arXiv subjects

Bing Zeng

Publications and source records attributed to Bing Zeng.

65 records · Page 4Linked to original sources

arXiv2019

MGANet: A Robust Model for Quality Enhancement of Compressed Video

In video compression, most of the existing deep learning approaches concentrate on the visual quality of a single frame, while ignoring the useful priors as well as the temporal information of adjacent frames. In this paper, we propose a multi-frame guided attention network (MGANet) to enhance the quality of compressed videos. Our network is composed of a temporal encoder that discovers inter-frame relations, a guided encoder-decoder subnet that encodes and enhances the visual patterns of target frame, and a multi-supervised reconstruction component that aggregates information to predict details. We design a bidirectional residual convolutional LSTM unit to implicitly discover frames variations over time with respect to the target frame. Meanwhile, the guided map is proposed to guide our network to concentrate more on the block boundary. Our approach takes advantage of intra-frame prior information and inter-frame information to improve the quality of compressed video. Experimental results show the robustness and superior performance of the proposed method.Code is available at https://github.com/mengab/MGANet

cs.CV↗

arXiv2018

Rain Removal By Image Quasi-Sparsity Priors

Rain streaks will inevitably be captured by some outdoor vision systems, which lowers the image visual quality and also interferes various computer vision applications. We present a novel rain removal method in this paper, which consists of two steps, i.e., detection of rain streaks and reconstruction of the rain-removed image. An accurate detection of rain streaks determines the quality of the overall performance. To this end, we first detect rain streaks according to pixel intensities, motivated by the observation that rain streaks often possess higher intensities compared to other neighboring image structures. Some mis-detected locations are then refined through a morphological processing and the principal component analysis (PCA) such that only locations corresponding to real rain streaks are retained. In the second step, we separate image gradients into a background layer and a rain streak layer, thanks to the image quasi-sparsity prior, so that a rain image can be decomposed into a background layer and a rain layer. We validate the effectiveness of our method through quantitative and qualitative evaluations. We show that our method can remove rain (even for some relatively bright rain) from images robustly and outperforms some state-of-the-art rain removal algorithms.

cs.CV↗

arXiv2018

Removing rain streaks by a linear model

Removing rain streaks from a single image continues to draw attentions today in outdoor vision systems. In this paper, we present an efficient method to remove rain streaks. First, the location map of rain pixels needs to be known as precisely as possible, to which we implement a relatively accurate detection of rain streaks by utilizing two characteristics of rain streaks.The key component of our method is to represent the intensity of each detected rain pixel using a linear model: $p=αs + β$, where $p$ is the observed intensity of a rain pixel and $s$ represents the intensity of the background (i.e., before rain-affected). To solve $α$ and $β$ for each detected rain pixel, we concentrate on a window centered around it and form an $L_2$-norm cost function by considering all detected rain pixels within the window, where the corresponding rain-removed intensity of each detected rain pixel is estimated by some neighboring non-rain pixels. By minimizing this cost function, we determine $α$ and $β$ so as to construct the final rain-removed pixel intensity. Compared with several state-of-the-art works, our proposed method can remove rain streaks from a single color image much more efficiently - it offers not only a better visual quality but also a speed-up of several times to one degree of magnitude.

cs.CV↗

arXiv2018

Simultaneously Color-Depth Super-Resolution with Conditional Generative Adversarial Network

Recently, Generative Adversarial Network (GAN) has been found wide applications in style transfer, image-to-image translation and image super-resolution. In this paper, a color-depth conditional GAN is proposed to concurrently resolve the problems of depth super-resolution and color super-resolution in 3D videos. Firstly, given the low-resolution depth image and low-resolution color image, a generative network is proposed to leverage mutual information of color image and depth image to enhance each other in consideration of the geometry structural dependency of color-depth image in the same scene. Secondly, three loss functions, including data loss, total variation loss, and 8-connected gradient difference loss are introduced to train this generative network in order to keep generated images close to the real ones, in addition to the adversarial loss. Experimental results demonstrate that the proposed approach produces high-quality color image and depth image from low-quality image pair, and it is superior to several other leading methods. Besides, we use the same neural network framework to resolve the problem of image smoothing and edge detection at the same time.

cs.CV↗

arXiv2018

A Decomposition-Based Many-Objective Evolutionary Algorithm with Local Iterative Update

Existing studies have shown that the conventional multi-objective evolutionary algorithms (MOEAs) based on decomposition may lose the population diversity when solving some many-objective optimization problems. In this paper, a simple decomposition-based MOEA with local iterative update (LIU) is proposed. The LIU strategy has two features that are expected to drive the population to approximate the Pareto Front with good distribution. One is that only the worst solution in the current neighborhood is swapped out by the newly generated offspring, preventing the population from being occupied by copies of a few individuals. The other is that its iterative process helps to assign better solutions to subproblems, which is beneficial to make full use of the similarity of solutions to neighboring subproblems and explore local areas in the search space. In addition, the time complexity of the proposed algorithm is the same as that of MOEA/D, and lower than that of other known MOEAs, since it considers only individuals within the current neighborhood at each update. The algorithm is compared with several of the best MOEAs on problems chosen from two famous test suites DTLZ and WFG. Experimental results demonstrate that only a handful of running instances of the algorithm on DTLZ4 lose their population diversity. What's more, the algorithm wins in most of the test instances in terms of both running time and solution quality, indicating that it is very effective in solving MaOPs.

cs.NE↗

arXiv2018

A mullti- or many- objective evolutionary algorithm with global loop update

Multi- or many-objective evolutionary algorithm- s(MOEAs), especially the decomposition-based MOEAs have been widely concerned in recent years. The decomposition-based MOEAs emphasize convergence and diversity in a simple model and have made a great success in dealing with theoretical and practical multi- or many-objective optimization problems. In this paper, we focus on update strategies of the decomposition- based MOEAs, and their criteria for comparing solutions. Three disadvantages of the decomposition-based MOEAs with local update strategies and several existing criteria for comparing solutions are analyzed and discussed. And a global loop update strategy and two hybrid criteria are suggested. Subsequently, an evolutionary algorithm with the global loop update is implement- ed and compared to several of the best multi- or many-objective optimization algorithms on two famous unconstraint test suites with up to 15 objectives. Experimental results demonstrate that unlike evolutionary algorithms with local update strategies, the population of our algorithm does not degenerate at any generation of its evolution, which guarantees the diversity of the resulting population. In addition, our algorithm wins in most instances of the two test suites, indicating that it is very compet- itive in terms of convergence and diversity. Running results of our algorithm with different criteria for comparing solutions are also compared. Their differences are very significant, indicating that the performance of our algorithm is affected by the criterion it adopts.

cs.NE↗

arXiv2017

Fast Low-Rank Bayesian Matrix Completion with Hierarchical Gaussian Prior Models

The problem of low rank matrix completion is considered in this paper. To exploit the underlying low-rank structure of the data matrix, we propose a hierarchical Gaussian prior model, where columns of the low-rank matrix are assumed to follow a Gaussian distribution with zero mean and a common precision matrix, and a Wishart distribution is specified as a hyperprior over the precision matrix. We show that such a hierarchical Gaussian prior has the potential to encourage a low-rank solution. Based on the proposed hierarchical prior model, a variational Bayesian method is developed for matrix completion, where the generalized approximate massage passing (GAMP) technique is embedded into the variational Bayesian inference in order to circumvent cumbersome matrix inverse operations. Simulation results show that our proposed method demonstrates superiority over existing state-of-the-art matrix completion methods.

cs.LG↗

arXiv2017

Whale swarm algorithm for function optimization

Increasing nature-inspired metaheuristic algorithms are applied to solving the real-world optimization problems, as they have some advantages over the classical methods of numerical optimization. This paper has proposed a new nature-inspired metaheuristic called Whale Swarm Algorithm for function optimization, which is inspired by the whales behavior of communicating with each other via ultrasound for hunting. The proposed Whale Swarm Algorithm has been compared with several popular metaheuristic algorithms on comprehensive performance metrics. According to the experimental results, Whale Swarm Algorithm has a quite competitive performance when compared with other algorithms.

cs.NE↗

arXiv2015

Real-Valued Khatri-Rao Subspace Approaches on the ULA and a New Nested Array

In underdetermined direction-of-arrival (DOA) estimation using the covariance-based signal models, the computational complexity turns into a noticeable issue because of the high dimension of the virtual array manifold. In this paper, real-valued Khatri-Rao (KR) approaches are developed on the uniform linear array (ULA) and the nested array. The complexities of subspace decomposition and spectral search are reduced compared with the complex-valued KR approach. By designing a special transformation matrix, the influence of the noise is removed in the mean time while the data is transformed from the complex domain to the real domain. Deploying the sensors with nonuniform spacings can raise the degree of freedom (DOF) and hence help detect more sources in the underdetermined situation. To increase the DOF further, a new nested array geometry is designed. The real-valued denoising KR approach developed on the new nested array can resolve more sources with reduced complexities. The performance improvement is demonstrated by numerical studies.

cs.IT↗

arXiv2015

An Iterative Reweighted Method for Tucker Decomposition of Incomplete Multiway Tensors

We consider the problem of low-rank decomposition of incomplete multiway tensors. Since many real-world data lie on an intrinsically low dimensional subspace, tensor low-rank decomposition with missing entries has applications in many data analysis problems such as recommender systems and image inpainting. In this paper, we focus on Tucker decomposition which represents an Nth-order tensor in terms of N factor matrices and a core tensor via multilinear operations. To exploit the underlying multilinear low-rank structure in high-dimensional datasets, we propose a group-based log-sum penalty functional to place structural sparsity over the core tensor, which leads to a compact representation with smallest core tensor. The method for Tucker decomposition is developed by iteratively minimizing a surrogate function that majorizes the original objective function, which results in an iterative reweighted process. In addition, to reduce the computational complexity, an over-relaxed monotone fast iterative shrinkage-thresholding technique is adapted and embedded in the iterative reweighted process. The proposed method is able to determine the model complexity (i.e. multilinear rank) in an automatic way. Simulation results show that the proposed algorithm offers competitive performance compared with other existing algorithms.

math.NA↗

arXiv2011

A Framework For Fully-Simulatable $h$-Out-Of-$n$ Oblivious Transfer

We present a framework for fully-simulatable $h$-out-of-$n$ oblivious transfer ($OT^{n}_{h}$) with security against non-adaptive malicious adversaries. The framework costs six communication rounds and costs at most $40n$ public-key operations in computational overhead. Compared with the known protocols for fully-simulatable oblivious transfer that works in the plain mode (where there is no trusted common reference string available) and proven to be secure under standard model (where there is no random oracle available), the instantiation based on the decisional Diffie-Hellman assumption of the framework is the most efficient one, no matter seen from communication rounds or computational overhead. Our framework uses three abstract tools, i.e., perfectly binding commitment, perfectly hiding commitment and our new smooth projective hash. This allows a simple and intuitive understanding of its security. We instantiate the new smooth projective hash under the lattice assumption, the decisional Diffie-Hellman assumption, the decisional $N$-th residuosity assumption, the decisional quadratic residuosity assumption. This indeed shows that the folklore that it is technically difficult to instantiate the projective hash framework under the lattice assumption is not true. What's more, by using this lattice-based hash and lattice-based commitment scheme, we gain a concrete protocol for $OT^{n}_{h}$ which is secure against quantum algorithms.

cs.CR↗