Indirect Image Registration with Large Diffeomorphic Deformations

Chong Chen, Ozan Öktem

Research output: Contribution to journalArticlepeer-review

22 Citations (Scopus)


This paper adapts the large deformation diffeomorphic metric mapping framework for image registration to the indirect setting, where a template is registered against a target that is given through indirect noisy observations. The registration uses diffeomorphisms that transform the template through a (group) action. These diffeomorphisms are generated by solving a flow equation that is defined by a velocity field with certain regularity. The theoretical analysis includes a proof that indirect image registration has solutions (existence) that are stable and that converge as the data error tends to zero, so it becomes a well-defined regularization method. The paper concludes with examples of indirect image registration in 2D tomography with very sparse and/or highly noisy data.
Original languageEnglish
Pages (from-to)575-617
Number of pages43
JournalSIAM Journal on Imaging Sciences
Issue number1
Early online date1 Mar 2018
Publication statusPublished - 2018


Dive into the research topics of 'Indirect Image Registration with Large Diffeomorphic Deformations'. Together they form a unique fingerprint.

Cite this