Two Variational Models for Image Denoising Using Jacobian of Normals

Variational models with second order regularizers can efficiently overcome the problems of staircasing effects caused by first models. However, different types may lead to properties feature preserving in restored images. In this paper, we show two variational regularizers. The one is bounded Hessian model Jacobian normals, which uses image intensity normals as regularizer, it an extension classical (BH) model. total generalized variation (TGV) replacing gradients TGV normals. common objective improve preserving, such edge, contrast and smoothness preservation. Additionally, their Alternating Direction Method Multipliers (ADMM) are designed introducing some proper auxiliary variables, Lagrange multipliers penalty parameters decompose original into simple minimization sub-problems solve. Extensive comparisons demonstrate that proposed superior regularizers, especially edge corner preservation, smoothness, enhancement. Moreover, be also extended inpainting, deblurring,