Unnatural L0 Sparse Representation for Natural Image Deblurring

By Li Xu, Shicheng Zheng, Jiaya Jia. 2013

1,151 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Neural Blind Deconvolution Using Deep Priors (2019, methodology): “After blur kernel estimation, non-blind deconvolution is required to recover the latent clean image with ﬁne texture details [15, 22, 27, 29, 41, 49].”
Deblurring via Stochastic Refinement (2021, methodology): “Traditional deblur-ring methods formulate the problem as one of blind deconvolution [9,10,16,19,29,37,39,60,74,78].”
$L_0$ -Regularized Intensity and Gradient Prior for Deblurring Text Images and Beyond (2017, methodology): “tional Bayesian inference is computationally expensive, methods based on MAP formulations have been developed with different likelihood functions and image priors [2], [6], [7], [10], [14], [15], [16].”
Scale-Recurrent Network for Deep Image Deblurring (2018, background): “They include total variation (TV) [3], sparse image priors [22], heavy-tailed gradient prior [30], hyper-Laplacian prior [21], l0-norm gradient prior [40], etc.”
Human-Aware Motion Deblurring (2019, background): “Blind-Image Deblurring: For the uniform blur problem, conventional methods typically resort to natural image priors to estimate latent images [8, 20, 34, 26, 52, 5, 39, 51, 33].”
A Comparative Study for Single Image Blind Deblurring (2016, methodology): “The progress in this field can be attributed to the advancement of efficient inference algorithms [2, 5, 17, 35, 44], various natural image priors [15, 21, 29, 38, 45], and more general motion blur models [8, 9, 11, 43].”
From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur (2016, methodology): “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.”
Single Image Layer Separation Using Relative Smoothness (2014, methodology): “The function ρ is similar to the sparse penalty used in [25].”
Learning to Super-Resolve Blurry Face and Text Images (2017, methodology): “Methods [45]+[43] [45]+[8] [45]+[18] [32]+[43] [32]+[8] [32]+[18] [33]+[43] [33]+[8] [33]+[18]”
Uformer: A General U-Shaped Transformer for Image Restoration (2021, neutral): “[64], DeblurGAN-v2 [28], DB-GAN [77], SPAIR [44], Zhang et al .”
Total Variation Blind Deconvolution: The Devil Is in the Details (2014, methodology): “[24] have proposed an approximation of the L0-norm as a sparsity prior.”
Segmentation-Free Dynamic Scene Deblurring (2014, methodology): “8(c), [26] fails in deblurring as depth discontinuity exist in the blurry image.”
Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks (2018, methodology): “(a) blurry image (b) Whyte [36] (c) Xu [41] (d) Sun [33] (e) Pan [24] psnr/ssim 27.”
Deep Video Deblurring for Hand-Held Cameras (2017, methodology): “[52], WFA [6], and Photoshop CC Shake Reduction.”
Deblurring by Realistic Blurring (2020, background): “Often, special characteristics of the blur kernel are assumed, and natural image priors are exploited in the deblurring process [5, 7, 22, 40, 41].”
Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration (2019, background): “Early works [2, 7, 45, 46] attempt to simultaneously estimate both blur kernels and sharp images.”