Blind image deconvolution

By Patrizio Campisi. 2007

630 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/8f83317989bc025d2f70f7f69118a3e52f618eba

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

PSF estimation using sharp edge prediction (2008, background): “Early work in this area significantly constrained the form of the kernel [6], while more recently, researchers have put constraints on the underlying sharp image [3].”
Removing Camera Shake from a Single Photograph (2009, background): “For a survey on the extensive literature in this area, see [Kundur and Hatzinakos 1996].”
Blind Motion Deblurring Using Image Statistics (2006, background): “A summary and analysis of many deconvolution algorithms can be found in [14].”
A Convex Formulation for Hyperspectral Image Superresolution via Subspace-Based Regularization (2014, methodology): “With this representation, we model the hyperspectral measurements as where matrix B ∈ R n m × n m is a spatial blurring matrix representing the hyperspectral sensor’s point spread function in the spatial resolution of Z ; it is assumed to be band-independent and to be under circular boundary…”
Learning Deep CNN Denoiser Prior for Image Restoration (2017, background): “Image restoration (IR) has been a long-standing problem for its highly practical value in various low-level vision applications [1, 9, 47].”
Understanding Blind Deconvolution Algorithms (2011, background): “B LIND deconvolution is the problem of recovering a sharp version of an input blurry image when the blur kernel is unknown [16].”
Modern regularization methods for inverse problems (2018, methodology): “nvolution Following up on Example 6.1, an obvious nonconvex extension of the problem of deconvolution is blind deconvolution, where the convolution kernel that degrades the image is also unknown (cf. [252, 118, 93]). We basically follow the setup of [27, Section 6.2], where we assume F(K(u;h);f) = 1”
Understanding and evaluating blind deconvolution algorithms (2009, background): “Blind deconvolution is the subject of numerous papers in the signal and image processing literature, to name a few consider [1, 8, 22, 15, 17] and the survey in [10].”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 on Bayesian Adaptive Video Super Resolution (background): “Therefore, a practical super resolution system should simultaneously estimate optical flow [12], noise level [23] and blur kernel [16] in addition to reconstructing the highres image.”
Digital image forensics via intrinsic fingerprints (2008, methodology): “The frequency response of the estimated manipulation filter in the th iteration is obtained by using the technique described in [35] with”
Fast removal of non-uniform camera shake (2011, unknown): “See Kundur and Hatzinakos [10] for an overview of related methods.”
Moments and Moment Invariants in Pattern Recognition (2009, background): “For instance, in the case of image blurring, “normalization” means in fact blind deconvolution [5] and in the case of spatial image deformation, “normalization” requires registration of the image to be performed to some reference frame [6].”
Image deblurring with blurred/noisy image pairs (2007, background): “A comprehensive literature review on image deblurring can be found in [Kundur and Hatzinakos 1996].”
Total Variation Blind Deconvolution: The Devil Is in the Details (2014, background): “Yet, despite over three decades of research in the field (see [11] and references therein), the design of a principled, stable and robust algorithm that can handle real images remains a challenge.”