Fast Inverse Compositional Image Alignment with Missing Data and Re-weighting

Vincent Lui, Dinesh Gamage and Tom Drummond

Abstract

This paper proposes a novel method of performing inverse compositional image alignment which elegantly deals with missing data and re-weighting, and does not require the Jacobians and Hessian to be re-computed at every iteration. We show how missing data and re-weighting can be handled through preconditioning. We propose a few preconditioning techniques and analyse how each technique models the effects of missing data and re-weighting for inverse composition. We show through extensive experiments on different applications that our method improves the convergence rate of the conventional re-weighted inverse compositional method while remaining robust to outliers. We also show that the update parameters are usually underestimated and how this can be used to further speed up convergence of image alignment methods.

Session

Poster 1

Files

Extended Abstract (PDF, 1750K)
Paper (PDF, 3M)
Supplemental Materials (ZIP, 6M)

DOI

10.5244/C.29.54
https://dx.doi.org/10.5244/C.29.54

Citation

Bibtex

@inproceedings{BMVC2015_54,
	title={Fast Inverse Compositional Image Alignment with Missing Data and Re-weighting},
	author={Vincent Lui and Dinesh Gamage and Tom Drummond},
	year={2015},
	month={September},
	pages={54.1-54.12},
	articleno={54},
	numpages={12},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.54},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.54}
}