Markus Kaiser
Siemens
19 Papers
119 Citations
Markus Kaiser is an academic researcher from Siemens. The author has contributed to research in topics: Gaussian process & Inference. The author has an hindex of 6, co-authored 19 publications. Previous affiliations of Markus Kaiser include Otto-von-Guericke University Magdeburg & Technische Universität München.
Chat about Author
Papers
Patent
Method and system for registration of ultrasound and physiological models to X-ray fluoroscopic images
Peter Mountney,Markus Kaiser,Ingmar Voigt,Matthias John,Razvan Ioan Ionasec,Jan Dr. Boese,Dorin Comaniciu +6 more
- 18 May 2012
TL;DR: In this paper, a method and system for registering ultrasound images and physiological models to x-ray fluoroscopy images is disclosed, where a 2D location of an ultrasound probe is detected in the fluoroscopic image.
23
•Proceedings Article
Bayesian Alignments of Warped Multi-Output Gaussian Processes
Markus Kaiser,Clemens Otte,Thomas A. Runkler,Carl Henrik Ek +3 more
- 03 Dec 2018
TL;DR: An efficient variational approximation based on nested variational compression is presented and it is shown how the model can be used to extract shared information between dependent time series, recovering an interpretable functional decomposition of the learning problem.
•Posted Content
Compositional uncertainty in deep Gaussian processes
Ivan Ustyuzhaninov,Ieva Kazlauskaite,Markus Kaiser,Erik Bodin,Neill D. F. Campbell,Carl Henrik Ek +5 more
TL;DR: It is argued that such an inference scheme is suboptimal, not taking advantage of the potential of the model to discover the compositional structure in the data, and examines alternative variational inference schemes allowing for dependencies across different layers.
19
2D/3D registration of TEE probe from two non-orthogonal C-arm directions.
Markus Kaiser,Markus Kaiser,Matthias John,Tobias Heimann,Alexander Brost,Thomas Neumuth,Georg Rose +6 more
- 14 Sep 2014
TL;DR: This work automates the automation of a novel registration approach that handles translation and rotation of a volume in a way that in-plane parameters are kept invariant and independent of the angle offset between both projections in a double-oblique setting.
Significant acceleration of 2D-3D registration-based fusion of ultrasound and x-ray images by mesh-based DRR rendering
Markus Kaiser,Matthias John,Anja Borsdorf,Peter Mountney,Razvan Ioan Ionasec,Alois Nöttling,Philipp Kiefer,Jörg Seeburger,Thomas Neumuth +8 more
TL;DR: The main novelty is to generate the projection images (DRR) of the 3D object not via volume ray-casting but instead via a fast rendering of triangular meshes, which could potentially accelerate other applications of 2D-3D registrations, e.g. the registration of implant models with X-ray images.