Sciweavers

Share
ECCV
2008
Springer

Deformed Lattice Discovery Via Efficient Mean-Shift Belief Propagation

9 years 9 months ago
Deformed Lattice Discovery Via Efficient Mean-Shift Belief Propagation
We introduce a novel framework for automatic detection of repeated patterns in real images. The novelty of our work is to formulate the extraction of an underlying deformed lattice as a spatial, multi-target tracking problem using a new and efficient Mean-Shift Belief Propagation (MSBP) method. Compared to existing work, our approach has multiple advantages, including: 1) incorporating higher order constraints early-on to propose highly plausible lattice points; 2) growing a lattice in multiple directions simultaneously instead of one at a time sequentially; and 3) achieving more efficient and more accurate performance than state-ofthe-art algorithms. These advantages are demonstrated by quantitative experimental results on a diverse set of real world photos.
Minwoo Park, Robert T. Collins, Yanxi Liu
Added 15 Oct 2009
Updated 15 Oct 2009
Type Conference
Year 2008
Where ECCV
Authors Minwoo Park, Robert T. Collins, Yanxi Liu
Comments (0)
books