Image reconstruction through metamorphosis
From MaRDI portal
Abstract: This article adapts the framework of metamorphosis to solve inverse problems in imaging that includes joint reconstruction and image registration. The deformations in question have two components, one that is a geometric deformation moving intensities and the other a deformation of intensity values itself, which, e.g., allows for appearance of a new structure. The idea developed here is to reconstruct an image from noisy and indirect observations by registering, via metamorphosis, a template to the observed data. Unlike a registration with only geometrical changes, this framework gives good results when intensities of the template are poorly chosen. We show that this method is a well-defined regularisation method (proving existence, stability and convergence) and present several numerical examples.
Recommendations
- Indirect image registration with large diffeomorphic deformations
- Template-based image reconstruction from sparse tomographic data
- Metamorphosis of images in reproducing kernel Hilbert spaces
- Shape-based image reconstruction using linearized deformations
- Regularization of inverse problems via time discrete geodesics in image spaces
Cites work
- A Lagrangian Gauss-Newton-Krylov solver for mass- and intensity-preserving diffeomorphic image registration
- A new linearized split Bregman iterative algorithm for image reconstruction in sparse-view X-ray computed tomography
- A new variational model for joint image reconstruction and motion estimation in spatiotemporal imaging
- Analytic Tomography
- Computing large deformation metric mappings via geodesic flows of diffeomorphisms
- Constrained H^1-regularization schemes for diffeomorphic image registration
- Generalized Bregman distances and convergence rates for non-convex regularization methods
- Geometry of image registration: the diffeomorphism group and momentum maps
- Gradient-flow-based semi-implicit finite-element method and its convergence analysis for image reconstruction
- Image extrapolation for the time discrete metamorphosis model: existence and applications
- Indirect image registration with large diffeomorphic deformations
- Mathematical methods in image reconstruction
- Metamorphoses of functional shapes in Sobolev spaces
- Metamorphoses through Lie group action
- Mixture of Kernels and Iterated Semidirect Product of Diffeomorphisms Groups
- Overview of the geometries of shape spaces and diffeomorphism groups
- Regularization of inverse problems via time discrete geodesics in image spaces
- Shape deformation analysis from the optimal control viewpoint
- Shape-based image reconstruction using linearized deformations
- Shapes and diffeomorphisms
- The mathematics of computerized tomography
Cited in
(19)- Self-adaptive image reconstruction inspired by insect compound eye mechanism
- Incorporation of a deformation prior in image reconstruction
- Template-based image reconstruction from sparse tomographic data
- Metamorphic image registration using a semi-Lagrangian scheme
- Joint reconstruction and low-rank decomposition for dynamic inverse problems
- Metamorphosis of images in reproducing kernel Hilbert spaces
- Shape-based image reconstruction using linearized deformations
- Stochastic metamorphosis with template uncertainties
- Indirect image registration with large diffeomorphic deformations
- Task adapted reconstruction for inverse problems
- Deconstructing <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si1.gif" overflow="scroll"><mml:mi mathvariant="script">R</mml:mi><mml:mi mathvariant="sans-serif">eo</mml:mi></mml:math>
- Regularization of inverse problems via time discrete geodesics in image spaces
- Template-based CT reconstruction with optimal transport and total generalized variation
- Template-based image reconstruction facing different topologies
- Image reconstruction in dynamic inverse problems with temporal models
- Deformation and transport of image data
- Regularization for time-dependent inverse problems: geometry of Lebesgue-Bochner spaces and algorithms
- Geometric shape matching for recovering protein conformations from single-particle cryo-EM data
- Joint manifold learning and optimal transport for dynamic imaging
This page was built for publication: Image reconstruction through metamorphosis
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5213315)
