Convolutional neural networks have recently demonstrated high-quality reconstruction for single image super-resolution. However, existing methods often require a large number of network parameters ...and entail heavy computational loads at runtime for generating high-accuracy super-resolution results. In this paper, we propose the deep Laplacian Pyramid Super-Resolution Network for fast and accurate image super-resolution. The proposed network progressively reconstructs the sub-band residuals of high-resolution images at multiple pyramid levels. In contrast to existing methods that involve the bicubic interpolation for pre-processing (which results in large feature maps), the proposed method directly extracts features from the low-resolution input space and thereby entails low computational loads. We train the proposed network with deep supervision using the robust Charbonnier loss functions and achieve high-quality image reconstruction. Furthermore, we utilize the recursive layers to share parameters across as well as within pyramid levels, and thus drastically reduce the number of parameters. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of run-time and image quality.
The sudden outbreak of 2019 novel coronavirus (2019-nCoV, later named SARS-CoV-2) in Wuhan, China, which rapidly grew into a global pandemic, marked the third introduction of a virulent coronavirus ...into the human society, affecting not only the healthcare system, but also the global economy. Although our understanding of coronaviruses has undergone a huge leap after two precedents, the effective approaches to treatment and epidemiological control are still lacking. In this article, we present a succinct overview of the epidemiology, clinical features, and molecular characteristics of SARS-CoV-2. We summarize the current epidemiological and clinical data from the initial Wuhan studies, and emphasize several features of SARS-CoV-2, which differentiate it from SARS-CoV and Middle East respiratory syndrome coronavirus (MERS-CoV), such as high variability of disease presentation. We systematize the current clinical trials that have been rapidly initiated after the outbreak of COVID-19 pandemic. Whereas the trials on SARS-CoV-2 genome-based specific vaccines and therapeutic antibodies are currently being tested, this solution is more long-term, as they require thorough testing of their safety. On the other hand, the repurposing of the existing therapeutic agents previously designed for other virus infections and pathologies happens to be the only practical approach as a rapid response measure to the emergent pandemic, as most of these agents have already been tested for their safety. These agents can be divided into two broad categories, those that can directly target the virus replication cycle, and those based on immunotherapy approaches either aimed to boost innate antiviral immune responses or alleviate damage induced by dysregulated inflammatory responses. The initial clinical studies revealed the promising therapeutic potential of several of such drugs, including
, a broad-spectrum antiviral drug that interferes with the viral replication, and
, the repurposed antimalarial drug that interferes with the virus endosomal entry pathway. We speculate that the current pandemic emergency will be a trigger for more systematic drug repurposing design approaches based on big data analysis.
Motion estimation (ME) and motion compensation (MC) have been widely used for classical video frame interpolation systems over the past decades. Recently, a number of data-driven frame interpolation ...methods based on convolutional neural networks have been proposed. However, existing learning based methods typically estimate either flow or compensation kernels, thereby limiting performance on both computational efficiency and interpolation accuracy. In this work, we propose a motion estimation and compensation driven neural network for video frame interpolation. A novel adaptive warping layer is developed to integrate both optical flow and interpolation kernels to synthesize target frame pixels. This layer is fully differentiable such that both the flow and kernel estimation networks can be optimized jointly. The proposed model benefits from the advantages of motion estimation and compensation methods without using hand-crafted features. Compared to existing methods, our approach is computationally efficient and able to generate more visually appealing results. Furthermore, the proposed MEMC-Net architecture can be seamlessly adapted to several video enhancement tasks, e.g., super-resolution, denoising, and deblocking. Extensive quantitative and qualitative evaluations demonstrate that the proposed method performs favorably against the state-of-the-art video frame interpolation and enhancement algorithms on a wide range of datasets.
Neuromorphic computing has been extensively studied to mimic the brain functions of perception, learning, and memory because it may overcome the von Neumann bottleneck. Here, with the light‐induced ...bidirectional photoresponse of the proposed Bi2O2Se/graphene hybrid structure, its potential use in next‐generation neuromorphic hardware is examined with three distinct optoelectronic applications. First, a photodetector based on a Bi2O2Se/graphene hybrid structure presents positive and negative photoresponsibility of 88 and −110 A W−1 achieved by the excitation of visible wavelength and ultraviolet wavelength light at intensities of 1.2 and 0.3 mW cm−2, respectively. Second, this unique photoresponse contributes to the realization of all optically stimulated long‐term potentiation or long‐term depression to mimic synaptic short‐term plasticity and long‐term plasticity, which are attributed to the combined effect of photoconductivity, bolometric, and photoinduced desorption. Third, the devices are applied to perform digital logic functions, such as “AND” and “OR,” using full light modulation. The proposed Bi2O2Se/graphene‐based optoelectronic device represents an innovative and efficient building block for the development of future multifunctional artificial neuromorphic systems.
All‐optical synapses based on a 2D Bi2O2Se/graphene hybrid structure can yield positive photoresponses under visible light and negative photoresponses under 365 nm illumination without the extra electrical control. Contributing to this unique optoelectronic property, the single two‐terminal device with fully optical operations is demonstrated for the photodetector, optoelectronic synapses, and optical logic functions.
We present an effective blind image deblurring method based on a data-driven discriminative prior. Our work is motivated by the fact that a good image prior should favor sharp images over blurred ...ones. In this work, we formulate the image prior as a binary classifier using a deep convolutional neural network. The learned prior is able to distinguish whether an input image is sharp or not. Embedded into the maximum a posterior framework, it helps blind deblurring in various scenarios, including natural, face, text, and low-illumination images, as well as non-uniform deblurring. However, it is difficult to optimize the deblurring method with the learned image prior as it involves a non-linear neural network. In this work, we develop an efficient numerical approach based on the half-quadratic splitting method and gradient descent algorithm to optimize the proposed model. Furthermore, we extend the proposed model to handle image dehazing. Both qualitative and quantitative experimental results show that our method performs favorably against the state-of-the-art algorithms as well as domain-specific image deblurring approaches.
The controlled size and surface treatment of magnetic nanoparticles (NPs) make one‐stage combination feasible for enhanced magnetic resonance imaging (MRI) contrast and effective hyperthermia. ...However, superparamagnetic behavior, essential for avoiding the aggregation of magnetic NPs, substantially limits their performance. Here, a superparamagnetic core–shell structure is developed, which promotes the formation of vortex‐like intraparticle magnetization structures in the remanent state, leading to reduced dipolar interactions between two neighboring NPs, while during an MRI scan, the presence of a DC magnetic field induces the formation of NP chains, introducing increased local inhomogeneous dipole fields that enhance relaxivity. The core–shell NPs also reveal an augmented anisotropy, due to exchange coupling to the high anisotropy core, which enhances the specific absorption rate. This in vivo tumor study reveals that the tumor cells can be clearly diagnosed during an MRI scan and the tumor size is substantially reduced through hyperthermia therapy by using the same FePt@iron oxide nanoparticles, realizing the concept of theranostics.
The magnetic interaction among nanoparticles is demonstrated to be able to be manipulated by a core–shell structure to enhance the resolution of magnetic resonance imaging and the specific absorption rate of nanoparticles. It is rather remarkable that the magnetic configuration of the assembly shape can be controlled under a magnetic field toimprove the relaxivity of the contrast agent and the effectiveness of hyperthermia, making theranostics feasible.
Deep Image Deblurring: A Survey Zhang, Kaihao; Ren, Wenqi; Luo, Wenhan ...
International journal of computer vision,
09/2022, Volume:
130, Issue:
9
Journal Article
Peer reviewed
Image deblurring is a classic problem in low-level computer vision with the aim to recover a sharp image from a blurred input image. Advances in deep learning have led to significant progress in ...solving this problem, and a large number of deblurring networks have been proposed. This paper presents a comprehensive and timely survey of recently published deep-learning based image deblurring approaches, aiming to serve the community as a useful literature review. We start by discussing common causes of image blur, introduce benchmark datasets and performance metrics, and summarize different problem formulations. Next, we present a taxonomy of methods using convolutional neural networks (CNN) based on architecture, loss function, and application, offering a detailed review and comparison. In addition, we discuss some domain-specific deblurring applications including face images, text, and stereo image pairs. We conclude by discussing key challenges and future research directions.
Convolutional neural networks have recently demonstrated high-quality reconstruction for single-image super-resolution. In this paper, we propose the Laplacian Pyramid Super-Resolution Network ...(LapSRN) to progressively reconstruct the sub-band residuals of high-resolution images. At each pyramid level, our model takes coarse-resolution feature maps as input, predicts the high-frequency residuals, and uses transposed convolutions for upsampling to the finer level. Our method does not require the bicubic interpolation as the pre-processing step and thus dramatically reduces the computational complexity. We train the proposed LapSRN with deep supervision using a robust Charbonnier loss function and achieve high-quality reconstruction. Furthermore, our network generates multi-scale predictions in one feed-forward pass through the progressive reconstruction, thereby facilitates resource-aware applications. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of speed and accuracy.
Dynamic scene blur is usually caused by object motion, depth variation as well as camera shake. Most existing methods usually solve this problem using image segmentation or fully end-to-end trainable ...deep convolutional neural networks by considering different object motions or camera shakes. However, these algorithms are less effective when there exist depth variations. In this work, we propose a deep neural convolutional network that exploits the depth map for dynamic scene deblurring. Given a blurred image, we first extract the depth map and adopt a depth refinement network to restore the edges and structure in the depth map. To effectively exploit the depth map, we adopt the spatial feature transform layer to extract depth features and fuse with the image features through scaling and shifting. Our image deblurring network thus learns to restore a clear image under the guidance of the depth map. With substantial experiments and analysis, we show that the depth information is crucial to the performance of the proposed model. Finally, extensive quantitative and qualitative evaluations demonstrate that the proposed model performs favorably against the state-of-the-art dynamic scene deblurring approaches as well as conventional depth-based deblurring algorithms.
Several Zika virus (ZIKV) vaccine candidates have recently been described which use inactivated whole virus, DNA or RNA that express the virus' Envelope (E) glycoprotein as the antigen. These were ...successful in stimulating production of virus-targeted antibodies that protected animals against ZIKV challenges, but their use potentially will predispose vaccinated individuals to infection by the related Dengue virus (DENV). We have devised a virus like particle (VLP) carrier based on the hepatitis B core antigen (HBcAg) that displays the ZIKV E protein domain III (zDIII), and shown that it can be produced quickly and easily purified in large quantities from Nicotiana benthamiana plants. HBcAg-zDIII VLPs are shown to be highly immunogenic, as two doses elicited potent humoral and cellular responses in mice that exceed the threshold correlated with protective immunity against multiple strains of Zika virus. Notably, HBcAg-zDIII VLPs-elicited antibodies did not enhance the infection of DENV in Fc gamma receptor-expressing cells, offsetting the concern of ZIKV vaccines inducing cross-reactive antibodies and sensitizing people to subsequent DENV infection. Thus, our zDIII-based vaccine offers improved safety and lower cost production than other current alternatives, with equivalent effectiveness.
PDF
