The diffusion performance analysis of variational PDE based neural network restoration models
Yadong Wu, Yu Sun, Hongying Zhang · 2008
In this paper, we introduce two variational PDEs (Partial Differential Equations) as the regularization terms to the image restoration model based on the modified Hopfield neural network. The performance of these regularization terms is analyzed from the viewpoint of nonlinear diffusion. It can be shown that the two proposed restoration models have superior edge preserving performance than the traditional restoration model.