C
Christoph Jud
Researcher at University of Basel
Publications - 36
Citations - 570
Christoph Jud is an academic researcher from University of Basel. The author has contributed to research in topics: Image registration & Gaussian process. The author has an hindex of 9, co-authored 34 publications receiving 408 citations. Previous affiliations of Christoph Jud include University Hospital of Basel.
Papers
More filters
Journal ArticleDOI
Gaussian Process Morphable Models
TL;DR: This paper model the shape variations with a Gaussian process, which they represent using the leading components of its Karhunen-Loève expansion, and introduces a simple algorithm for fitting a GPMM to a surface or image, which results in a non-rigid registration approach whose regularization properties are defined by a G PMM.
Posted Content
Gaussian Process Morphable Models
TL;DR: The Gaussian Process Morphable Models (GPMM) as discussed by the authors model the shape variations with a Gaussian process, which they represent using the leading components of its Karhunen-Loeve expansion.
Posted Content
AirLab: Autograd Image Registration Laboratory.
TL;DR: The "Autograd Image Registration Laboratory" (AIRLab), an open laboratory for image registration tasks, where the analytic gradients of the objective function are computed automatically and the device where the computations are performed, on a CPU or a GPU, is transparent.
Book ChapterDOI
Using landmarks as a deformation prior for hybrid image registration
TL;DR: Gaussian process regression is used to model the deformations as a Gaussian process and regard the landmarks as additional information on the admissible deformations, which leads to a new, probabilistic regularization term that penalizes deformations that do not agree with the modeled landmark uncertainty.
Book ChapterDOI
A Unified Approach to Shape Model Fitting and Non-rigid Registration
TL;DR: This paper uses the well known formulation of non-rigid registration as the problem of fitting a Gaussian process model, whose covariance function favors smooth deformations, and uses the Nystrom method to formulate it as a parametric fitting problem of the same form as shape model fitting.