no code implementations • 25 Jan 2024 • Martin Hanik, Gabriele Steidl, Christoph von Tycowicz
We propose two graph neural network layers for graphs with features in a Riemannian manifold.
1 code implementation • 30 May 2023 • Martin Hanik, Benjamin Ducke, Hans-Christian Hege, Friederike Fless, Christoph von Tycowicz
By performing regression in shape space, we find that for Roman sundials, the bend of the sundials' shadow-receiving surface changes with the location's latitude.
1 code implementation • 30 Mar 2023 • Esfandiar Nava-Yazdani, Felix Ambellan, Martin Hanik, Christoph von Tycowicz
We propose a generic spatiotemporal framework to analyze manifold-valued measurements, which allows for employing an intrinsic and computationally efficient Riemannian hierarchical model.
no code implementations • 9 Dec 2022 • Doğa Türkseven, Islem Rekik, Christoph von Tycowicz, Martin Hanik
Predicting the future development of an anatomical shape from a single baseline observation is a challenging task.
1 code implementation • 17 Jun 2021 • Martin Hanik, Mehmet Arif Demirtaş, Mohammed Amine Gharsallaoui, Islem Rekik
On top of that, we introduce a novel, fully modular sample selection method to select the best samples to learn from for our target prediction task.