Institute Homepage DE Sign In

Back

Empirical Inference Conference Paper 2011

Fast removal of non-uniform camera shake

Thumb ticker sm stefan harmeling
Empirical Inference
Stefan Harmeling
Thumb ticker sm me
Empirical Inference
Michael Hirsch
Affiliated Researcher
Thumb ticker sm l1170153
Empirical Inference
Bernhard Schölkopf
  • Director

Camera shake leads to non-uniform image blurs. State-of-the-art methods for removing camera shake model the blur as a linear combination of homographically transformed versions of the true image. While this is conceptually interesting, the resulting algorithms are computationally demanding. In this paper we develop a forward model based on the efficient filter flow framework, incorporating the particularities of camera shake, and show how an efficient algorithm for blur removal can be obtained. Comprehensive comparisons on a number of real-world blurry images show that our approach is not only substantially faster, but it also leads to better deblurring results.

Author(s): Hirsch, M. and Schuler, CJ. and Harmeling, S. and Schölkopf, B.
Pages: 463-470
Year: 2011
Month: November
Day: 0
Editors: DN Metaxas and L Quan and A Sanfeliu and LJ Van Gool
Publisher: IEEE
Bibtex Type: Conference Paper (inproceedings)
Address: Piscataway, NJ, USA
DOI: 10.1109/ICCV.2011.6126276
Event Name: 13th IEEE International Conference on Computer Vision (ICCV 2011)
Event Place: Barcelona, Spain
Digital: 0
Electronic Archiving: grant_archive
ISBN: 978-1-4577-1101-5
Links:

BibTex 

@inproceedings{HirschSHS2011,
  title = {Fast removal of non-uniform camera shake},
  abstract = {Camera shake leads to non-uniform image blurs. State-of-the-art methods for removing camera shake model the blur as a linear combination of homographically transformed versions of the true image. While this is conceptually interesting, the resulting algorithms are computationally demanding. In this paper we develop a forward model based on the efficient filter flow framework, incorporating the particularities of camera shake, and show how an efficient algorithm for blur removal can be obtained. Comprehensive comparisons on a number of real-world blurry images show that our approach is not only substantially faster, but it also leads to better deblurring results.},
  pages = {463-470 },
  editors = {DN Metaxas and L Quan and A Sanfeliu and LJ Van Gool},
  publisher = {IEEE},
  address = {Piscataway, NJ, USA},
  month = nov,
  year = {2011},
  slug = {hirschshs2011},
  author = {Hirsch, M. and Schuler, CJ. and Harmeling, S. and Sch{\"o}lkopf, B.},
  month_numeric = {11}
}