Filter-based mean-field inference for random fields with higher-order terms and product label-spaces

DOI10.1007/s11263-014-0708-6zbMath1328.68252OpenAlexW2086225343MaRDI QIDQ901813

Philip H. S. Torr, Jonathan Warrell, Vibhav Vineet

Publication date: 6 January 2016

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

Full work available at URL: https://doi.org/10.1007/s11263-014-0708-6

zbMATH Keywords

CRFobject class segmentationbilateral filtersdense stereo reconstructionhigher-order potentialsmean-field methods

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Image analysis in multivariate analysis (62H35) Computing methodologies for image processing (68U10) Machine vision and scene understanding (68T45)

Related Items (3)

Conditional random fields for image labeling ⋮ Revisiting Deep Structured Models for Pixel-Level Labeling with Gradient-Based Inference ⋮ Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials

Uses Software

• GrabCut
• PASCAL VOC
• GeoS

Cites Work

• Unnamed Item
• Unnamed Item
• Inference methods for CRFs with co-occurrence statistics
• Harmony potentials fusing global and local scale for semantic image segmentation
• Bilateral Filtering: Theory and Applications
• Modeling the shape of the scene: A holistic representation of the spatial envelope

This page was built for publication: Filter-based mean-field inference for random fields with higher-order terms and product label-spaces