基于非线性多重网格的TV^(p)配准

A TV^(p) Registration Model Based on Nonlinear Multigrid

设计了一种简化的p函数以简化TV^(p)配准模型,以滞后不动点迭代和Gauss⁃Seidel松弛迭代相结合构造光滑化方法,给出了一种有效的非线性多重网格(NMG)算法.数值实验表明该算法与不动点迭代方法(FP)相比具有更好的配准速度和配准精度.

Based on the multigrid strategy,a fast registration algorithm(NMG)is designed to solve the simplified TV^(p) registration model which preserves the discontinuity and smoothness of displacement field.The algorithm combines fixed point iteration and Gauss Seidel relaxation iteration as smoothing method,Numerical experiments show that the proposed algorithm has better registration speed and accuracy than fixed point iterative method(FP).