activity
20172022
most citedThe Swiss Army Knife for Image-to-Image Translation: Multi-Task Diffusion Models

17 citations · 43 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV202217 cited

The Swiss Army Knife for Image-to-Image Translation: Multi-Task Diffusion Models

Julia Wolleb, Robin Sandkühler, Florentin Bieder +1

Recently, diffusion models were applied to a wide range of image analysis tasks. We build on a method for image-to-image translation using denoising diffusion implicit models and i…

cs.CV20215 cited

Comparison of Methods Generalizing Max- and Average-Pooling

Florentin Bieder, Robin Sandkühler, Philippe C. Cattin

Max- and average-pooling are the most popular pooling methods for downsampling in convolutional neural networks. In this paper, we compare different pooling methods that generalize…

cs.CV201914 cited

Recurrent Registration Neural Networks for Deformable Image Registration

Robin Sandkühler, Simon Andermatt, Grzegorz Bauman +3

Parametric spatial transformation models have been successfully applied to image registration tasks. In such models, the transformation of interest is parameterized by a fixed set…

cs.CV2018

Spinal Cord Gray Matter-White Matter Segmentation on Magnetic Resonance AMIRA Images with MD-GRU

Antal Horvath, Charidimos Tsagkas, Simon Andermatt +3

The small butterfly shaped structure of spinal cord (SC) gray matter (GM) is challenging to image and to delinate from its surrounding white matter (WM). Segmenting GM is up to a p…

cs.CV2018

AirLab: Autograd Image Registration Laboratory

Robin Sandkühler, Christoph Jud, Simon Andermatt +1

Medical image registration is an active research topic and forms a basis for many medical image analysis tasks. Although image registration is a rather general concept specialized…

cs.CV2018

Pathology Segmentation using Distributional Differences to Images of Healthy Origin

Simon Andermatt, Antal Horváth, Simon Pezold +1

Fully supervised segmentation methods require a large training cohort of already segmented images, providing information at the pixel level of each image. We present a method to au…