Header logo is

Multiframe Blind Deconvolution, Super-Resolution, and Saturation Correction via Incremental EM

2010

Conference Paper

ei


We formulate the multiframe blind deconvolution problem in an incremental expectation maximization (EM) framework. Beyond deconvolution, we show how to use the same framework to address: (i) super-resolution despite noise and unknown blurring; (ii) saturationcorrection of overexposed pixels that confound image restoration. The abundance of data allows us to address both of these without using explicit image or blur priors. The end result is a simple but effective algorithm with no hyperparameters. We apply this algorithm to real-world images from astronomy and to super resolution tasks: for both, our algorithm yields increased resolution and deconvolved images simultaneously.

Author(s): Harmeling, S. and Sra, S. and Hirsch, M. and Schölkopf, B.
Journal: Proceedings of the 17th International Conference on Image Processing (ICIP 2010)
Pages: 3313-3316
Year: 2010
Month: September
Day: 0
Publisher: IEEE

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

DOI: 10.1109/ICIP.2010.5651650
Event Name: 17th International Conference on Image Processing (ICIP 2010)
Event Place: Hong Kong, China

Address: Piscataway, NJ, USA
Digital: 0
Institution: Institute of Electrical and Electronics Engineers
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
Web

BibTex

@inproceedings{6673,
  title = {Multiframe Blind Deconvolution, Super-Resolution, and Saturation Correction via Incremental EM},
  author = {Harmeling, S. and Sra, S. and Hirsch, M. and Sch{\"o}lkopf, B.},
  journal = {Proceedings of the 17th International Conference on Image Processing (ICIP 2010)},
  pages = {3313-3316},
  publisher = {IEEE},
  organization = {Max-Planck-Gesellschaft},
  institution = {Institute of Electrical and Electronics Engineers},
  school = {Biologische Kybernetik},
  address = {Piscataway, NJ, USA},
  month = sep,
  year = {2010},
  doi = {10.1109/ICIP.2010.5651650},
  month_numeric = {9}
}