Fast motion deblurring

By Sunghyun Cho, Seungyong Lee. 2009

1,265 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

Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms (2020, methodology): “Following conventional blur kernel estimation methods [7, 46, 6], we estimate a blur kernel k by minimizing the following energy function:”
Edge-based blur kernel estimation using patch priors (2013, methodology): “Sparse deconvolution with identical parameters are applied to all compared methods except Cho and Lee [4].”
Non-uniform Deblurring for Shaken Images (2010, methodology): “(2006), and by Cho and Lee (2009) for the blind case, and Yuan et al.”
Learning to Estimate and Remove Non-uniform Image Blur (2013, methodology): “Our approach is related to previous methods, such as [5, 9, 25, 28], but with significant differences and advantages.”
Deblurring Text Images via L0-Regularized Intensity and Gradient Prior (2014, methodology): “As the solution directly from (5) based on intensity values is not accurate [3, 12], we estimate the blur kernel k in the gradient space by min k ‖∇x ∗ k −∇y‖22 + γ‖k‖22 (12) and the solution can be efficiently computed by FFTs [3].”
Learning to Super-Resolve Blurry Face and Text Images (2017, methodology): “Therefore, heuristic edge selection steps are often adopted [5, 44] for MAP estimation.”
From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur (2016, methodology): “nificant progress in image deblurring [9, 6, 42, 27, 28, 10], most work focuses on spatially-uniform blur.”
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].”
Total Variation Blind Deconvolution: The Devil Is in the Details (2014, methodology): “p(k) is the prior knowledge about the blur function, and that is typically a Gaussian distribution [23, 4], a sparsity-inducing distribution [7, 19] or a uniform distribution [13].”
Deep Image Deblurring: A Survey (2022, methodology): “Early blind deblurring methods focus on removing uniform blur (Cho and Lee 2009; Fergus et al. 2006; Michaeli and Irani 2014; Schuler et al. 2015; Xu and Jia 2010).”
Learning to Deblur (2014, neutral): “to learn blind deconvolution.”
Shrinkage Fields for Effective Image Restoration (2014, neutral): “42 Cho and Lee [4] 29.”
Two-Phase Kernel Estimation for Robust Motion Deblurring (2010, methodology): “To obtain sparse PSFs, previous methods [1, 3, 5, 21] apply hard or hysteresis thresholding to the kernel estimates.”
A no-reference metric for evaluating the quality of motion deblurring (2013, neutral): “CR Categories: I.3.0 [Computer Graphics]: General—; Keywords: image quality metric, no-reference, percetuallyvalidated, deblurring Links: DL PDF WEB ∗Part of this work was done when the first author was an intern at Adobe Research.”
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].”
Scale-Recurrent Network for Deep Image Deblurring (2018, methodology): “This framework follows the multi-scale mechanism in traditional methods, where the coarse-to-fine pipelines are common when handling large blur kernels [6].”