Learning iteration-wise generalized shrinkage-thresholding operators for blind deconvolution

Wangmeng Zuo, Dongwei Ren, Dapeng Zhang, Shuhang Gu, Lei Zhang

Research output: Journal article publicationJournal articleAcademic researchpeer-review

107 Citations (Scopus)


Salient edge selection and time-varying regularization are two crucial techniques to guarantee the success of maximum a posteriori (MAP)-based blind deconvolution. However, the existing approaches usually rely on carefully designed regularizers and handcrafted parameter tuning to obtain satisfactory estimation of the blur kernel. Many regularizers exhibit the structure-preserving smoothing capability, but fail to enhance salient edges. In this paper, under the MAP framework, we propose the iteration-wise ell -{p} -norm regularizers together with data-driven strategy to address these issues. First, we extend the generalized shrinkage-thresholding (GST) operator for ell -{p} -norm minimization with negative p value, which can sharpen salient edges while suppressing trivial details. Then, the iteration-wise GST parameters are specified to allow dynamical salient edge selection and time-varying regularization. Finally, instead of handcrafted tuning, a principled discriminative learning approach is proposed to learn the iterationwise GST operators from the training dataset. Furthermore, the multi-scale scheme is developed to improve the efficiency of the algorithm. Experimental results show that, negative p value is more effective in estimating the coarse shape of blur kernel at the early stage, and the learned GST operators can be well generalized to other dataset and real world blurry images. Compared with the state-of-the-art methods, our method achieves better deblurring results in terms of both quantitative metrics and visual quality, and it is much faster than the state-of-the-art patch-based blind deconvolution method.
Original languageEnglish
Article number7412703
Pages (from-to)1751-1764
Number of pages14
JournalIEEE Transactions on Image Processing
Issue number4
Publication statusPublished - 1 Apr 2016


  • blind deconvolution
  • discriminative learning
  • hyper-Laplacian
  • image deblurring
  • kernel estimation

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Learning iteration-wise generalized shrinkage-thresholding operators for blind deconvolution'. Together they form a unique fingerprint.

Cite this