16 citations · 22 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021★ 5 cited
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…
cs.LG2020★ 16 cited
A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model
Steffen Czolbe, Oswin Krause, Ingemar Cox +1
To train Variational Autoencoders (VAEs) to generate realistic imagery requires a loss function that reflects human perception of image similarity. We propose such a loss function…