Deformed Lattice Discovery via Efficient Mean-Shift Belief Propagation
Abstract
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-of-the-art algorithms. These advantages are demonstrated by quantitative experimental results on a diverse set of real world photos.
Cite
Text
Park et al. "Deformed Lattice Discovery via Efficient Mean-Shift Belief Propagation." European Conference on Computer Vision, 2008. doi:10.1007/978-3-540-88688-4_35Markdown
[Park et al. "Deformed Lattice Discovery via Efficient Mean-Shift Belief Propagation." European Conference on Computer Vision, 2008.](https://mlanthology.org/eccv/2008/park2008eccv-deformed/) doi:10.1007/978-3-540-88688-4_35BibTeX
@inproceedings{park2008eccv-deformed,
title = {{Deformed Lattice Discovery via Efficient Mean-Shift Belief Propagation}},
author = {Park, Minwoo and Collins, Robert T. and Liu, Yanxi},
booktitle = {European Conference on Computer Vision},
year = {2008},
pages = {474-485},
doi = {10.1007/978-3-540-88688-4_35},
url = {https://mlanthology.org/eccv/2008/park2008eccv-deformed/}
}