MAP image labeling using Wasserstein messages and geometric assignment

DOI10.1007/978-3-319-58771-4_30MaRDI QIDQ5864022zbMATH OpenOpenAlexFDO

Authors Freddie Åström, Ruben Hühnerbein, Fabrizio Savarino, Judit Recknagel, Christoph Schnörr

Publication date 3 June 2022

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-319-58771-4_30

zbMATH Keywords

assignment manifoldgraphical modelsimage labelingmessage passingmultiplicative updatesreplicator equationRiemannian gradient flowWasserstein distance

Mathematics Subject Classification ID

Numerical aspects of computer graphics, image analysis, and computational geometry (65D18)

Recommendations

• Image labeling based on graphical models using Wasserstein messages and geometric assignment
• Image labeling by assignment
• Numerical integration of Riemannian gradient flows for image labeling
• Learning adaptive regularization for image labeling using geometric assignment
• Unsupervised assignment flow: label learning on feature manifolds by spatially regularized geometric assignment

Cited in

(6)

• Image labeling by assignment
• Learning adaptive regularization for image labeling using geometric assignment
• Geometric labeling of image regions based on combination of multiple features
• Image labeling based on graphical models using Wasserstein messages and geometric assignment
• Numerical integration of Riemannian gradient flows for image labeling
• A variational perspective on the assignment flow

This page was built for publication: MAP image labeling using Wasserstein messages and geometric assignment

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5864022)