Deblurring Face Images with Exemplars

Jinshan Pan ☨ *      Zhe Hu§ *      Zhixun Su      Ming-Hsuan Yang§

§UC Merced       DLUT

*indicates equal contribution.

Proceedings of European Conference on Computer Vision (ECCV 2014)


The human face is one of the most interesting subjects in- volved in numerous applications. Signi cant progress has been made to- wards the image deblurring problem, however, existing generic deblur- ring methods are not able to achieve satisfying results on blurry face im- ages. The success of the state-of-the-art image deblurring methods stems mainly from implicit or explicit restoration of salient edges for kernel es- timation. When there is not much texture in the blurry image (e.g., face images), existing methods are less e ective as only few edges can be used for kernel estimation. Moreover, recent methods are usually jeopardized by selecting ambiguous edges, which are imaged from the same edge of the object after blur, for kernel estimation due to local edge selection strategies. In this paper, we address these problems of deblurring face images by exploiting facial structures. We propose a maximum a poste- riori (MAP) deblurring algorithm based on an exemplar dataset, with- out using the coarse-to- ne strategy or ad-hoc edge selections. Extensive evaluations against state-of-the-art methods demonstrate the e ective- ness of the proposed algorithm for deblurring face images. We also show the extendability of our method to other speci c deblurring tasks.

Paper and MATLAB code

The paper and MATLAB code can be found here. [PDF] [Poster] MATLAB code


title = {Deblurring Face Images with Exemplars },
author = {Jinshan Pan, Zhe Hu, Zhixun Su and Ming-Hsuan Yang},
journal = {European Conference on Computer Vision (ECCV 2014)},
year = {2014}