Deformed Lattice Discovery Via Efficient Mean-Shift Belief Propagation

@inproceedings{Park2008DeformedLD,
  title={Deformed Lattice Discovery Via Efficient Mean-Shift Belief Propagation},
  author={Minwoo Park and Robert T. Collins and Yanxi Liu},
  booktitle={ECCV},
  year={2008}
}
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… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 20 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 17 references

Shape matching and object recognition using shape contexts

2010 3rd International Conference on Computer Science and Information Technology • 2010
View 1 Excerpt

Efficient mean shift belief propagation for vision tracking

2008 IEEE Conference on Computer Vision and Pattern Recognition • 2008
View 12 Excerpts

A Lattice-Based MRF Model for Dynamic Near-Regular Texture Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2007
View 10 Excerpts

Phase Based Modelling of Dynamic Textures

2007 IEEE 11th International Conference on Computer Vision • 2007
View 1 Excerpt

The Promise and Perils of Near-Regular Texture

International Journal of Computer Vision • 2004
View 1 Excerpt

A computational model for periodic pattern perception based on frieze and wallpaper groups

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2003
View 2 Excerpts

Similar Papers

Loading similar papers…