39 citations · 95 across the 35 of their papers we have counts for
6 papers · 1 filter
diffConv: Analyzing Irregular Point Clouds with an Irregular View
Manxi Lin, Aasa Feragen
Standard spatial convolutions assume input data with a regular neighborhood structure. Existing methods typically generalize convolution to the irregular point cloud domain by fixi…
Graph2Graph Learning with Conditional Autoregressive Models
Guan Wang, Francois Bernard Lauze, Aasa Feragen
We present a graph neural network model for solving graph-to-graph learning problems. Most deep learning on graphs considers ``simple'' problems such as graph classification or reg…
Spot the Difference: Detection of Topological Changes via Geometric Alignment
Steffen Czolbe, Aasa Feragen, Oswin Krause
Geometric alignment appears in a variety of applications, ranging from domain adaptation, optimal transport, and normalizing flows in machine learning; optical flow and learned aug…
Quantifying Topology In Pancreatic Tubular Networks From Live Imaging 3D Microscopy
Kasra Arnavaz, Oswin Krause, Kilian Zepf +5
Motivated by the challenging segmentation task of pancreatic tubular networks, this paper tackles two commonly encountered problems in biomedical imaging: Topological consistency o…
Semantic similarity metrics for learned image registration
Steffen Czolbe, Oswin Krause, Aasa Feragen
We propose a semantic similarity metric for image registration. Existing metrics like Euclidean Distance or Normalized Cross-Correlation focus on aligning intensity values, giving…
Is segmentation uncertainty useful?
Steffen Czolbe, Kasra Arnavaz, Oswin Krause +1
Probabilistic image segmentation encodes varying prediction confidence and inherent ambiguity in the segmentation problem. While different probabilistic segmentation models are des…