Richardson-Lucy Deblurring for Scenes under a Projective Motion Path

By Yu-Wing Tai, Ping Tan, Michael S. Brown. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011

331 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/44d1b2e2431b24cb6f3dd848fa5feaf55f21224f

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

Non-uniform Deblurring for Shaken Images (2010, methodology): “This algorithm can be applied to general linear systems as well as to convolutional blurs, using the notation of Eqn. (8) for a known blur [ 25 ].”
Learning a convolutional neural network for non-uniform motion blur removal (2015, background): “In [7, 8, 25, 26, 31], nonuniform motion blur is modeled as a global camera motion, which basically estimates an uniform kernel in the camera motion space.”
Blind Image Deblurring Using Dark Channel Prior (2016, background): “Based on the geometric model of camera motion [30, 33], the non-uniform blur model can be expressed as:”
Unnatural L0 Sparse Representation for Natural Image Deblurring (2013, methodology): “[22] solved non-blind deconvolution with a general projective motion model.”
Face Recognition Across Non-Uniform Motion Blur, Illumination, and Pose (2015, methodology): “While techniques have been proposed that address the restoration of non-uniform blur by local spaceinvariance approximation [5], [6], [7], recent methods for image restoration have modeled the motion-blurred image as an average of projectively transformed images [8], [9], [10], [11], [12].”
Learning to Estimate and Remove Non-uniform Image Blur (2013, background): “We aim to overcome these limitations, and cast the estimation of the global (non-uniform) image blur as a multilabel energy minimization problem (Section 2).”
Fast removal of non-uniform camera shake (2011, background): “This motivated work on non-uniform blur models which we already discussed in the introduction [22, 24, 5, 6].”
From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur (2016, background): “In [35], a projective motion path model formulates a blurry image as the weighted sum of a set of transformed sharp images, an approach which is which is simplified and extended in [40] and [45].”
Blind deconvolution in scientific imaging & computational photography (2011, methodology): “which is the forward model of Tai et al. (2009). Derivation of time-agnostic model.”
$L_0$ -Regularized Intensity and Gradient Prior for Deblurring Text Images and Beyond (2017, background): “Based on the geometric model of camera motion [23], [24], we represent a blurred image as the weighted sum of a clear image under transformations,”