Joint learning for side information and correlation model based on linear regression model in distributed video coding

The coding efficiency of distributed video coding system is significantly determined by the side information quality and correlation model. Motivated by theoretical analysis of the maximum likelihood treatment for linear regression model, we propose a novel joint online learning model for side information generation and correlation model estimation in this paper. In our proposed scheme, each pixel in the side information is approximated as the linear weighted combination of samples within a local spatio-temporal neighboring space. Weights are trained in a self-feedback fashion, during which the correlation model parameters can also be achieved. The efficiency of the proposed joint learning model is confirmed experimentally.