Three-dimensional contrast source inversion-electrical properties tomography (3-D CSI-EPT) is an iterative reconstruction method that estimates the electrical properties of tissue from transmit field magnetic resonance data. However, in order to bring 3-D CSI-EPT into practice for complex tissue structures and to understand the origin and effect of errors, insight in the sensitivities of reconstruction

Structured illumination microscopy (SIM) enhances spatial resolution by projecting sinusoidal patterns with various orientations and lateral phase shifts. Here, we report a framework, termed DNN-SIM, powered by a deep neural network that learns the physical relationship between images with different lateral phase shifts. This approach captures one image per sinusoidal pattern orientation and infers

Defocus blur often degrades the performance of image understanding, such as object recognition and image segmentation. Restoring an all-in-focus image from its defocused version is highly beneficial to visual information processing and many photographic applications, despite being a severely ill-posed problem. We propose a novel convolutional neural network architecture AIFNet for removing spatially-varying

In this work, we introduce a learning-based method to achieve high-quality reconstructions for inverse scattering problems (ISPs). Particularly, the proposed method decouples the full-wave reconstruction model into two steps, including coarse imaging of dielectric profiles by the back-propagation scheme, and a resolution enhancement of coarse results as an image-to-image translation task solved by

Deep neural networks have been applied successfully to a wide variety of inverse problems arising in computational imaging. These networks are typically trained using a forward model that describes the measurement process to be inverted, which is often incorporated directly into the network itself. However, these approaches are sensitive to changes in the forward model: if at test time the forward

Low-dose CT (LDCT) imaging is preferred in many applications to reduce the object's exposure to X-ray radiation. In recent years, one promising approach to image reconstruction in LDCT is the so-called optimization-unrolling-based deep learning approach, which replaces pre-defined image prior by learnable adaptive prior in some model-based iterative image reconstruction scheme (MBIR). While it is known

An existing forward-backward time-stepping (FBTS) time-domain quantitative imaging algorithm is augmented with a discontinuous Galerkin method (DGM) forward solver. The resulting DGM-FBTS imaging algorithm is capable of solving the electromagnetic inverse scattering problem using high-order expansions of the fields and unknown target constitutives, decoupling the solution from the unstructured grid

We demonstrate a high-throughput computation-efficient snapshot coherence tomographic imaging method by combining interferometric coding and compressive sampling. We first encode the depth distribution of a three-dimensional (3D) object into the spectrum of a light field, using the principle of optical coherence tomography (OCT), i.e. , through a Michaelson interferometer, which generates an intermediate

Image restoration techniques generally use intrinsic correlations of image contents to reduce the uncertainty of the unknown signal and estimate the latent ground truth. Local and non-local correlation are the two major kinds of correlations utilized. They are different sources of correlations reflecting connections between different image data, but such a difference is not taken into consideration

Deep unfolding networks have recently gained popularity for solving imaging inverse problems. However, the computational and memory complexity of data-consistency layers within traditional deep unfolding networks scales with the number of measurements, limiting their applicability to large-scale imaging inverse problems. We propose SGD-Net as a new methodology for improving the efficiency of deep unfolding

The Computed Tomography Imaging Spectrometer (CTIS) permits a snapshot acquisition of a hyperspectral cube, through the creation of an image of indirect measurements which is then traditionally used for reconstruction of the cube. This reconstruction step is time-consuming and only yields an approximation of the original cube. Following a compressed learning framework, we compare the performance of

In cell and molecular biology, the fusion of green fluorescent protein (GFP) and phase contrast (PC) images aims to generate a composite image, which can simultaneously display the functional information in the GFP image related to the molecular distribution of biological living cells and the structural information in the PC image such as nucleus and mitochondria. In this paper, we propose a detail

We introduce a new algorithm for complex image reconstruction with separate regularization of the image magnitude and phase. This optimization problem is interesting in many different image reconstruction contexts, although is nonconvex and can be difficult to solve. In this work, we first describe a novel implementation of the previous proximal alternating linearized minimization (PALM) algorithm

Given a spectral library, sparse unmixing aims to estimate the fractional proportions in each pixel of a hyperspectral image scene. However, the ever-growing dimensionality of spectral dictionaries strongly limits the performance of sparse unmixing algorithms. In this study, we propose a novel dictionary pruning (DP) approach to improve the performance of sparse unmixing algorithms, making them more

Spectral imaging is a fundamental diagnostic technique with widespread application. Conventional spectral imaging approaches have intrinsic limitations on spatial and spectral resolutions due to the physical components they rely on. To overcome these physical limitations, in this paper, we develop a novel multi-spectral imaging modality that enables higher spatial and spectral resolutions. In the developed

The identification of parameters of spatially variant blurs given a clean image and its blurry noisy version is a challenging inverse problem of interest in many application fields, such as biological microscopy and astronomical imaging. In this paper, we consider a parametric model of the blur and introduce an 1D state-space model to describe the statistical dependence among the neighboring kernels

Deep Learning frameworks are gaining increased popularity in image processing tasks such as computational hyperspectral imaging. While these frameworks achieve state-of-the-art results in terms of reconstruction quality and run time, they often require massive databases of hyperspectral cubes for training the reconstruction algorithms. Unfortunately, such databases are usually hard to acquire due to

In a focused ion beam (FIB) microscope, source particles interact with a small volume of a sample to generate secondary electrons that are detected, pixel by pixel, to produce a micrograph. Randomness of the number of incident particles causes excess variation in the micrograph, beyond the variation in the underlying particle–sample interaction. We recently demonstrated that joint processing of multiple

Camera motion deblurring is an important low-level vision task for achieving better imaging quality. When a scene has outliers such as saturated pixels, the captured blurred image becomes more difficult to restore. In this paper, we propose a novel method to handle camera motion blur with outliers. We first propose an edge-aware scale-recurrent network (EASRN) to conduct deblurring. EASRN has a separate

Compressive light field photography enables light field acquisition using a single sensor by utilizing a color coded mask. This approach is very cost effective since consumer-level digital cameras can be turned into light field cameras by simply placing a coded mask between the sensor and the aperture plane. This paper describes a deep learning architecture for compressive light field acquisition using

Inverse problems spanning four or more dimensions such as space, time andother independent parameters have become increasingly important. State-of-the-art 4D reconstruction methods use model based iterative reconstruction (MBIR), but depend critically on the quality of the prior modeling. Recently, plug-and-play (PnP) methods have been shown to be an effective way to incorporate advanced prior models

Dual-energy computed tomography (DECT) is of great clinical significance because of its material identification and quantification capacity. Although DECT measures attenuation using two different spectra, the anatomical structure of the low- and high-energy CT images are consistent with each other and the images are also correlated in the energy domain, resulting in significant information redundancy

Compressive sensing (CS) applied to through-the-wall radar imaging (TWRI) exploits the group sparsity of a target scene in the presence of wall clutter and multipath from enclosed structures towards achieving high-resolution imaging with limited measurements. In this paper, we extend the CS-based TWRI to include the clustering structure property of the target within a hierarchical Bayesian framework

Design of a residual block that provides a rich set of features while requiring only small numbers of parameters and operations is crucial for the task of single image super resolution. This is especially important in applications with limited power and storage capacity. In this paper, a new multi-domain residual block is proposed in order to generate richer set of features for the task of image super

We consider a variational model for single-image super-resolution based on the assumption that the gradient of the target image is sparse. We enforce this assumption by considering both an isotropic and an anisotropic $\ell ^0$ regularisation on the image gradient combined with a quadratic data fidelity, similarly as studied in [1] for signal recovery problems. For the numerical realisation of the

Monocular depth estimation has been carried out with convolutional neural networks (CNNs). However, vast quantities of ground truth depth data are required as a supervising signal. Recently, self-supervised learning is explored for monocular depth estimation, which uses the minor loss of image reconstruction, rather than depth information, as the supervising signal in the training phase. However, the

With the goal of persistent surveillance over a scene of interest, this paper proposes an approach for joint imaging and trajectory extraction of multiple moving objects, using circular video-SAR (ViSAR) mode. Unlike stationary SAR imaging where the phase perturbation of the received signal arises from the platform motion, the moving targets impose additional phase errors, contributing to defocusing

The single-scatter approximation is fundamental in many tomographic imaging problems including x-ray scatter imaging and optical scatter imaging for certain media. In all cases, noisy measurements are affected by both local scatter events and nonlocal attenuation. Prior works focus on reconstructing one of two images: scatter density or total attenuation. However, both images are media specific and

A standard model for image reconstruction involves the minimization of a data-fidelity term along with a regularizer, where the optimization is performed using proximal algorithms such as ISTA and ADMM. In plug-and-play (PnP) regularization, the proximal operator (associated with the regularizer) in ISTA and ADMM is replaced by a powerful image denoiser. Although PnP regularization works surprisingly

Joint inversion of microwave and ultrasonic data for breast imaging is investigated with deterministic edge-preserving regularization by introducing auxiliary variables indicating whether a pixel is on an edge or not. These edge markers are shared by dielectric and acoustic parameters and are the link to fusion between modalities. They can be jointly optimized from the last parameter profiles of microwave

Image domain prior models have been shown to improve the quality of reconstructed images, especially when data are limited. Pre-processing of raw data, through the implicit or explicit inclusion of data domain priors have separately also shown utility in improving reconstructions. In this work, a principled approach is presented allowing the unified integration of both data and image domain priors

In this paper, a novel self-supervised mask-optimization model, termed as SMFuse, is proposed for multi-focus image fusion. In our model, given two source images, a fully end-to-end Mask-Generator is trained to directly generate the binary mask without requiring any patch operation or postprocessing through self-supervised learning. On the one hand, based on the principle of repeated blur, we design

Gabor holography is an amazingly simple and effective approach for three-dimensional (3D) imaging. However, it suffers from a DC term, twin-image entanglement, and defocus noise. The conventional approach for solving this problem is either using an off-axis setup, or compressive holography. The former sacrifices simplicity, and the latter is computationally demanding and time-consuming. To cope with

Resolution level and reconstruction quality in nano-computed tomography (nano-CT) are in part limited by the stability of microscopes, because the magnitude of mechanical vibrations during scanning becomes comparable to the imaging resolution, and the ability of the samples to resist radiation induced deformations during data acquisition. In such cases, there is no incentive in recovering the sample

Most digital cameras use specialized autofocus sensors, such as phase detection, lidar or ultrasound, to directly measure focus state. However, such sensors increase cost and complexity without directly optimizing final image quality. This paper proposes a new pipeline for image-based autofocus and shows that neural image analysis finds focus 5-10x faster than traditional contrast enhancement. We achieve

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

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

In CT images, tissue structures and lesion changes illustrate evident non-local self-similarity and regionally constant properties. The low-rank model and the learnable sparse representation model are powerful tools that can respectively encode the correlations among non-local similar patches and the sparsity in a local transformed subspace about the underlying CT image. Existing Model-Based Iterative

We propose original, accurate and computationally efficient procedures to calibrate fluorescence microscopes from micro-beads images. The designed algorithms present many singularities. 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

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

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,

Model-based learned iterative reconstruction methods have recently been shown to outperform classical reconstruction algorithms. Applicability of these methods to large scale inverse problems is however limited by the available memory for training and extensive training times, the latter due to computationally expensive forward models. As a possible solution to these restrictions we propose a multi-scale

Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.

Several recent studies on compressive video sensing realized scene capture beyond the fundamental trade-off limit between spatial resolution and temporal resolution using random space-time sampling. However, most of these studies obtained results for higher-frame-rate video that was produced in simulation experiments or using an optically simulated random sampling camera, because there are currently

Model-Based Image Reconstruction (MBIR) methods significantly enhance the quality of computed tomographic (CT) reconstructions relative to analytical techniques, but are limited by high computational cost. In this paper, we propose a multi-agent consensus equilibrium (MACE) algorithm for distributing both the computation and memory of MBIR reconstruction across a large number of parallel nodes. In

Image demosaicing and super-resolution are two important tasks in color imaging pipeline. So far they have been mostly independently studied in the open literature of deep learning; little is known about the potential benefit of formulating a joint demosaicing and super-resolution (JDSR) problem. In this paper, we propose an end-to-end optimization solution to the JDSR problem and demonstrate its practical

Model-based learned iterative reconstruction methods have recently been shown to outperform classical reconstruction algorithms. Applicability of these methods to large scale inverse problems is however limited by the available memory for training and extensive training times, the latter due to computationally expensive forward models. As a possible solution to these restrictions we propose a multi-scale