Blind deconvolution using a normalized sparsity measure

By Dilip Krishnan, Terence Tay, Rob Fergus. 2011

1,194 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Deep multi-scale video prediction beyond mean square error (2015, methodology): “We tried to apply the blind deconvolution method of Krishnan et al. (2011) to improve Ranzato et al. and our different results.”
Blind Deblurring Using Internal Patch Recurrence (2014, methodology): “This resulted in a significant improvement in performance over all the previous blind deblurring methods [13,10,1,19,2].”
DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures (2019, methodology): “Given its success as a sparsity measure in NMF, the Hoyer measure has also been applied as a sparsity-inducing regularizer in optimization problems such as blind deconvolution [21] and image deblurring [20].”
Image Deblurring via Extreme Channels Prior (2017, methodology): “In [12], a minimization scheme is proposed by utilizing L1/L2 regularizer for edge selection.”
Deep Video Deblurring for Hand-Held Cameras (2017, methodology): “In recent years many successful methods have been introduced [3, 8, 22, 32, 39, 42, 51, 52], see [47] for a recent survey.”
A Neural Approach to Blind Motion Deblurring (2016, methodology): “[1], the last decade has seen considerable progress [2,3,4,5,6,7,8] in the development of effective blind motion deblurring methods that seek to estimate camera motion in terms of the induced blur kernel, and then reverse its effect.”
Unsupervised Domain-Specific Deblurring via Disentangled Representations (2019, methodology): “Conventional methods [28, 29, 27, 41, 14] still tend to under-deblur or over-deblur images, especially on local regions such as eyes and mouths.”
Blind Image Deblurring Using Dark Channel Prior (2016, methodology): “Efficient methods based on MAP formulations have been developed with different likelihood functions and image priors [1, 17, 21, 27, 31, 36, 37].”
Segmentation-Free Dynamic Scene Deblurring (2014, background): “To address this problem, many researchers studied the prior of latent image [14, 15, 18].”
Artificial intelligence in the creative industries: a review (2020, methodology): “More sophisticated algorithms such as blind deconvolution (BD), attempt to restore the image and the PSF simultaneously [118, 119].”
From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur (2016, background): “Numerous image priors or regularizers have been studied to overcome the ill-posed nature of the problem, such as the total variational regularizer [5, 29], Gaussian scale mixture priors [9] and 1/ 2-norms [19], 0-norms [44, 27], and dark channel [28] based regularizers.”
Hand-Held Video Deblurring Via Efficient Fourier Aggregation (2015, methodology): “The single image deconvolution method in [17] manages to get sharper images than the input ones, but their quality is significantly lower to the ones produced by our method.”
Edge-based blur kernel estimation using patch priors (2013, methodology): “However, even with some parameter tuning, we are unable to obtain good results with the online MATLAB code packages from [14, 11, 5] on this test dataset.”
Neural Blind Deconvolution Using Deep Priors (2019, methodology): “(3), projected alternating minimization is generally adopted, but several optimization details, e.g ., delayed normalization [32] and multi-scale implementation [15], are also crucial to the success of blind deconvolution.”
Deblurring Text Images via L0-Regularized Intensity and Gradient Prior (2014, methodology): “For each sharp image, we compute the average PSNR on the blurred images from different kernels and compare among different methods [16, 3, 18, 10, 12, 20, 21] in Figure 8.”
$L_0$ -Regularized Intensity and Gradient Prior for Deblurring Text Images and Beyond (2017, methodology): “The success of recent deblurring methods hinges on latent image estimation explicitly [3], [4] or implicitly [1], [2], [6].”
Blind Deconvolution Using Convex Programming (2012, background): “Since the advent of compressed sensing and our understanding of the fact that the 1 penalty favors sparsity, several works; see, for example, [12], [13], imposed the 1 penalty on the vectors being convolved to separate the unknown sparse vectors.”