Despite its success in many biomedical applications, Positron Emission Tomography (PET) has the drawback of typically having lower spatial resolution and higher noise respect to other medical imaging techniques. The best achievable spatial resolution in PET scanners is limited by factors such as the positron range, non-collinearity and the size of the detector crystals. In this work, we present a novel

Four-dimensional (4D) ultrasound reconstruction can greatly extend the spatial and temporal range of two-dimensional (2D) ultrasound in clinical practice. However, uneven breaths may yield a considerable motion artifact in the reconstructed time sequences of volume ultrasound. In this paper, a system with sparse respiratory signal matching is proposed to realize accurate 4D ultrasound reconstruction

In this article, we propose a method to reconstruct the total electromagnetic field in an arbitrary two-dimensional scattering environment without any prior knowledge of the incident field or the permittivities of the scatterers. However, we assume that the region between the scatterers is homogeneous and that the approximate geometry describing the environment is known. Our approach uses field measurements

We propose accurate and computationally efficient procedures to calibrate fluorescence microscopes from micro-beads images. The designed algorithms present many original features. First, they allow to estimate space-varying blurs, which is a critical feature for large fields of views. Second, we propose a novel approach for calibration: instead of describing an optical system through a single operator

There remains an important need for the development of image reconstruction methods that can produce diagnostically useful images from undersampled measurements. In magnetic resonance imaging (MRI), for example, such methods can facilitate reductions in data-acquisition times. Deep learning-based methods hold potential for learning object priors or constraints that can serve to mitigate the effects

Most X-ray tomographic reconstruction methods represent a solution as an image on a regular grid. Such representation may be inefficient for reconstructing homogeneous objects from noisy or incomplete projections. Here, we propose a mesh-based method for reconstruction and segmentation of homogeneous objects directly from sinogram data. The outcome of our proposed method consists of curves outlining

Higher-order low-rank tensor arises in many data processing applications and has attracted great interests. Inspired by low-rank approximation theory, researchers have proposed a series of effective tensor completion methods. However, most of these methods directly consider the global low-rankness of underlying tensors, which is not sufficient for a low sampling rate; in addition, the single nuclear

We present an all-in-one camera model that encompasses the architectures of most existing compressive-sensing light-field cameras, equipped with a single lens and multiple amplitude coded masks that can be placed at different positions between the lens and the sensor. The proposed model, named the equivalent multi-mask camera (EMMC) model, enables the comparison between different camera designs, e

In recent years there has been an increasing interest in compressive imaging devices that capture spectral images with high spatial and spectral resolution with as few as a single snapshot. Nonetheless, there exists an intrinsic trade-off between spatial and spectral resolution which degrades one at the expense of the other. To alleviate this, state-of-art systems have relied on multiple snapshots

Whole slide imaging (WSI) is an emerging technology for digital pathology. The accuracy and speed of autofocusing are critical for the performance of the WSI system. This paper introduces a novel technique of deep autofocusing for WSI. Instead of mechanically adjusting the focal distance on a tile-by-tile basis, we develop a deep convolutional neural network for tile-wise autofocusing to generate in-focus

Low-light imaging is a challenging task because of the excessive photon shot noise. Color imaging in low-light is even more difficult because one needs to demosaick and denoise simultaneously. Existing demosaicking algorithms are mostly designed for well-illuminated scenarios, which fail to work with low-light. Recognizing the recent development of small pixels and low read noise image sensors, we

Recently, deep learning approaches using CycleGAN have been demonstrated as a powerful unsupervised learning scheme for low-dose CT denoising. Unfortunately, one of the main limitations of the CycleGAN approach is that it requires two deep neural network generators at the training phase, although only one of them is used at the inference phase. The secondary auxiliary generator is needed to enforce

The reconstruction of synthetic aperture radar (SAR) images from phase history data is an ill-posed inverse problem which, in several lines of recent work, is solved by minimizing a cost function. Existing reconstruction methods use regularization to tackle the ill-posed nature of the imaging task. However, in general, these regularizers are either too simple to capture complex spatial patterns and

Previous studies on the forward problem of magnetic induction tomography (MIT) have used simplified Maxwell's equations which assume a constant and position-independent total current density (TCD) inside the coils (ignoring skin effect). Moreover, they assume that TCD is independent of relative position of the coils (ignoring proximity effect). This article presents an improved finite element (FE)

Optical lithography is a critical technique to fabricate nano-scale semiconductor devices by replicating the layouts of integrated circuits from the lithography mask onto the silicon wafer. As the critical dimension of integrated circuits continuously shrinks, source and mask optimization (SMO) methods are extensively used to improve the resolution and image fidelity of lithography patterning. However

Bringing deep learning techniques to electromagnetic imaging is of interest considering its great success in various fields. Deep neural nets however are known for being data hungry machines, and in many practical cases, such as electromagnetic medical imaging, there is not enough to feed them. Scarcity of data necessitates reliance on simulations to generate a sufficiently large dataset for deep learning

Non-line-of-sight (NLOS) imaging and tracking is an emerging technology that allows the shape or position of objects around corners or behind diffusers to be recovered from transient, time-of-flight measurements. However, existing NLOS approaches require the imaging system to scan a large area on a visible surface, where the indirect light paths of hidden objects are sampled. In many applications,

In order to image a distant object through atmospheric turbulence, it is necessary to correct for the phase errors that would otherwise cause rapidly varying spatial blur in a conventionally focused image. One approach to solving this problem is to illuminate an object with coherent light and to use a digital holography (DH) receiver to form a coherent measurement. The associated amplitude and phase

Magnifying left and right images by increasing focal length of optical zoom lenses is a direct way for stereoscopic zoom. However, without adjusting the baseline distance, the optical zoom may distort the three-dimensional (3D) perception. To tackle this problem, this article presents a stereoscopic zoomer that directly operates on image plane by synthesizing a virtual camera in depth direction to

A brain anomaly localization algorithm in an unsupervised machine learning (ML) framework is presented for electromagnetic brain imaging. The method is based on expected value estimation and takes the advantage of the highly symmetrical human brain. The algorithm processes signals collected from pairs of antennas that are positioned symmetrically around the head, discretizes the imaging domain into

Multi-focus image fusion (MFF) is a popular technique to generate an all-in-focus image, where all objects in the scene are sharp. However, existing methods pay little attention to defocus spread effects of the real-world multi-focus images. Consequently, most of the methods perform badly in the areas near focus map boundaries. According to the idea that each local region in the fused image should

High dynamic range (HDR) imaging is one of the biggest achievements in modern photography. Traditional solutions to HDR imaging are designed for and applied to CMOS image sensors (CIS). However, the mainstream one-micron CIS cameras today generally have a high read noise and low frame-rate. Consequently, these sensors have limited acquisition speed, making the cameras slow in the HDR mode. In this

The solution to the microwave imaging problem is often provided by systems that employ global optimization methods that search for material properties of the selected investigation domain. A novel method for the solution of the microwave imaging problem based on the optimization with a variable number of dimensions is introduced in this article. Shapes of scatterers with an arbitrary complexity can

Recently, deep-learning based methods have been widely used for computed tomography (CT) reconstruction. However, most of these methods need extra steps to convert the sinogrmas into CT images and so their networks are not end-to-end. In this paper, we propose an end-to-end deep network for CT image reconstruction, which directly maps sparse sinogramss to CT images. Our network has three cascaded blocks

Inverse scattering is the process of estimating the spatial distribution of the scattering potential of an object by measuring the scattered wavefields around it. In this article, we consider reflection tomography of high contrast objects that commonly occurs in ground-penetrating radar, exploration geophysics, terahertz imaging, ultrasound, and electron microscopy. Unlike conventional transmission

Three-dimensional reconstruction of tomograms from optical projection microscopy is confronted with several drawbacks. In this paper we employ iterative reconstruction algorithms to avoid streak artefacts in the reconstruction and explore possible ways to optimize two parameters of the algorithms, i.e., iteration number and initialization, in order to improve the reconstruction performance. As benchmarks

Densely-sampled light field (LF) image is drawing increased attention for its wide applications in 3D reconstruction, digital refocusing, depth estimation, and virtual/augmented reality, et al. In order to reconstruct a densely-sampled LF with high angular resolution, many computational methods have been proposed. However, most existing methods consider LF angular reconstruction based on neighboring

The advent of single molecule microscopy has revolutionized biological investigations by providing a powerful tool for the study of intercellular and intracellular trafficking processes of protein molecules which was not available before through conventional microscopy. In practice, pixelated detectors are used to acquire the images of fluorescently labeled objects moving in cellular environments.

Passive non-line-of-sight imaging methods are often faster and stealthier than their active counterparts, requiring less complex and costly equipment. However, many of these methods exploit motion of an occluder or the hidden scene, or require knowledge or calibration of complicated occluders. The edge of a wall is a known and ubiquitous occluding structure that may be used as an aperture to image

This article proposes a novel approach to regularize the ill-posed and non-linear blind image deconvolution (blind deblurring) using deep generative networks as priors. We employ two separate pretrained generative networks — given lower-dimensional Gaussian vectors as input, one of the generative models samples from the distribution of sharp images, while the other from that of the blur kernels. To

Recently, deep learning-based compressive imaging (DCI) has surpassed conventional compressive imaging in reconstruction quality and running speed. While multi-scale sampling has shown superior performance over single-scale, research in DCI has been limited to single-scale sampling. Despite training with single-scale images, DCI tends to favor low-frequency components similar to conventional multi-scale

Various natural and artificial materials are anisotropic. The inverse scattering problem of anisotropic scatterers is widely involved in oil detection, nondestructive evaluation of composite materials and microscopic imaging of biological tissue. In this contribution, the two-dimensional inverse scattering problem of biaxial anisotropic scatterers illuminated by the TE-polarized incident wave is investigated

Incremental sampling can be applied in scientific imaging techniques whenever the measurements are taken incrementally, i.e., one pixel position is measured at a time. It can be used to reduce the measurement time as well as the dose impinging onto a specimen. For incremental sampling, the choice of the sampling pattern plays a major role in order to achieve a high reconstruction quality. Besides using

Magnetic field inhomogeneity estimation is important in some types of magnetic resonance imaging (MRI), including field-corrected reconstruction for fast MRI with long readout times, and chemical shift based water-fat imaging. Regularized field map estimation methods that account for phase wrapping and noise involve nonconvex cost functions that require iterative algorithms. Most existing minimization

In this work we investigate the practicality of stochastic gradient descent and its variants with variance-reduction techniques in imaging inverse problems. Such algorithms have been shown in the large-scale optimization and machine learning literature to have optimal complexity in theory, and to provide great improvement empirically over the deterministic gradient methods. However, in some tasks such

Though deep learning based spectral super-resolution (SSR) methods have state-of-the-art performances, most previous deep spectral super-resolution approaches require extensive paired RGB images and hyperspectral images (HSIs) for well-fitting learning. However, in real cases, the cost of generating such paired images is too prohibitive to collect sufficient training samples. To solve this problem

Coherent imaging methods like synthetic aperture radar (SAR) are subject to speckle, and the suppression of this noise-like quality is often considered a prerequisite to image interpretation. Likewise, circumstances such as frequency jamming or system multiplexing produce gaps in the data and corresponding image artifacts, which further impact the utility of resulting imagery and induce correlation

Ground based long-range passive imaging systems often suffer from degraded image quality due to a turbulent atmosphere. While methods exist for removing such turbulent distortions, many are limited to static sequences which cannot be extended to dynamic scenes. In addition, the physics of the turbulence is often not integrated into the image reconstruction algorithms, making the physics foundations

Critical aspects of computational imaging systems, such as experimental design and image priors, can be optimized through deep networks formed by the unrolled iterations of classical physics-based reconstructions. Termed physics-based networks, they incorporate both the known physics of the system via its forward model, and the power of deep learning via data-driven training. However, for realistic

In Magnetic Particle Imaging (MPI), the system matrix plays an important role, as it encodes the relationship between particle concentration and the measured signal. Its acquisition requires a time-consuming calibration scan, whereas its size leads to a high memory-demand. Both of these aspects can be limiting factors in practice. In order to reduce measurement time, compressed sensing exploits the

Perfusion computed tomography (PCT) is critical in detecting cerebral ischemic lesions. PCT examination with low-dose scans can effectively reduce radiation exposure to patients at the cost of degraded images with severe noise, and artifacts. Tensor total variation (TTV) models are powerful tools that can encode the regional continuous structures underlying a PCT object. In a TTV model, the sparsity

Hyperspectral imaging has become a significant source of valuable data for astronomers over the past decades. Current instrumental and observing time constraints allow direct acquisition of multispectral images, with high spatial but low spectral resolution, and hyperspectral images, with low spatial but high spectral resolution. To enhance scientific interpretation of the data, we propose a data fusion

The use of microwave tomography (MWT) in an industrial drying process is demonstrated in this feasibility study with synthetic measurement data. The studied imaging modality is applied to estimate the moisture content distribution in a polymer foam during the microwave drying process. Such moisture information is crucial in developing control strategies for controlling the microwave power for selective

Recovering a high-quality image from noisy indirect measurements is an important problem with many applications. For such inverse problems, supervised deep convolutional neural network (CNN)-based denoising methods have shown strong results, but the success of these supervised methods critically depends on the availability of a high-quality training dataset of similar measurements. For image denoising

As a non-invasive and radiation-free imaging modality, electrical impedance tomography (EIT) has attracted much attention in the field of industrial measurement. However, image reconstruction with EIT is a non-linear and ill-posed inverse problem, causing it to suffer from low spatial resolution and high noise sensitivity. To overcome this problem, a point-constrained framework is proposed to guide

For compressed sensing magnetic resonance imaging (CS-MRI) that utilize sparse representations, the regularization parameter establishes a trade-off between sparsity and data fidelity. While convergence to the desired solution is slow for mean squared error (MSE) optimal constant regularization, continuation using decreasing parameter values enables faster convergence. To derive an explicit rule for

The range frequency autocorrelation function (RFAF) based algorithm is proposed for radar target detection and motion parameter estimation in our previous work. In the RFAF-based method, the symmetric autocorrelation function (SAF) is constructed with respect to the range frequency, and three dimensional (slow time, range frequency, and shift frequency) energy accumulation can be completed coherently

In conventional ultrasound (US) imaging, it is common to transmit several focused beams at multiple locations to generate a multi-focus image with constant lateral resolution throughout the image. However, this method comes at the expense of a loss in temporal resolution, which is important in applications requiring both high-frame rate and constant lateral resolution. Moreover, relative motions of

Recently, deep learning approaches for accelerated MRI have been extensively studied thanks to their high performance reconstruction in spite of significantly reduced run-time complexity. These neural networks are usually trained in a supervised manner, so matched pairs of subsampled, and fully sampled $k$ -space data are required. Unfortunately, it is often difficult to acquire matched fully sampled

Discrete delta functions define the limits of attainable spatial resolution for all imaging systems. Here we construct broad, multi-dimensional discrete functions that replicate closely the action of a Dirac delta function for convolution under aperiodic boundary conditions. These arrays spread the energy of a sharp probe beam to simultaneously sample multiple points across the volume of a large object

Recently, deep learning becomes the main focus of machine learning research and has greatly impacted many important fields. However, deep learning is criticized for lack of interpretability. As a successful unsupervised model in deep learning, the autoencoder embraces a wide spectrum of applications, yet it suffers from the model opaqueness as well. In this article, we propose a new type of convolutional

Although lowering X-ray radiation helps reduce the risk of cancer in patients, low-dose computed tomography (LDCT) technology usually leads to poor image quality, such as amplified mottle noise and streak artifacts, which severely impact the diagnostic results. To improve diagnostic performance, we propose an algorithm based on a cycle-consistent generative adversarial network (CycleGAN) to suppress

The principle of quantitative acoustic microscopy (QAM) is to form two-dimensional (2D) acoustic parameter maps from a collection of radiofrequency (RF) signals acquired by raster scanning a biological sample. Despite their relatively simple structure consisting of two main reflections, RF signals are currently sampled at very high frequencies, e.g. , at 2.5 GHz for QAM system employing a single-element

It is possible to generate stereo high dynamic range (HDR) images/videos by using a pair of cameras with different exposure parameters. In this article, a learning-based stereo HDR imaging (SHDRI) method with three modules is proposed. In the proposed method, we construct three convolutional neural network (CNN) modules that perform specific tasks, including exposure calibration CNN (EC-CNN) module

Hyperspectral recovery using RGB images has recently attracted considerable attention in many imaging and computer vision applications because of its ability to equip a low cost tool in acquiring spectral signatures of natural scenes. Current methods of recovering hyperspectral information via RGB measurements may fail for objects sharing similar RGB features. In this paper, we introduce a novel framework

The modeling of phenomenological structure is a crucial aspect in inverse imaging problems. One emerging modeling tool in computer vision is the optimal transport framework. Its ability to model geometric displacements across an image's support gives it attractive qualities similar to optical flow methods that are effective at capturing visual motion, but are restricted to operate in significantly

Fusion based hyperspectral image (HSI) super-resolution method, which obtains a spatially high-resolution (HR) HSI by fusing a low-resolution (LR) HSI and an HR conventional image, has been a prevalent method for HSI super-resolution. One effective fusion based method is to cast HSI super-resolution into a unified optimization problem, where handcrafted priors such as sparse prior or low rank prior

A full 360 $^\circ$ × 180 $^\circ$ image provides an unlimited field of view (FOV) and an immersive experience for the users without any loss of information of the surrounding. In this study, a deep learning based approach is proposed to synthesize a 360 $^\circ$ image from a sparse set of images captured with a limited FOV. The proposed network consists of a cascade of the FOV estimation network and

A multistage algorithm for quantitative microwave breast imaging is presented which utilizes the eigenfunction-based reconstruction of the complex-valued permittivity as prior information. The eigenfunction-based reconstruction is obtained from a single-frequency non-iterative microwave inversion technique that uses the eigenfunctions of the Helmholtz operator, in a resonant conductive enclosure, as

Mask-based lensless cameras replace the lens of a conventional camera with a custom mask. These cameras can potentially be very thin and even flexible. Recently, it has been demonstrated that such mask-based cameras can recover light intensity and depth information of a scene. Existing depth recovery algorithms either assume that the scene consists of a small number of depth planes or solve a sparse