Deblurring by example using dense correspondence

Yoav Hacohen, Eli Shechtman, Dani Lischinski

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


This paper presents a new method for deblurring photos using a sharp reference example that contains some shared content with the blurry photo. Most previous deblurring methods that exploit information from other photos require an accurately registered photo of the same static scene. In contrast, our method aims to exploit reference images where the shared content may have undergone substantial photometric and non-rigid geometric transformations, as these are the kind of reference images most likely to be found in personal photo albums. Our approach builds upon a recent method for example-based deblurring using non-rigid dense correspondence (NRDC) [HaCohen et al. 2011] and extends it in two ways. First, we suggest exploiting information from the reference image not only for blur kernel estimation, but also as a powerful local prior for the non-blind deconvolution step. Second, we introduce a simple yet robust technique for spatially varying blur estimation, rather than assuming spatially uniform blur. Unlike the above previous method, which has proven successful only with simple deblurring scenarios, we demonstrate that our method succeeds on a variety of real-world examples. We provide quantitative and qualitative evaluation of our method and show that it outperforms the state-of-the-art.

Original languageAmerican English
Title of host publicationProceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages8
ISBN (Print)9781479928392
StatePublished - 2013
Event2013 14th IEEE International Conference on Computer Vision, ICCV 2013 - Sydney, NSW, Australia
Duration: 1 Dec 20138 Dec 2013

Publication series

NameProceedings of the IEEE International Conference on Computer Vision


Conference2013 14th IEEE International Conference on Computer Vision, ICCV 2013
CitySydney, NSW


  • deblurring
  • image restoration

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Deblurring by example using dense correspondence'. Together they form a unique fingerprint.

Cite this