Skip to content

Latest commit

 

History

History
18 lines (11 loc) · 1.04 KB

README.md

File metadata and controls

18 lines (11 loc) · 1.04 KB

d_RPCA

Deformable Groupwise Image Registration using Low-Rank and Sparse Decomposition

  • A new groupwise distance measure for non-parametric image registration based on low-rank and sparse decompositions, inspired by Heber and Pock, 2014
  • Regularization through Total Variation or Curvature Penalty
  • Optimization is performed using iterative relinearization and the primal-dual hybrid gradient algorithm from Chambolle and Pock, 2011

Implementation in MATLAB.

Add your local copy of this repository to your MATLAB path. Then, simply run

Demo/demo_mf_nn_tv_registration_no_ref_ml.m

for a demo on synthetic image data with TV regularization.

As a method of comparison, a simple variance-based groupwise registration method as in Metz et al., 2011 is implemented as well. A demo is found in

Demo/demo_var_tv_registration_no_ref_ml.m