Robust Image Restoration Based on Adaptive Multiple Columns Generative Model
Yongchao Wang, Xiaohua Li, Lei Zhao · 2016
During the process of film post-production, images usually need denoising and completion. And aiming at finishing these two aspects, there emerged a package-based restoration method. This paper proposes an algorithm of image background restoration based on generative model (AMC -RBM). This algorithm is a novel technology, which uses RBM (restricted boltzmann machine) not only to calculate the optimal weights by solving a nonlinear optimization program, but also to train a distributed network to predict the optimal weights. At the time of testing we don't need the concise void categories of noise or completion and care about statistics either. Moreover, we can even show that system is robust enough with regard to voids beyond the training set.