id: 05259091
dt: a
an: 05259091
au: Corso, Jason J.; Tu, Zhuowen; Yuille, Alan
ti: MRF labeling with a graph-shifts algorithm.
so: Brimkov, Valentin E. (ed.) et al., Combinatorial image analysis. 12th
    international workshop, IWCIA 2008, Buffalo, NY, USA, April 7‒9,
    2008. Proceedings. Berlin: Springer (ISBN 978-3-540-78274-2/pbk).
    Lecture Notes in Computer Science 4958, 172-184 (2008).
py: 2008
pu: Berlin: Springer
la: EN
cc: 
ut: 
ci: 
li: doi:10.1007/978-3-540-78275-9_15
ab: Summary: We present an adaptation of the recently proposed graph-shifts
    algorithm for labeling MRF problems from low-level vision. Graph-shifts
    is an energy minimization algorithm that does labeling by dynamically
    manipulating, or shifting, the parent-child relationships in a
    hierarchical decomposition of the image. Graph-shifts was originally
    proposed for labeling using relatively small label sets (e.g., 9) for
    problems in high-level vision. In the low-level vision problems we
    consider, there are much larger label sets (e.g., 256). However, the
    original graph-shifts algorithm does not scale well with the number of
    labels; for example, the memory requirement is quadratic in the number
    of labels. We propose four improvements to the graph-shifts
    representation and algorithm that make it suitable for doing labeling
    on these large label sets. We implement and test the algorithm on two
    low-level vision problems: image restoration and stereo. Our results
    demonstrate the potential for such a hierarchical energy minimization
    algorithm on low-level vision problems with large label sets.
rv: