the side information has an important influence on the performance of the distributed video coding system. At present, the generation of side information is mainly based on a model that uses inter-frame correlation for motion estimation. In order to make full use of the intra-frame self-similarity of the side information frame, we use the idea of image denoising, and propose an improved side information generation method. Since the initial side information frame can be viewed as a noisy version of the Wyner-Ziv (WZ) frame, improving the side information frame can be translated to denoising the frame. The experimental results show that the quality of the side information obtained by the proposed scheme has been significantly improved, thereby effectively improve the performance of distributed video coding.