Removing camera shake from a single photograph

By Rob Fergus, Barun Singh, Aaron Hertzmann, Sam T. Roweis, William T. Freeman. ACM Transactions on Graphics, 2006

837 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/464dbb687cc87ae784fdd0f7314bae4c0c9f57ec

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

Image and depth from a conventional camera with a coded aperture (2007, background): “Recent approaches assume the entire image is blurred uniformly [Fergus et al. 2006].”
A no-reference metric for evaluating the quality of motion deblurring (2013, methodology): “This is a problem that has been studied intensively over the past several years [Fergus et al. 2006; Yuan et al. 2007; Shan 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…”
Hierarchical Convolutional Deep Learning in Computer Vision (2013, background): “[35] introduced the idea of decomposing a blury image into a sharp image and blur kernel while imposing a prior on the gradients of the image.”
Deblurring Text Images via L0-Regularized Intensity and Gradient Prior (2014, methodology): “The state-of-the-art natural image deblurring methods [3, 18, 21, 20, 6] do not perform well in this image.”
Finding Tiny Faces in the Wild with Generative Adversarial Network (2018, methodology): “Most existing deblur methods heavily rely on prior models to solve the illposed problem, and a prior assumes that gradients of natural images have a heavy-tailed distribution [21, 7].”
Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms (2020, methodology): “Thus, image deblurring, a problem to restore a sharp image from a blurred one, has been extensively studied for decades [12, 38, 7, 45, 46, 33, 40, 6].”
Deep Image Deblurring: A Survey (2022, methodology): “Since this task is ill-posed, the solution is regularized using various additional constraints (Bahat et al. 2017; Cho and Lee 2009; Fergus et al. 2006; Xu and Jia 2010).”
Image deblurring using inertial measurement sensors (2010, methodology): “Prior knowledge about the image or kernel can disambiguate the potential solutions and make deblurring more tractable [Fergus et al. 2006].”
Learning to Super-Resolve Blurry Face and Text Images (2017, background): “This is in sharp contrast to empirical priors [9, 20, 23, 32, 33, 45] that are developed using the statistics of natural images.”
Face swapping: automatically replacing faces in photographs (2008, methodology): “While there exists extensive work on estimating blur in images [Kundur and Hatzinakos 1996; Fergus et al. 2006], we use a simple heuristic metric to measure the similarity of the degree of blur in two images.”
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.”
Image Deblurring via Extreme Channels Prior (2017, methodology): “Figure 5(a) indicates that our ECP based algorithm performs well against the state-of-the-art methods [2, 5, 19, 12, 16, 25] on this benchmark dataset [13] in terms of cumulative error ratio.”
Blind deconvolution in scientific imaging & computational photography (2011, background): “While Fergus et al. (2006) assume a uniform blur model and estimate an invariant PSF, Whyte et al. (2010) and our approach account for the spatial variation of the PSF.”