Non-uniform Deblurring for Shaken Images

By Oliver Whyte, Josef Sivic, Andrew Zisserman, Jean Ponce. 2010

785 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Deblurring by Realistic Blurring (2020, background): “The blurring process can be mathematically formulated as [8, 38], where I B and I S are blurry and sharp images, respectively.”
Unnatural L0 Sparse Representation for Natural Image Deblurring (2013, methodology): “[24] presented a non-uniform method using variational Bayesian.”
Deep Image Deblurring: A Survey (2022, neutral): “Numerous approaches have been developed to address non-uniform blur by modeling the blur kernel from 3D camera motion (Hirsch et al. 2011; Whyte et al. 2012).”
Blind deconvolution using a normalized sparsity measure (2011, methodology): “In this section, we present results of our algorithm and compare it to the algorithms of [4],[22] and [24].”
Learning a convolutional neural network for non-uniform motion blur removal (2015, methodology): “Methods in [7, 8, 26, 31] work on non-uniform blur caused by camera rotations, in-plane translations or forward out-of-plane translations.”
Blind deconvolution in scientific imaging & computational photography (2011, methodology): “7: The curve shows the relative error of a homographically transformed image (1600 × 1200 pixels) using the forward model of Whyte et al. (2010) and our fast forward model which approximates the homography by the camera motion constrained EFF framework.”
Efficient marginal likelihood optimization in blind deconvolution (2011, methodology): “In general, despite the superior robustness of the MAPk estimation principle, only a few recent approaches to blind deconvolution have taken this direction [5, 22, 18], whereas many research attempts are devoted to the MAPx,k approach [20, 2, 4, 7, 6, 21, 3, 23].”
DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks (2017, methodology): “[40] are non-CNN blind deblurring methods, whereas Sun et al.”
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).”
Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms (2020, background): “To deal with more realistic blur, several approaches with extended blur models have been proposed, but their performance is still limited due to the inherent ill-posedness of the inverse problem [18, 44, 8, 14, 17, 19].”
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better (2019, neutral): “[49], Xu et al .”
A no-reference metric for evaluating the quality of motion deblurring (2013, background): “…et al. 2008; Cho and Lee 2009; Krishnan and Fergus 2009; ACM Transactions on Graphics, Vol. 32, No. 6, Article 175, Publication Date: November 2013 Whyte et al. 2010; Xu and Jia 2010; Cho et al. 2011; Levin et al. 2011; Zoran and Weiss 2011; Goldstein and Fattal 2012], but even state-of-the-art…”
Segmentation-Free Dynamic Scene Deblurring (2014, methodology): “Our method does not require any complex model to handle specific types of motion blur [10, 23, 27] and does not depend on the accurate motion segmentation.”