Sorry, you need to enable JavaScript to visit this website.

BLIND IMAGE DEBLURRING BASED ON SPARSE REPRESENTATION AND STRUCTURAL SELF-SIMILARITY

Citation Author(s):
Jing Yu, Zhenchun Chang, Chuangbai Xiao,Weidong Sun
Submitted by:
Weidong Sun
Last updated:
8 March 2017 - 3:42am
Document Type:
Presentation Slides
Document Year:
2017
Event:
Presenters:
Jing YU
Paper Code:
IVMSP-L5.3
 

In this paper, we propose a blind motion deblurring method based on sparse representation and structural self-similarity from a single image. The priors for sparse representation and structural self-similarity are explicitly added into the recovery of the latent image by means of sparse and multi-scale non-local regularizations, and the down-sampled version of the observed blurry image is used as training samples in the dic-tionary learning for sparse representation so that the sparsity of the latent image over this dictionary can be guaranteed,which implicitly makes use of multi-scale similar structures. Experimental results on both simulated and real blurry images demonstrate that our method outperforms existing state-of-the-art blind deblurring methods.

up
0 users have voted: