Efficient relaxations for dense CRFs with sparse higher-order potentials
<p>Dense conditional random fields (CRFs) have become a popular framework for modelling several problems in computer vision such as stereo correspondence and multi-class semantic segmentation. By modelling long- range interactions, dense CRFs provide a labelling that captures finer detail than...
Hlavní autoři: | Joy, T, Desmaison, A, Ajanthan, T, Bunel, R, Salzmann, M, Kohli, P, Torr, PHS, Kumar, MP |
---|---|
Médium: | Journal article |
Vydáno: |
Society for Industrial and Applied Mathematics
2019
|
Podobné jednotky
-
Efficient linear programming for dense CRFs
Autor: Mudigonda, P, a další
Vydáno: (2017) -
Exact inference in multi-label CRFs with higher order cliques
Autor: Ramalingam, S, a další
Vydáno: (2008) -
Efficient continuous relaxations for dense CRF
Autor: Bunel, R, a další
Vydáno: (2016) -
Bottom-up Instance Segmentation using Deep Higher-Order CRFs
Autor: Arnab, A, a další
Vydáno: (2016) -
DenseCut: densely connected CRFs for realtime GrabCut
Autor: Cheng, MM, a další
Vydáno: (2015)