1 code implementation • 28 Feb 2023 • Josua Sassen, Klaus Hildebrandt, Martin Rumpf, Benedikt Wirth
Parametrizations of data manifolds in shape spaces can be computed using the rich toolbox of Riemannian geometry.
1 code implementation • 22 Aug 2022 • Juliane Braunsmann, Marko Rajković, Martin Rumpf, Benedikt Wirth
The encoder embeds the input data manifold into a lower-dimensional latent space, while the decoder represents the inverse map, providing a parametrization of the data manifold by the manifold in latent space.
no code implementations • 27 Apr 2021 • Juliane Braunsmann, Marko Rajković, Martin Rumpf, Benedikt Wirth
The encoder provides an embedding from the input data manifold into a latent space which may then be used for further processing.
no code implementations • ICCV 2015 • Chao Zhang, Behrend Heeren, Martin Rumpf, William A. P. Smith
In this paper we describe how to perform Principal Components Analysis in "shell space".
no code implementations • 22 Mar 2013 • Benjamin Berkels, Ivan Cabrilo, Sven Haller, Martin Rumpf, Carlo Schaller
Brain shift, i. e. the change in configuration of the brain after opening the dura mater, is a key problem in neuronavigation.