1 code implementation • CVPR 2023 • Steffen Czolbe, Adrian V. Dalca
We introduce Neuralizer, a single model that generalizes to previously unseen neuroimaging tasks and modalities without the need for re-training or fine-tuning.
1 code implementation • NeurIPS 2021 • Steffen Czolbe, Aasa Feragen, Oswin Krause
As a first step towards solving such alignment problems, we propose an unsupervised algorithm for the detection of changes in image topology.
1 code implementation • 20 Apr 2021 • Steffen Czolbe, Oswin Krause, Aasa Feragen
We propose a semantic similarity metric for image registration.
1 code implementation • 30 Mar 2021 • Steffen Czolbe, Kasra Arnavaz, Oswin Krause, Aasa Feragen
Probabilistic image segmentation encodes varying prediction confidence and inherent ambiguity in the segmentation problem.
1 code implementation • NeurIPS 2020 • Steffen Czolbe, Oswin Krause, Ingemar Cox, Christian Igel
To train Variational Autoencoders (VAEs) to generate realistic imagery requires a loss function that reflects human perception of image similarity.
1 code implementation • 11 Nov 2020 • Steffen Czolbe, Oswin Krause, Aasa Feragen
We propose a semantic similarity metric for image registration.
1 code implementation • 26 Jun 2020 • Steffen Czolbe, Oswin Krause, Ingemar Cox, Christian Igel
To train Variational Autoencoders (VAEs) to generate realistic imagery requires a loss function that reflects human perception of image similarity.