Results 1 -
1 of
1
Globally optimal solutions for energy minimization in stereo vision using reweighted belief propagation
- In ICCV
, 2005
"... Abstract A wide range of low level vision problems have been for-mulated in terms of finding the most probable assignment of a Markov Random Field (or equivalently the lowest en-ergy configuration). Perhaps the most successful example is stereo vision. For the stereo problem, it has been shown thatf ..."
Abstract
-
Cited by 21 (5 self)
- Add to MetaCart
Abstract A wide range of low level vision problems have been for-mulated in terms of finding the most probable assignment of a Markov Random Field (or equivalently the lowest en-ergy configuration). Perhaps the most successful example is stereo vision. For the stereo problem, it has been shown thatfinding the global optimum is NP hard but good results have been obtained using a number of approximate optimizationalgorithms.

