Midrange geometric interactions for semantic segmentation. Constraints for continuous multi-label optimization

DOI10.1007/s11263-015-0828-7zbMath1398.68634OpenAlexW785873054MaRDI QIDQ1800049

Julia Diebold, Claudia Nieuwenhuis, Daniel Cremers

Publication date: 19 October 2018

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11263-015-0828-7

zbMATH Keywords

convex optimizationimage segmentationvariationaldirectional relationsgeometric relationsmidlevel range interactions

Mathematics Subject Classification ID

Computing methodologies for image processing (68U10) Pattern recognition, speech recognition (68T10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Uses Software

• iCoseg

Cites Work

• Unnamed Item
• Inference methods for CRFs with co-occurrence statistics
• A finite algorithm for finding the projection of a point onto the canonical simplex of \({\mathbb R}^ n\)
• Minimizing energies with hierarchical costs
• A first-order primal-dual algorithm for convex problems with applications to imaging
• A survey and comparison of discrete and continuous multi-label optimization approaches for the Potts model
• Tight Convex Relaxations for Vector-Valued Labeling
• Global Solutions of Variational Models with Convex Regularization
• Efficient Convex Optimization for Minimal Partition Problems with Volume Constraints

This page was built for publication: Midrange geometric interactions for semantic segmentation. Constraints for continuous multi-label optimization