Please use this identifier to cite or link to this item:
Title: Discriminative learning of iteration-wise priors for blind deconvolution
Authors: Zuo, W
Ren, D
Gu, S
Lin, L
Zhang, L 
Keywords: Realistic images
Edge detection
Estimation theory
Gradient methods
Image restoration
Learning (artificial intelligence)
Issue Date: 2015
Publisher: Institute of Electrical and Electronics Engineers
Source: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, June 7-12, 2015, p. 3232-3240 How to cite?
Abstract: The maximum a posterior (MAP)-based blind deconvolution framework generally involves two stages: blur kernel estimation and non-blind restoration. For blur kernel estimation, sharp edge prediction and carefully designed image priors are vital to the success of MAP. In this paper, we propose a blind deconvolution framework together with iteration specific priors for better blur kernel estimation. The family of hyper-Laplacian (Pr(d) ∝ e-∥d∥pp/λ) is adopted for modeling iteration-wise priors of image gra- dients, where each iteration has its own model parameters {λ(t), p(t)}. To avoid heavy parameter tuning, all iteration-wise model parameters can be learned using our principled discriminative learning model from a training set, and can be directly applied to other dataset and real blurry images. Interestingly, with the generalized shrinkage / thresholding operator, negative p value (p <;0) is allowable and we find that it contributes more in estimating the coarse shape of blur kernel. Experimental results on synthetic and real world images demonstrate that our method achieves better deblurring results than the existing gradient prior-based methods. Compared with the state-of-the-art patch prior-based method, our method is competitive in restoration results but is much more efficient.
ISBN: 978-1-4673-6964-0 (electronic)
978-1-4673-6963-3 (USB)
978-1-4673-6965-7 (print on demand(PoD))
ISSN: 1063-6919
EISSN: 1063-6919
DOI: 10.1109/CVPR.2015.7298943
Appears in Collections:Conference Paper

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of May 9, 2020

Page view(s)

Last Week
Last month
Citations as of May 6, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.