Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields.
Hartmut BauermeisterEmanuel LaudeThomas MöllenhoffMichael MöllerDaniel CremersPublished in: SIAM J. Imaging Sci. (2022)
Keyphrases
- markov random field
- convex relaxation
- graph cuts
- semidefinite
- random fields
- pairwise
- np hard
- maximum a posteriori
- belief propagation
- mrf model
- higher order
- parameter estimation
- image segmentation
- energy function
- potential functions
- energy minimization
- convex optimization
- image restoration
- wavelet transform
- message passing
- convex hull
- conditional random fields
- labeling problems
- low level vision
- globally optimal
- loopy belief propagation
- textured images
- lower bound
- linear programming
- potts model
- map estimation
- partition function
- min cut
- iterative conditional
- optimal solution
- image processing
- generative model
- markov networks
- map inference
- dynamic programming
- image reconstruction