Two-Phase Kernel Estimation for Robust Motion Deblurring

By Li Xu, Jiaya Jia. European Conference on Computer Vision, 2010

1,141 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/1a3df5c0a4471af6fe13433951758efc9d81846d

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

In Media Technology

Citations in the corpus

Learning to Super-Resolve Blurry Face and Text Images (2017, methodology): “Therefore, heuristic edge selection steps are often adopted [5, 44] for MAP estimation.”
Learning to Estimate and Remove Non-uniform Image Blur (2013, background): “Chakrabarti et al. [5] show interesting results for separating the blur and sharp regions in an image, but do not address deblurring itself, which is equally challenging.”
Blind deconvolution using a normalized sparsity measure (2011, methodology): “These include: marginalization over all possible images [4, 15, 17]; dynamic adaptation of the cost function [22]; alpha-matt extraction [10]; re-weighting of the image edges [3]; determination of the edge locations using shock filtering [18]; selective edge suppression [ 25 ].”
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].”
Blind Image Deblurring Using Dark Channel Prior (2016, methodology): “Cho and Lee [5] Xu and Jia [34] Krishnan et al. [17] Levin et al. [20] Xu et al. [36] Pan et al. [26] Ours Average PSNRs 23.80 26.21 20.86 24.90 26.21 28.80 27.94 (a) Input (b) Krishnan et al. [17] (c) Xu et al. [36] (d) Pan et al. [26] (e) Ours without D(I) (f) Ours with D(I) Figure 7.”
Learning a convolutional neural network for non-uniform motion blur removal (2015, methodology): “The third and fourth columns show the results of methods in [18, 26, 27, 29] using their source codes.”
Blind deconvolution in scientific imaging & computational photography (2011, methodology): “For comparison, we also show the result of Xu and Jia (2010) whose assumption of a invariant motion blur is again too restrictive to yield a good restoration result.”
Scale-Recurrent Network for Deep Image Deblurring (2018, background): “uniform/non-uniform/depth-aware), and utilized different natural image priors [1, 3, 6, 39, 14, 40, 26, 27] to regularize the solution space.”
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].”
$L_0$ -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].”
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.”
NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results (2017, methodology): “A blind deconvolution method [39] estimated the blur kernel on each train image and the average blur kernel was used for deblurring.”
A Neural Approach to Blind Motion Deblurring (2016, methodology): “, most of [3,4]’s failure cases correspond to images that lack well-separated strong edges.”
Learning to Deblur (2014, neutral): “to learn blind deconvolution.”
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].”
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.”
Text Detection and Recognition in Imagery: A Survey (2015, background): “Nevertheless, research [120], [131], [157] has shown that deconvolution has difficulties when processing text images, as they do not respect the special properties of text regions.”