Single Image Motion Deblurring Using Transparency

By Jiaya Jia. 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007

383 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/7910d3924ead1b5bd66da13e4e821536d38b6cca

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

Fast motion deblurring (2009, methodology): “Recently, several methods were proposed to handle a more general motion blur given a single image [Fergus et al. 2006; Jia 2007; Shan et al. 2008].”
Two-Phase Kernel Estimation for Robust Motion Deblurring (2010, neutral): “Notable progress has been made lately [1–6].”
PSF estimation using sharp edge prediction (2008, background): “For more complex blurs, such as motion blur, many recent single-image estimation techniques model blurs as a collections of 1D or 2D box blurs and use segmentation techniques to handle multiple motions [7, 4, 2].”
Understanding and evaluating blind deconvolution algorithms (2009, background): “Algorithms like [7, 6] explicitly detect edges in the image (either manually or automatically), and seek a kernel which transfers these edges into binary ones.”
Analyzing spatially-varying blur (2010, methodology): “As an alternative to using two or more images, one can use a single image but assume that a solution to the foreground/background matting problem is given as input [7, 8, 13].”
Richardson-Lucy Deblurring for Scenes under a Projective Motion Path (2011, positive): “Jia [13] demonstrated how to use an object’s alpha matte to better compute the PSF.”
Blind motion deblurring from a single image using sparse approximation (2009, background): “[15], Levin [18], Joshi [17]) or manually selecting blurred edges to obtain the local blur kernel (Jia [16]).”
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].”
Artificial intelligence in the creative industries: a review (2020, methodology): “nhancement [79] [80] Histogram [81]. Colorization [82{84] [85{88] Super-resolution [89{103] [104,105] [90,103] Content Deblurring [106{112] [113] [110], Statistic model [114] Enhancement [115{117] BD [118,119] and Post Denoising [120{134] [128,135] [136,137] Filtering [138{142] Production Dehazing [”
Efficient marginal likelihood optimization in blind deconvolution (2011, methodology): “The common approach is to utilize prior knowledge about the statistics of natural images, such as their sparse derivative distribution [5, 11, 20, 2, 4, 7, 6, 21, 3, 23].”
Unnatural L0 Sparse Representation for Natural Image Deblurring (2013, methodology): “[11, 13, 19, 3, 25, 9, 23], which are referred to as semi-blind schemes, and those [20, 16] implicitly incorporating special regularization to remove detrimental structures in early stages and gradually enrich image details in iterations.”
Single Image Deblurring Using Motion Density Functions (2010, methodology): “[13] use transparency maps to get cues for object motion to recover blur kernels by performing blind-deconvolution on the alpha matte, with a prior on the alpha-matte.”
$L_0$ -Regularized Intensity and Gradient Prior for Deblurring Text Images and Beyond (2017, background): “In [40], [41], Jia shows that the matte map of an”