Filters








886 Hits in 4.0 sec

Blind Deconvolution via Lower-Bounded Logarithmic Image Priors [chapter]

Daniele Perrone, Remo Diethelm, Paolo Favaro
2015 Lecture Notes in Computer Science  
In this work we devise two novel algorithms for blind deconvolution based on a family of logarithmic image priors.  ...  prior based on a lowerbounded logarithm of the norm of the image gradients.  ...  Conclusions In this paper we presented solutions to blind deconvolution based on a logarithmic image prior.  ... 
doi:10.1007/978-3-319-14612-6_9 fatcat:env5psd3sbgpdgepccltmtzlbe

Blind Deconvolution via Lower-Bounded Logarithmic Image Priors

Paolo Favaro, Remo Diethelm, Daniele Perrone
2015
In this work we devise two novel algorithms for blind deconvolution based on a family of logarithmic image priors.  ...  prior based on a lowerbounded logarithm of the norm of the image gradients.  ...  Conclusions In this paper we presented solutions to blind deconvolution based on a logarithmic image prior.  ... 
doi:10.7892/boris.67438 fatcat:bnbv7umtmbfp7jzmxnzlgem27m

A Logarithmic Image Prior for Blind Deconvolution

Daniele Perrone, Paolo Favaro
2015 International Journal of Computer Vision  
In this work we also study a logarithmic image prior. We show empirically how well the prior suits the blind deconvolution problem.  ...  Blind Deconvolution consists in the estimation of a sharp image and a blur kernel from an observed blurry image.  ...  via the logarithmic prior (for a given λ).  ... 
doi:10.1007/s11263-015-0857-2 fatcat:6vi2nzjrw5cz5g4kxmgziksbx4

Deep Mean-Shift Priors for Image Restoration [article]

Siavash Arjomand Bigdeli, Meiguang Jin, Paolo Favaro, Matthias Zwicker
2017 arXiv   pre-print
We include our prior in a formulation of image restoration as a Bayes estimator that also allows us to solve noise-blind image restoration problems.  ...  In this paper we introduce a natural image prior that directly represents a Gaussian-smoothed version of the natural image distribution.  ...  We address our DAE overfitting issue by using the new, lower bound prior L (x) with σ 1 = σ 2 = σ √ 2 .  ... 
arXiv:1709.03749v2 fatcat:7ddmi5sugjbxzmundeitqgg6dq

A Deep Optimization Approach for Image Deconvolution [article]

Zhijian Luo, Siyu Chen, Yuntao Qian
2019 arXiv   pre-print
In blind image deconvolution, priors are often leveraged to constrain the solution space, so as to alleviate the under-determinacy.  ...  Priors which are trained separately from the task of deconvolution tend to be instable, or ineffective.  ...  Our formulation is low-bounded by the logarithm of the MAP estimator [12, 4] as max x log p(y|x)p(x) ≥ max x log p(y|x) + log p(x + )g σ ( )d , where the prior is expressed as the logarithm of the Gaussiansmoothed  ... 
arXiv:1904.07516v1 fatcat:oswvicolezeffmioce4sc7fjfe

The Maximum Entropy on the Mean Method for Image Deblurring [article]

Gabriel Rioux, Rustum Choksi, Tim Hoheisel, Pierre Marechal, Christopher Scarvelis
2020 arXiv   pre-print
Image deblurring is a notoriously challenging ill-posed inverse problem.  ...  We propose an alternative approach, shifting the paradigm towards regularization at the level of the probability distribution on the space of images.  ...  approximations of the 0 penalty via concatenation of a quadratic penalty and a constant [95] or via a logarithmic prior [66] .  ... 
arXiv:2002.10434v4 fatcat:i6cvogrbmnb2dfpp6k2xup33s4

Variational Semi-blind Sparse Deconvolution with Orthogonal Kernel Bases and its Application to MRFM [article]

Se Un Park, Nicolas Dobigeon, Alfred O. Hero
2013 arXiv   pre-print
To solve this semi-blind deconvolution problem, prior distributions are specified for the PSF and the 3D image.  ...  The image prior distribution imposes an explicit atomic measure that corresponds to image sparsity. Importantly, the proposed Bayesian deconvolution algorithm does not require hand tuning.  ...  We observe that maximizing the lower bound L(q) is equivalent to minimizing the Kullback-Leibler (KL) divergence KL(q p).  ... 
arXiv:1303.3866v1 fatcat:y3oi7sziyvaklbldvqzumstjba

Variational Bayesian Learning for Decentralized Blind Deconvolution of Seismic Signals Over Sensor Networks

Dmitriy Shutin, Ban-Sok Shin
2021 IEEE Access  
Blind seismic deconvolution is cast into a probabilistic framework based on Sparse Bayesian learning developed for blind image deconvolution.  ...  This work discusses a variational Bayesian learning approach towards decentralized blind deconvolution of seismic signals within a sensor network.  ...  DISTRIBUTED SPARSE BLIND DECONVOLUTION AS A VARIATIONAL INFERENCE PROBLEM The maximization of the lower bound in (8) requires specifying (i) the form of the factors in ( 9 ) and (ii) the sparsifying prior  ... 
doi:10.1109/access.2021.3134126 fatcat:u6guourhjzahnnkmnqcg7wngny

Variational semi-blind sparse deconvolution with orthogonal kernel bases and its application to MRFM

Se Un Park, Nicolas Dobigeon, Alfred O. Hero
2014 Signal Processing  
To solve this semi-blind deconvolution problem, prior distributions are specified for the PSF and the 3D image.  ...  The image prior distribution imposes an explicit atomic measure that corresponds to image sparsity. Importantly, the proposed Bayesian deconvolution algorithm does not require hand tuning.  ...  We observe that maximizing the lower bound LðqÞ is equivalent to minimizing the Kullback-Leibler (KL) divergence KLðq∥pÞ.  ... 
doi:10.1016/j.sigpro.2013.06.013 fatcat:hdtlxwy6jzfxhehnpvjxsb6xfe

A Non-Convex Optimization Technique for Sparse Blind Deconvolution -- Initialization Aspects and Error Reduction Properties [article]

Aniruddha Adiga, Chandra Sekhar Seelamantula
2017 arXiv   pre-print
Comparisons with state-of-the-art blind deconvolution algorithms show that the deconvolution accuracy is higher in case of ALPA.  ...  Sparse blind deconvolution is the problem of estimating the blur kernel and sparse excitation, both of which are unknown.  ...  In the computer vision and image processing communities, blind deconvolution is almost synonymous with image deblurring.  ... 
arXiv:1708.07370v2 fatcat:vfvz7kkb4najtgl36pn3456e3i

Shift-Variant Blind Deconvolution Using a Field of Kernels

Motoharu SONOGASHIRA, Masaaki IIYAMA, Michihiko MINOH
2017 IEICE transactions on information and systems  
Motoharu SONOGASHIRA †a) , Nonmember, Masaaki IIYAMA †b) , Member, and Michihiko MINOH †c) , Fellow SUMMARY Blind deconvolution (BD) is the problem of restoring sharp images from blurry images when convolution  ...  Experiments using images with nonuniform blur demonstrate the effectiveness of the proposed SV BD method in comparison with previous SI and SV approaches. key words: blind deconvolution, deblurring, shift-variant  ...  Then, we perform lower bound maximization with q(Gx) instead of q(x).  ... 
doi:10.1587/transinf.2016pcp0013 fatcat:xgzgjcinn5fg7f77tfuqbc7ll4

Robust Blind Deconvolution via Mirror Descent [article]

Sathya N. Ravi, Ronak Mehta, Vikas Singh
2018 arXiv   pre-print
Keywords: blind deconvolution, robust continuous optimization  ...  We derive new insights into the theoretical underpinnings of blind deconvolution.  ...  Prior Work Methods for image deblurring via blind deconvolution have employed a variety of regularizations derived from a wide range of image priors.  ... 
arXiv:1803.08137v1 fatcat:o2dtouwyrjc5hchv3cjoioghba

Blind Recovery of Sparse Signals from Subsampled Convolution [article]

Kiryung Lee, Yanjun Li, Marius Junge, Yoram Bresler
2015 arXiv   pre-print
In particular, it has been shown that a naive sparsity model is not a strong enough prior for identifiability in the blind deconvolution problem.  ...  Under this prior, we provide an iterative algorithm that achieves guaranteed performance in blind deconvolution at near optimal sample complexity.  ...  In wireless communications and image processing, the blind deconvolution of a single input signal from multiple channel outputs has been of interest.  ... 
arXiv:1511.06149v2 fatcat:hc6ln34q7bfqxaps4mhs3gs3u4

APEX blind deconvolution of color Hubble space telescope imagery and other astronomical data

Alfred S. Carasso
2006 Optical Engineering: The Journal of SPIE  
The APEX method is a noniterative direct blind deconvolution technique that can sharpen certain kinds of high-resolution images in quasi real time.  ...  Not all images can be usefully enhanced with the APEX method.  ...  A Priori Nonuniqueness in Blind Deconvolution Blind deconvolution seeks to deblur an image without knowing the cause of the blur.  ... 
doi:10.1117/1.2362579 fatcat:l2zrgpedv5e4nm2tag3xja6cae

Estimation of speed of sound in dual-layered media using medical ultrasound image deconvolution

Ho-Chul Shin, Richard Prager, Henry Gomersall, Nick Kingsbury, Graham Treece, Andrew Gee
2010 Ultrasonics  
Previously we reported a new method of sound-speed estimation in the context of image deconvolution.  ...  Then, when the layer boundary position is known, a series of deconvolutions are carried out with dual-layered pointspread functions having different lower-layer speeds.  ...  Using an Expectation-Maximisation (see p. 285 in [23] ) framework, we can construct an iterative deconvolution strategy alternating between the Wiener filter for x (Expectation step) and the denoising  ... 
doi:10.1016/j.ultras.2010.02.008 pmid:20231026 fatcat:3lcwxan2hjazpguulysoibj244
« Previous Showing results 1 — 15 out of 886 results