Header logo is ei

Recording and Playback of Camera Shake: Benchmarking Blind Deconvolution with a Real-World Database

2012

Conference Paper

ei


Motion blur due to camera shake is one of the predominant sources of degradation in handheld photography. Single image blind deconvolution (BD) or motion deblurring aims at restoring a sharp latent image from the blurred recorded picture without knowing the camera motion that took place during the exposure. BD is a long-standing problem, but has attracted much attention recently, cumulating in several algorithms able to restore photos degraded by real camera motion in high quality. In this paper, we present a benchmark dataset for motion deblurring that allows quantitative performance evaluation and comparison of recent approaches featuring non-uniform blur models. To this end, we record and analyse real camera motion, which is played back on a robot platform such that we can record a sequence of sharp images sampling the six dimensional camera motion trajectory. The goal of deblurring is to recover one of these sharp images, and our dataset contains all information to assess how closely various algorithms approximate that goal. In a comprehensive comparison, we evaluate state-of-the-art single image BD algorithms incorporating uniform and non-uniform blur models.

Author(s): Köhler, R. and Hirsch, M. and Mohler, B. and Schölkopf, B. and Harmeling, S.
Book Title: Computer Vision - ECCV 2012, LNCS Vol. 7578
Pages: 27-40
Year: 2012
Day: 0
Editors: A. Fitzgibbon, S. Lazebnik, P. Perona, Y. Sato, and C. Schmid
Publisher: Springer

Department(s): Empirical Inference
Research Project(s): Computational Imaging
Bibtex Type: Conference Paper (inproceedings)

DOI: 10.1007/978-3-642-33786-4_3
Event Name: 12th European Conference on Computer Vision, ECCV 2012
Event Place: Florence, Italy

Address: Berlin, Germany
ISBN: 978-3-642-33785-7

Links: PDF

BibTex

@inproceedings{KohlerHMSHC2012,
  title = {Recording and Playback of Camera Shake: Benchmarking Blind Deconvolution with a Real-World Database},
  author = {K{\"o}hler, R. and Hirsch, M. and Mohler, B. and Sch{\"o}lkopf, B. and Harmeling, S.},
  booktitle = {Computer Vision - ECCV 2012, LNCS Vol. 7578},
  pages = {27-40},
  editors = {A. Fitzgibbon, S. Lazebnik, P. Perona, Y. Sato, and C. Schmid},
  publisher = {Springer},
  address = {Berlin, Germany},
  year = {2012}
}