A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
DeepDeblur: Fast one-step blurry face images restoration
[article]
2017
arXiv
pre-print
Preserved Fulltext
A smoothness regularization as well as a facial regularization are added to keep facial identity information which is the key to face image applications. ...
Also they cannot handle face images in small size. Our proposed method restores sharp face images directly in one step using Convolutional Neural Network. ...
However, L2 regularization just neglects texture details and information for recognition. Also, there are unrealistic noisy region in the generated image after deep neural network. ...
arXiv:1711.09515v1
fatcat:ayojtpccufh3npsfdedteai5xa
Autofocusing+: Noise-Resilient Motion Correction in Magnetic Resonance Imaging
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this work, we propose a neural network-based regularization term to enhance Autofocusing, a classic optimization-based method to remove motion artifacts. ...
The method takes the best of both worlds: the optimization-based routine iteratively executes the blind demotion and deep learning-based prior penalizes for unrealistic restorations and speeds up the convergence ...
The blind demotion routine uses the regularizer as an image prior penalizing for unrealistic restorations and improving the reconstruction quality. ...
arXiv:2203.05569v1
fatcat:rijnjbjdzbfwni56v2xuwiuz2m
Single Image Dehazing Based on Weighted Variational Regularized Model
2021
IEICE transactions on information and systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Specifically, the proposed model can simultaneously refine the transmittance and restore clear images, yielding a haze-free image. ...
Then a novel weighted variational regularization model is proposed to refine the transmission. ...
So, Eq. (3) can be rewritten as: arg min J * ,t,N
Fig. 2 2 Convergence curves for different images. (a) Most of the realistic images, (b) Most of the synthetic images. ...
doi:10.1587/transinf.2021edp7033
fatcat:auhyaaowdbeyvix6l5zgydexnu
Deblurring adaptive optics retinal images using deep convolutional neural networks
2017
Biomedical Optics Express
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This network was validated on synthetically generated retinal images as well as real AO retinal images. ...
The mapping was represented as a deep convolutional neural network that was trained to output high-quality images directly from blurry inputs without any preprocessing. ...
The regularizing prior term r(x) expresses the knowledge of the image statistics (e.g. sparsity priors, edge priors) and forces the solution to be a nice (meets the prior knowledge without obvious faults ...
doi:10.1364/boe.8.005675
pmid:29296496
pmcid:PMC5745111
fatcat:kq2efrqzfjfdpg4l6sndz3zcii
Deblurring Turbulent Images via Maximizing L1 Regularization
2021
Symmetry
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
To handle these problems, we first propose a convex image prior; namely, maximizing L1 regularization (ML1). ...
However, the general sparse priors support blurry images instead of explicit images, so the details of the restored images are lost. ...
Lately, the neural network has been employed for image restoration. Sun et al. [24] applied a convolutional neural network (CNN) to remove non-uniform motion blur. Zhang et al. ...
doi:10.3390/sym13081414
fatcat:peooua72yzegfhb3qkbqevggbm
Deep Learning for Image/Video Restoration and Super-resolution
2022
Foundations and Trends in Computer Graphics and Vision
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We can consider learned image/video restoration and SR as learning either a nonlinear regressive mapping from degraded to ideal images based on the universal approximation theorem, or a generative model ...
Recent advances in neural signal processing led to significant improvements in the performance of learned image/video restoration and super-resolution (SR). ...
In this case, minimizing the energy of high frequency image components can be viewed as imposing a smoothness constraint as an image prior. ...
doi:10.1561/0600000100
fatcat:5keqxf3lingubhlgrptdpq42xy
Adaptively Sparse Regularization for Blind Image Restoration
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The high-order gradients combine with low-order ones to form a hybrid regularization term, and an adaptive operator derived from the image entropy is introduced to maintain a good convergence. ...
Blind image restoration is widely used to improve image quality, where the main goal is to faithfully estimate the blur kernel and the latent sharp image. ...
[12] proposed a network consists of three deep CNNs and a recurrent neural network (RNN). Xu et al. [13] adopted CNN to regularize edge enhancement for kernel and image estimation. Li et al. ...
arXiv:2101.09401v1
fatcat:nfyavmj3xbhzfgkiw7dy6z2ssi
Unsupervised water scene dehazing network using multiple scattering model
2021
PLoS ONE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Unlike previous image dehazing methods, our method uses the unsupervised neural network and the atmospheric multiple scattering model and solves the problem of difficult acquisition of ideal datasets and ...
The method has a wide range of applications, with haze being thick and variable in marine, river and lake scenes, the method can be used to assist ship vision for target detection or forward road recognition ...
This method simply viewed the convolution of the feature map of the low-resolution image and the blur kernel as Hadamard product in the neural network, and finally restored the high-resolution image. ...
doi:10.1371/journal.pone.0253214
pmid:34181688
pmcid:PMC8238221
fatcat:3osk4bzal5gadacymqw7sgpuou
Single Image Dehazing via Conditional Generative Adversarial Network
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
In this paper, we present an algorithm to directly restore a clear image from a hazy image. ...
In contrast, we solve this problem based on a conditional generative adversarial network (cGAN), where the clear image is estimated by an end-to-end trainable neural network. ...
Finally, we combine the adversarial loss, perceptual loss, L 1 -regularized gradient prior and content-based pixel-wise loss to regularize the proposed generative network, which is defined as L = αL A ...
doi:10.1109/cvpr.2018.00856
dblp:conf/cvpr/LiPLT18
fatcat:i3ougkomjzd3hisfccvhicefg4
OCT Image Restoration Using Non-Local Deep Image Prior
2020
Electronics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
By adding the sorted non-local statics as a regularization loss in the DIP learning, more low-level image statistics are captured by CNN networks in the process of OCT image restoration. ...
Recently, deep image prior (DIP) networks have been proposed for image restoration without pre-training since the CNN structures have the intrinsic ability to capture the low-level statistics of a single ...
In this paper, a non-local deep image prior network was proposed for OCT image restoration. ...
doi:10.3390/electronics9050784
fatcat:r7tztjiggvgfxjotswg2tkvy7y
Editorial: Introduction to the Issue on Deep Learning for Image/Video Restoration and Compression
2021
IEEE Journal on Selected Topics in Signal Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
by a direct minimization of the energy function due to added regularization property of deep neural networks. ...
It adopts heatmaps from the landmark localization network as an additional prior. ...
doi:10.1109/jstsp.2021.3053364
fatcat:hjo5pvw6lvgpfga2wfq4vpaq3q
Non-blind Deblurring: Handling Kernel Uncertainty with CNNs
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Our network mitigates the effects of kernel noise so as to yield detail-preserving and artifact-free restoration. ...
We provide multiple latent image estimates corresponding to different prior strengths obtained from a given blurry observation in order to exploit the complementarity of these inputs for improved learning ...
Acknowledgements: The first author thanks Sunil Kumar for his help in running some comparisons. The authors gratefully acknowledge the travel grant support from Google Research India. ...
doi:10.1109/cvpr.2018.00345
dblp:conf/cvpr/VasuMR18
fatcat:owmbchycwzaq5hqjfhmqcqjssy
Deep Underwater Image Enhancement
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
To address this problem, we propose a convolutional neural network based image enhancement model, i.e., UWCNN, which is trained efficiently using a synthetic underwater image database. ...
Then, we separately train multiple UWCNN models for each underwater image formation type. ...
Reformulating the underwater image enhancement as an image restoration problem with an explicit regularization prior offers several benefits; i) The exact parameterization of the prior Ψ(·) can be unknown ...
arXiv:1807.03528v1
fatcat:afpdophjjvbpjard2kdsszyu2y
Physics-Based Generative Adversarial Models for Image Restoration and Beyond
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
These problems are highly ill-posed, and the common assumptions for existing methods are usually based on heuristic image priors. ...
The proposed algorithm is trained in an end-to-end fashion and can be applied to a variety of image restoration and related low-level vision problems. ...
Therefore, the adversarial loss can be used as a prior to regularize the solution space of image restoration as demonstrated by [45] . ...
arXiv:1808.00605v2
fatcat:ilu7dlurhrgexabbmzdaguakey
An end-to-end sea fog removal network using multiple scattering model
2021
PLoS ONE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
An end-to-end sea fog removal network using multiple scattering model was proposed. In this network, the atmospheric multiple scattering model was re-formulated and used for sea fog removal. ...
Therefore, we used the atmospheric multiple scattering model to avoid image blurring. ...
[3] proposed a dehazing method using dark channel prior (DCP) for image dehazing. ...
doi:10.1371/journal.pone.0251337
pmid:33989312
pmcid:PMC8121339
fatcat:csik2k34ljeojiwtuewcnikijm
« Previous
Showing results 1 — 15 out of 6,339 results