no code implementations • 19 Jan 2024 • Leon Frischauf, Otmar Scherzer, Cong Shi
Neural network with quadratic decision functions have been introduced as alternatives to standard neural networks with affine linear one.
no code implementations • 11 Aug 2022 • Fabian Parzer, Prashin Jethwa, Alina Boecker, Mayte Alfaro-Cuello, Otmar Scherzer, Glenn van de Ven
In this context, blobs may correspond to stars born in-situ versus those accreted from satellites, and the task of blob detection is to disentangle these components.
no code implementations • 3 Apr 2020 • Leon Frischauf, Melanie Melching, Otmar Scherzer
In this paper we propose a variational regularization method for denoising and inpainting of diffusion tensor magnetic resonance images.
Denoising Optimization and Control 47A52, 65J20
no code implementations • 23 Jun 2016 • Aniello Raffaele Patrone, Christian Valuch, Ulrich Ansorge, Otmar Scherzer
Saliency maps are used to understand human attention and visual fixation.
1 code implementation • 10 Jun 2015 • Lukas F. Lang, Otmar Scherzer
In this work we consider optical flow on evolving Riemannian 2-manifolds which can be parametrised from the 2-sphere.
no code implementations • 13 May 2015 • Aniello Raffale Patrone, Otmar Scherzer
In this paper we present a decomposition algorithm for computation of the spatial-temporal optical flow of a dynamic image sequence.
1 code implementation • 16 Dec 2013 • Clemens Kirisits, Lukas F. Lang, Otmar Scherzer
We propose a number of variational regularisation methods for the estimation and decomposition of motion fields on the $2$-sphere.
no code implementations • 1 Oct 2013 • Clemens Kirisits, Lukas F. Lang, Otmar Scherzer
We extend the concept of optical flow with spatiotemporal regularisation to a dynamic non-Euclidean setting.
no code implementations • 8 Jan 2013 • Clemens Kirisits, Lukas F. Lang, Otmar Scherzer
We extend the concept of optical flow to a dynamic non-Euclidean setting.