W.Z Shao

W.Z Shao
Nanjing University of Posts and Telecommunications · College of Telecommunications and Information Engineering

Postdoc (Technion - Israel Institute of Technology)

About

67
Publications
4,813
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
401
Citations
Citations since 2016
29 Research Items
306 Citations
20162017201820192020202120220102030405060
20162017201820192020202120220102030405060
20162017201820192020202120220102030405060
20162017201820192020202120220102030405060
Additional affiliations
May 2014 - June 2015
Technion - Israel Institute of Technology
Position
  • PostDoc Position
January 2012 - present
Nanjing University of Posts and Telecommunications
Position
  • Professor (Assistant)
September 2003 - July 2008
Nanjing University of Science and Technology
Position
  • PhD Student

Publications

Publications (67)
Article
In blind motion deblurring, leading methods today tend towards highly non-convex approximations of the l0-norm, especially in the image regularization term. In this paper, we propose a simple, effective and fast approach for the estimation of the motion blur-kernel, through a bi-l0-l2-norm regularization imposed on both the intermediate sharp image...
Conference Paper
Full-text available
This paper proposes a simple, accurate, and robust approach to single image blind super-resolution (SR). This task is formulated as a functional to be minimized with respect to both an intermediate super-resolved image and a non- parametric blur-kernel. The proposed method includes a convolution consistency constraint which uses a non-blind learnin...
Article
It is well-known that shaken cameras or mobile phones during exposure usually lead to motion blurry photographs. Therefore, camera shake deblurring or motion deblurring is required and requested in many practical scenarios. The contribution of this paper is the proposal of a simple yet effective approach for motion blur kernel estimation, i.e., bli...
Article
Full-text available
This paper proposes to adaptively combine the known total variation model and more recent Frobenius norm regularization for multi-frame image super-resolution (SR). In contrast to existing literature, in this paper both the composite prior modeling and posterior variational optimization are achieved in the Bayesian framework by utilizing the Kullba...
Article
Blind image deconvolution is a fundamental task in image processing, computational imaging, and computer vision. It has earned intensive attention in the past decade since the seminal work of Fergus et al. [1] for camera shake removal. In spite of the recent great progress in this field, this paper aims to formulate the blind problem with a simpler...
Article
This work studies dynamic scene deblurring (DSD) of a single photograph, mainly motivated by the very recent DeblurGAN method. It is discovered that training the generator alone of DeblurGAN will result in both regular checkerboard effects and irregular block color excursions unexpectedly. In this paper, two aspects of endeavors are made for a more...
Article
Super-resolution of facial images, a.k.a. face hallucination, has been intensively studied in the past decades due to the increasingly emerging analysis demands in video surveillance, e.g., face detection, verification, identification. However, the actual performance of most previous hallucination approaches will drop dramatically when a very low-r...
Article
Full-text available
Single image nonparametric blind super-resolution is a fundamental image restoration problem yet largely ignored in the past decades among the computational photography and computer vision communities. An interesting phenomenon is observed that learning-based single image super-resolution (SR) has been experiencing a rapid development since the boo...
Article
Full-text available
In this paper, a fast blind deconvolution approach is proposed for image deblurring by modifying a recent well-known natural image model, i.e., the total generalized variation (TGV). As a generalization of total variation, TGV aims at reconstructing a higher-quality image with high-order smoothness as well as sharp edge structures. However, when it...
Article
There are a lot of non-blind image deblurring methods, especially, with the total variation (TV) model-based method. However, how to choose the parameters adaptively for regularization is a major open problem. We proposed a very novel method which is based on TV deep network to learn the best parameters adaptively for regularization. We used deep l...
Chapter
Full-text available
This paper aims to exploit the full potential of gradient-based methods, attempting to explore a simple, robust yet discriminative image prior for blind deblurring. The specific contributions are three-fold: Above all, a pure gradient-based heavy-tailed model is proposed as a generalized integration of the normalized sparsity and the relative total...
Article
This paper aims to propose a candidate solution to the challenging task of single-image blind super-resolution (SR), via extensively exploring the potentials of learning-based SR schemes in the literature. The task is formulated into an energy functional to be minimized with respect to both an intermediate super-resolved image and a nonparametric b...
Article
Full-text available
We propose a convolutional sparse coding (CSC) for super resolution (CSC-SR) algorithm with a joint Bayesian learning strategy. Due to the unknown parameters in solving CSC-SR, the performance of the algorithm depends on the choice of the parameter. To this end, a coupled Beta-Bernoulli process is employed to infer appropriate filters and sparse co...
Chapter
Full-text available
Blind image deblurring or deconvolution is a very hot topic towards which numerous methods have been put forward in the past decade, demonstrating successful deblurring results on one or another benchmark natural image dataset. However, most of existing algorithms are found not robust enough as dealing with images in specific scenarios, such as ima...
Article
Full-text available
We focus on blind image deconvolution, which has attracted intensive attentions since Fergus et al.’s influential work in 2006. Among the current literature, the daring idea of imposing the normalized sparsity measure on blind image deblurring is a recent spotlight, which is, nevertheless, far from practical use in terms of estimating accuracy, eff...
Article
Nonlocal image representation methods, including group-based sparse coding and BM3D, have shown their great performance in application to low-level tasks. The nonlocal prior is extracted from each group consisting of patches with similar intensities. Grouping patches based on intensity similarity, however, gives rise to disturbance and inaccuracy i...
Conference Paper
Single sensor camera captures scenes using a color filter array, such that each pixel samples only one of the three primary colors. A process called color demosaicking (CDM) is used to produce full color image. In this paper, we present a new variational model for high quality CDM. The robust data term is measured by Z 1 -norm to repress the heavy...
Article
Full-text available
Sparse representation has shown the effectiveness in solving image restoration and classification problems. To improve the performance of sparse representation, the patch-based and graph-based regularization term with respect to the sparse coding are proposed to solve image restoration and classification problems, respectively. In this paper, the l...
Article
This paper proposes a regularized negative log-marginal-likelihood minimization method for motion blur-kernel estimation, which is the core problem of blind motion deblurring. In contrast to existing approaches, the proposed method treats the blur-kernel as a deterministic parameter in a directed graphical model wherein, the sharp image is sparsely...
Article
The nonparametric blur-kernel estimation, using either single image or multi-observation, has been intensively studied since Fergus et al.’s influential work (ACM Trans Graph 25: 787-794, 2006). However, in the current literature there is always a gap between the two highly relevant problems; that is, single and multi-shot blind deconvolution are m...
Article
Compressive imaging has been intensively studied during the past few years, capable of reconstructing high-resolution images with sampling ratios far below the Nyquist rate. In contrast to previous works, a new l0–l2 minimisation approach is proposed for compressive imaging in this paper, regularised by sparsity constraints in three complementary f...
Article
In blind motion deblurring, a commonly practiced approach is to perform the restoration in two stages: first, the blur-kernel is estimated along with a temporal restored image, and then a regular image deblurring algorithm is applied with the found kernel. This work addresses the first stage, for which a great deal of effort has been placed on the...
Article
Full-text available
This paper considers the problem of recovering low-rank matrices which are heavily corrupted by outliers or large errors. To improve the robustness of existing recovery methods, the problem is solved by formulating it as a generalized nonsmooth nonconvex minimization functional via exploiting the Schatten p-norm (0 < p <= 1) and L-q(0 <q <= 1) semi...
Article
We propose a structural feature region-based active contour model based on the level set method for image segmentation. Firstly, an anisotropic data fitting term is proposed to adaptively detect the intensity both in terms of local direction and global region. Secondly, coupling with the duality theory and a structured gradient vector flow (SGVF) m...
Conference Paper
This paper proposes adaptively combining the known total variation model and more recent Frobenius norm regularization for multi-frame super-resolution (SR). In contrast to existing literature, both composite prior modeling and variational optimization are achieved in the Bayesian framework by utilizing the Kullback-Leibler divergence, and the para...
Article
Multi-frame image super-resolution (SR) has been intensively studied in recent years, aiming at reconstructing high-resolution images from several degraded ones (e.g., shift, blurred, aliased, and noisy). In the literature, one of the most popular SR frameworks is the maximum a posteriori model, where a spatially homogeneous image prior and manuall...
Article
We propose a simple, yet efficient image deconvolution approach, which is formulated as a complementary K-frame-based l 0–l 2 minimization problem, aiming at benefiting from the advantages of each frame. The problem is solved by borrowing the idea of alternating split augmented Lagrangians. The experimental results demonstrate that our approach has...
Article
Image deconvolution is an ill-posed, low-level vision task, restoring a clear image from the blurred and noisy observation. From the perspective of statistics, previous work on image deconvolution has been formulated as a maximum a posteriori or a general Bayesian inference problem, with Gaussian or heavy-tailed non-Gaussian prior image models (e.g...
Article
In the past two decades, more and more quality and reliability activities have been moving into the design of product and process. The design and analysis of computer experiments, as a new frontier of the design of experiments, has become increasingly popular among modern companies for optimizing product and process conditions and producing high-qu...
Article
Metamodeling or surrogate modeling is becoming increasingly popular for product design optimization in manufacture industries. In this paper, an extended Gaussian Kriging method is proposed to improve the prediction performance of widely used ordinary Kriging in engineering design. Unlike the forgoing approaches, the proposed method places a varian...
Article
In this article, an efficient Bayesian meta-modeling approach is proposed for Gaussian stochastic process models in computer experiments. Different prior densities and particularly, a non informative hyper prior have been employed on the parameters involved in the correlation matrix. And the estimation of related parameters is obtained by the expec...
Article
In this paper, an efficient and effective Gaussian Kriging metamodeling approach is proposed in the framework of Bayesian maximum a posterior. Different prior densities and particularly, a Jeffreys' noninformative density based hierarchical prior is imposed respectively on the regression coefficients in the mean model and the correlation parameters...
Article
Computer experiments have become an attractive alternative to study complex physical systems. Computer experiments are primarily on the task of meta-modeling, which is the central to achieving any goal in computer experiments. A novel approach of meta-modeling was proposed for computer experiments via Bayesian hierarchical prior. Implementation was...
Article
In computer experiments, simulation of complex phenomenon requires a large number of inputs and identifying the inputs which most impact the outputs is of crucial importance. A novel algorithm of Bayesian variable selection was proposed for computer experiments via a Jeffreys' noninformative super prior. Different from existed algorithms of variabl...
Article
This paper mainly focuses on the structure tensor based image modeling approaches, including partial differential equations (PDE) and variational functionals. A type of corner shock filter is designated based on measures of corner strength and the theory of level-set evolution to enhance the corner structures. The filtering behavior of structure te...
Article
In computer experiments, simulation of complex phenomena requires a large number of inputs, and identifying the inputs which make a notable impact on the outputs is of crucial importance. A new Bayesian variable selection algorithm is proposed for computer experiments via a hierarchical sparseness prior. The new algorithm is not only capable of del...
Article
Computer experiments introduce the fundamental idea of building a metamodel of its simulation model, which has widely used for complex physical systems. The paper proposes a novel Bayesian meta-modeling approach for computer experiments. It imposes a hierarchical prior on the correlation parameters in Kriging based on Jeffreys' noninformative hyper...
Article
It is currently a hot research topic that how to design an effective over-complete dictionary matching various geometric structures of images to provide sparse representation of images. A multi-component Gabor perception dictionary matching various image structures is constructed in terms of geometric properties of the local structures and the perc...
Article
A variational super-resolution reconstruction method is proposed. First of all, a kind of structure-adaptive anisotropic filter is designed based on the recently reported bilateral filtering. It is not only edge-preserving but also corner-preserving. Then, an anisotropic Markov random field (MRF) model is deduced, which is the improvement of both t...
Article
The edge and corner structures are two categories of perceptually important image characteristics, and hence, edge-and-corner preserving regularization is required for many problems in image processing. In this paper, the first novelty is to propose a new edge-and-corner preserving approach for image interpolation, based on the coupling of robust o...
Article
Many magnification algorithms have been proposed in past decades, most of which concentrate on the smooth reconstruction of edge structures. Edge reconstruction, however, can destroy corners, thus producing perceptually unpleasant rounded corner structures. In this work, corner shock filtering is designated for enhancing corners relative to the kno...
Article
Super-Resolution (SR) reconstruction has been a very hot research topic currently. A kind of generalized MRF (GMRF, generalized Markov random field) models is firstly proposed based on the recently reported bilateral filtering. The GMRF model is not only edge-preserving and robust to noise, inherited directly from the bilateral filtering, but also...
Article
A unified designing framework for nonlinear digital filters is discussed in the paper. Based on robust statistics and the idea of bilateral filtering, a unified and robust energy functional for image restoration is firstly constructed, which incorporates both the double-weighting idea of bilateral filtering and the robustness of robust ρ-functions...
Chapter
Though there have been proposed many magnification works in literatures, magnification in this paper is approached as reconstructing the geometric structures of the original high-resolution image. The structure tensor is able to estimate the orientation of both the edges and flow-like textures, which hence is much appropriate to magnification. Firs...
Conference Paper
Though there have been proposed many magnification works in literatures, magnification in this paper is approached as reconstructing the geometric structures of the original high-resolution image. The structure tensor is able to estimate the orientation of both the edges and flow-like textures, which hence is much appropriate to magnification. Firs...
Conference Paper
Image magnification, or interpolation, produces a high resolution image from a low resolution, and perhaps noisy image. There have been proposed a variety of magnification algorithms. However, they are either sensitive to the noise, or non-robust to the blocking artifacts, or of high computational complexity, which hence limits their utility. In th...
Article
Image magnification, or interpolation, produces a high resolution image from a low resolution, and perhaps noisy image. There have been proposed a variety of magnification works. However, they are either sensitive to the noise, or nonrobust to the blocking artifacts, or of high computational complexity, which hence limits their utility. In this pap...
Article
In road surface images, in order to detect the cracks that are very tiny, we have to enhance them first. The image enhancement is a new type of diffusion process that simultaneously enhances, sharpens, and denoises images. Conventional coherence enhancing diffusion enhances the flow-like cracks but the other unwanted elements on the road surface ar...

Network

Cited By

Projects

Projects (3)
Project
In this granted project, we will develop a airborne imaging spectrometer, which features large field of view and high spectral resolution, and also we will develop software of hypespectral data processing & intelligent analysis.