• Corpus ID: 7641598

A Clearer Picture of Blind Deconvolution

@article{Perrone2014ACP,
  title={A Clearer Picture of Blind Deconvolution},
  author={Daniel Perrone and Paolo Favaro},
  journal={ArXiv},
  year={2014},
  volume={abs/1412.0251}
}
Blind deconvolution is the problem of recovering a sharp image and a blur kernel from a noisy blurry image. Recently, there has been a significant effort on understanding the basic mechanisms to solve blind deconvolution. While this effort resulted in the deployment of effective algorithms, the theoretical findings generated contrasting views on why these approaches worked. On the one hand, one could observe experimentally that alternating energy minimization algorithms converge to the desired… 
Towards a Novel Paradigm in Blind Deconvolution: From Natural to Cartooned Image Statistics
TLDR
This thesis proposes a novel “vanilla” algorithm stripped of any enhancement typically used in the literature, and provides experimental evidence supporting the recent belief that a good image prior is one that leads to a good blur estimate rather than being a good natural image statistical model.
Variational Bayesian Blind Image Deconvolution: A review
TLDR
This paper provides a review of the recent literature on Bayesian Blind Image Deconvolution methods and focuses on VB inference and the use of SG and SMG models with coverage of recent advances in sampling methods.
Blind Image Deblurring using the l0 Gradient Prior
TLDR
This article analyzes the blur kernel estimation method introduced by Pan and Su in 2013 that uses an l0 prior on the gradient image and presents deconvolution results using the estimated blur kernels.
Blind de-convolution of images degraded by atmospheric turbulence
TLDR
A convolutional network for blind deblurring atmospheric turbulence (BDATNet) that includes a feature extraction noise suppression block (FENSB), an asymmetric U-net, and an image reconstruction subnetwork (IRSubnetwork).

References

SHOWING 1-10 OF 41 REFERENCES
Understanding Blind Deconvolution Algorithms
TLDR
The previously reported failure of the naive MAP approach is explained by demonstrating that it mostly favors no-blur explanations and it is shown that, using reasonable image priors, a naive simulations MAP estimation of both latent image and blur kernel is guaranteed to fail even with infinitely large images sampled from the prior.
Total Variation Blind Deconvolution: The Devil Is in the Details
  • Daniel Perrone, P. Favaro
  • Mathematics, Computer Science
    2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
TLDR
An adaptation of this algorithm, based on the algorithm of Chan and Wong, is introduced and it is shown that, in spite of its extreme simplicity, it is very robust and achieves a performance comparable to the state of the art.
Analysis of Bayesian Blind Deconvolution
TLDR
It is demonstrated that the VB methodology can be recast as an unconventional MAP problem with a very particular penalty/prior that couples the image, blur kernel, and noise level in a principled way and challenges the prevailing notion of why VB is successful for blind deconvolution while providing a transparent platform for introducing enhancements and extensions.
Total variation blind deconvolution
TLDR
A blind deconvolution algorithm based on the total variational (TV) minimization method proposed is presented, and it is remarked that psf's without sharp edges, e.g., Gaussian blur, can also be identified through the TV approach.
Blind image deconvolution
TLDR
The problem of blind deconvolution for images is introduced, the basic principles and methodologies behind the existing algorithms are provided, and the current trends and the potential of this difficult signal processing problem are examined.
Blind deconvolution using a normalized sparsity measure
TLDR
A new type of image regularization which gives lowest cost for the true sharp image is introduced, which allows a very simple cost formulation to be used for the blind deconvolution model, obviating the need for additional methods.
Convergence of the alternating minimization algorithm for blind deconvolution
Abstract Blind deconvolution refers to the image processing task of restoring the original image from a blurred version without the knowledge of the blurring function. One approach that has been
A regularization approach to joint blur identification and image restoration
TLDR
A well-known space-adaptive regularization method for image restoration is extended, which effectively utilizes, among others, the piecewise smoothness of both the image and the PSF to solve the scale problem inherent to the cost function.
Efficient marginal likelihood optimization in blind deconvolution
TLDR
This paper derives a simple approximated MAPk algorithm which involves only a modest modification of common MAPx, k algorithms, and shows that MAPk can, in fact, be optimized easily, with no additional computational complexity.
Blind deconvolution using TV regularization and Bregman iteration
In this paper we formulate a new time dependent model for blind deconvolution based on a constrained variational model that uses the sum of the total variation norms of the signal and the kernel as a
...
1
2
3
4
5
...