Single-shot inline holography using a physics-aware diffusion model.

Among holographic imaging configurations, inline holography excels in its compact design and portability, making it the preferred choice for on-site or field applications with unique imaging requirements. However, effectively holographic reconstruction from a single-shot measurement remains a challenge. While several approaches have been proposed, our novel unsupervised algorithm, the physics-aware diffusion model for digital holographic reconstruction (PadDH), offers distinct advantages. By seamlessly integrating physical information with a pre-trained diffusion model, PadDH overcomes the need for a holographic training dataset and significantly reduces the number of parameters involved. Through comprehensive experiments using both synthetic and experimental data, we validate the capabilities of PadDH in reducing twin-image contamination and generating high-quality reconstructions. Our work represents significant advancements in unsupervised holographic imaging by harnessing the full potential of the pre-trained diffusion prior.

Neuromorphic Imaging With Joint Image Deblurring and Event Denoising.

Neuromorphic imaging reacts to per-pixel brightness changes of a dynamic scene with high temporal precision and responds with asynchronous streaming events as a result. It also often supports a simultaneous output of an intensity image. Nevertheless, the raw events typically involve a large amount of noise due to the high sensitivity of the sensor, while capturing fast-moving objects at low frame rates results in blurry images. These deficiencies significantly degrade human observation and machine processing. Fortunately, the two information sources are inherently complementary - events with microsecond-level temporal resolution, which are triggered by the edges of objects recorded in a latent sharp image, can supply rich motion details missing from the blurry one. In this work, we bring the two types of data together and introduce a simple yet effective unifying algorithm to jointly reconstruct blur-free images and noise-robust events in an iterative coarse-to-fine fashion. Specifically, an event-regularized prior offers precise high-frequency structures and dynamic features for blind deblurring, while image gradients serve as a kind of faithful supervision in regulating neuromorphic noise removal. Comprehensively evaluated on real and synthetic samples, such a synergy delivers superior reconstruction quality for both images with severe motion blur and raw event streams with a storm of noise, and also exhibits greater robustness to challenging realistic scenarios such as varying levels of illumination, contrast and motion magnitude. Meanwhile, it can be driven by much fewer events and holds a competitive edge at computational time overhead, rendering itself preferable as available computing resources are limited. Our solution gives impetus to the improvement of both sensing data and paves the way for highly accurate neuromorphic reasoning and analysis.

High-throughput microplastic assessment using polarization holographic imaging.

Microplastic (MP) pollution has emerged as a global environmental concern due to its ubiquity and harmful impacts on ecosystems and human health. MP assessment has therefore become increasingly necessary and common in environmental and experimental samples. Microscopy and spectroscopy are widely employed for the physical and chemical characterization of MPs. However, these analytical methods often require time-consuming pretreatments of samples or expensive instrumentation. In this work, we develop a portable and cost-effective polarization holographic imaging system that prominently incorporates deep learning techniques, enabling efficient, high-throughput detection and dynamic analysis of MPs in aqueous environments. The integration enhances the identification and classification of MPs, eliminating the need for extensive sample preparation. The system simultaneously captures holographic interference patterns and polarization states, allowing for multimodal information acquisition to facilitate rapid MP detection. The characteristics of light waves are registered, and birefringence features are leveraged to classify the material composition and structures of MPs. Furthermore, the system automates real-time counting and morphological measurements of various materials, including MP sheets and additional natural substances. This innovative approach significantly improves the dynamic monitoring of MPs and provides valuable information for their effective filtration and management.

On the use of deep learning for phase recovery.

Phase recovery (PR) refers to calculating the phase of the light field from its intensity measurements. As exemplified from quantitative phase imaging and coherent diffraction imaging to adaptive optics, PR is essential for reconstructing the refractive index distribution or topography of an object and correcting the aberration of an imaging system. In recent years, deep learning (DL), often implemented through deep neural networks, has provided unprecedented support for computational imaging, leading to more efficient solutions for various PR problems. In this review, we first briefly introduce conventional methods for PR. Then, we review how DL provides support for PR from the following three stages, namely, pre-processing, in-processing, and post-processing. We also review how DL is used in phase image processing. Finally, we summarize the work in DL for PR and provide an outlook on how to better use DL to improve the reliability and efficiency of PR. Furthermore, we present a live-updating resource ( https://github.com/kqwang/phase-recovery ) for readers to learn more about PR.

LRT: An Efficient Low-Light Restoration Transformer for Dark Light Field Images.

Light field (LF) images containing information for multiple views have numerous applications, which can be severely affected by low-light imaging. Recent learning-based methods for low-light enhancement have some disadvantages, such as a lack of noise suppression, complex training process and poor performance in extremely low-light conditions. To tackle these deficiencies while fully utilizing the multi-view information, we propose an efficient Low-light Restoration Transformer (LRT) for LF images, with multiple heads to perform intermediate tasks within a single network, including denoising, luminance adjustment, refinement and detail enhancement, achieving progressive restoration from small scale to full scale. Moreover, we design an angular transformer block with an efficient view-token scheme to model the global angular dependencies, and a multi-scale spatial transformer block to encode the multi-scale local and global information within each view. To address the issue of insufficient training data, we formulate a synthesis pipeline by simulating the major noise sources with the estimated noise parameters of LF camera. Experimental results demonstrate that our method achieves the state-of-the-art performance on low-light LF restoration with high efficiency.

Phase retrieval with a dual recursive scheme.

Since optical sensors cannot detect the phase information of the light wave, recovering the missing phase from the intensity measurements, called phase retrieval (PR), is a natural and important problem in many imaging applications. In this paper, we propose a learning-based recursive dual alternating direction method of multipliers, called RD-ADMM, for phase retrieval with a dual and recursive scheme. This method tackles the PR problem by solving the primal and dual problems separately. We design a dual structure to take advantage of the information embedded in the dual problem that can help with solving the PR problem, and we show that it is feasible to use the same operator for both the primal and dual problems for regularization. To demonstrate the efficiency of this scheme, we propose a learning-based coded holographic coherent diffractive imaging system to generate the reference pattern automatically according to the intensity information of the latent complex-valued wavefront. Experiments on different kinds of images with a high noise level indicate that our method is effective and robust, and can provide higher-quality results than other commonly-used PR methods for this setup.

Unifying temporal phase unwrapping framework using deep learning.

Temporal phase unwrapping (TPU) is significant for recovering an unambiguous phase of discontinuous surfaces or spatially isolated objects in fringe projection profilometry. Generally, temporal phase unwrapping algorithms can be classified into three groups: the multi-frequency (hierarchical) approach, the multi-wavelength (heterodyne) approach, and the number-theoretic approach. For all of them, extra fringe patterns of different spatial frequencies are required for retrieving the absolute phase. Due to the influence of image noise, people have to use many auxiliary patterns for high-accuracy phase unwrapping. Consequently, image noise limits the efficiency and the measurement speed greatly. Further, these three groups of TPU algorithms have their own theories and are usually applied in different ways. In this work, for the first time to our knowledge, we show that a generalized framework using deep learning can be developed to perform the TPU task for different groups of TPU algorithms. Experimental results show that benefiting from the assistance of deep learning the proposed framework can mitigate the impact of noise effectively and enhance the phase unwrapping reliability significantly without increasing the number of auxiliary patterns for different TPU approaches. We believe that the proposed method demonstrates great potential for developing powerful and reliable phase retrieval techniques.

Morphological profiling by high-throughput single-cell biophysical fractometry.

Complex and irregular cell architecture is known to statistically exhibit fractal geometry, i.e., a pattern resembles a smaller part of itself. Although fractal variations in cells are proven to be closely associated with the disease-related phenotypes that are otherwise obscured in the standard cell-based assays, fractal analysis with single-cell precision remains largely unexplored. To close this gap, here we develop an image-based approach that quantifies a multitude of single-cell biophysical fractal-related properties at subcellular resolution. Taking together with its high-throughput single-cell imaging performance (~10,000 cells/sec), this technique, termed single-cell biophysical fractometry, offers sufficient statistical power for delineating the cellular heterogeneity, in the context of lung-cancer cell subtype classification, drug response assays and cell-cycle progression tracking. Further correlative fractal analysis shows that single-cell biophysical fractometry can enrich the standard morphological profiling depth and spearhead systematic fractal analysis of how cell morphology encodes cellular health and pathological conditions.

Iterative phase retrieval with a sensor mask.

As an important inverse imaging problem in diffraction optics, Fourier phase retrieval aims at estimating the latent image of the target object only from the magnitude of its Fourier measurement. Although in real applications alternating methods are widely-used for Fourier phase retrieval considering the constraints in the object and Fourier domains, they need a lot of initial guesses and iterations to achieve reasonable results. In this paper, we show that a proper sensor mask directly attached to the Fourier magnitude can improve the efficiency of the iterative phase retrieval algorithms, such as alternating direction method of multipliers (ADMM). Furthermore, we refer to the learning-based method to determine the sensor mask according to the Fourier measurement, and unrolled ADMM is used for phase retrieval. Numerical results show that our method outperforms other existing methods for the Fourier phase retrieval problem.

Deep Unrolled Low-Rank Tensor Completion for High Dynamic Range Imaging.

The major challenge in high dynamic range (HDR) imaging for dynamic scenes is suppressing ghosting artifacts caused by large object motions or poor exposures. Whereas recent deep learning-based approaches have shown significant synthesis performance, interpretation and analysis of their behaviors are difficult and their performance is affected by the diversity of training data. In contrast, traditional model-based approaches yield inferior synthesis performance to learning-based algorithms despite their theoretical thoroughness. In this paper, we propose an algorithm unrolling approach to ghost-free HDR image synthesis algorithm that unrolls an iterative low-rank tensor completion algorithm into deep neural networks to take advantage of the merits of both learning- and model-based approaches while overcoming their weaknesses. First, we formulate ghost-free HDR image synthesis as a low-rank tensor completion problem by assuming the low-rank structure of the tensor constructed from low dynamic range (LDR) images and linear dependency among LDR images. We also define two regularization functions to compensate for modeling inaccuracy by extracting hidden model information. Then, we solve the problem efficiently using an iterative optimization algorithm by reformulating it into a series of subproblems. Finally, we unroll the iterative algorithm into a series of blocks corresponding to each iteration, in which the optimization variables are updated by rigorous closed-form solutions and the regularizers are updated by learned deep neural networks. Experimental results on different datasets show that the proposed algorithm provides better HDR image synthesis performance with superior robustness compared with state-of-the-art algorithms, while using significantly fewer training samples.

Dual Alternating Direction Method of Multipliers for Inverse Imaging.

Inverse imaging covers a wide range of imaging applications, including super-resolution, deblurring, and compressive sensing. We propose a novel scheme to solve such problems by combining duality and the alternating direction method of multipliers (ADMM). In addition to a conventional ADMM process, we introduce a second one that solves the dual problem to find the estimated nontrivial lower bound of the objective function, and the related iteration results are used in turn to guide the primal iterations. We call this D-ADMM, and show that it converges to the global minimum when the regularization function is convex and the optimization problem has at least one optimizer. Furthermore, we show how the scheme can give rise to two specific algorithms, called D-ADMM-L2 and D-ADMM-TV, by having different regularization functions. We compare D-ADMM-TV with other methods on image super-resolution and demonstrate comparable or occasionally slightly better quality results. This paves the way of incorporating advanced operators and strategies designed for basic ADMM into the D-ADMM method as well to further improve the performances of those methods.

A Portable Sign Language Collection and Translation Platform with Smart Watches Using a BLSTM-Based Multi-Feature Framework.

Continuous sign language recognition (CSLR) using different types of sensors to precisely recognize sign language in real time is a very challenging but important research direction in sensor technology. Many previous methods are vision-based, with computationally intensive algorithms to process a large number of image/video frames possibly contaminated with noises, which can result in a large translation delay. On the other hand, gesture-based CSLR relying on hand movement data captured on wearable devices may require less computation resources and translation time. Thus, it is more efficient to provide instant translation during real-world communication. However, the insufficient amount of information provided by the wearable sensors often affect the overall performance of this system. To tackle this issue, we propose a bidirectional long short-term memory (BLSTM)-based multi-feature framework for conducting gesture-based CSLR precisely with two smart watches. In this framework, multiple sets of input features are extracted from the collected gesture data to provide a diverse spectrum of valuable information to the underlying BLSTM model for CSLR. To demonstrate the effectiveness of the proposed framework, we test it on an extremely challenging and radically new dataset of Hong Kong sign language (HKSL), in which hand movement data are collected from 6 individual signers for 50 different sentences. The experimental results reveal that the proposed framework attains a much lower word error rate compared with other existing machine learning or deep learning approaches for gesture-based CSLR. Based on this framework, we further propose a portable sign language collection and translation platform, which can simplify the procedure of collecting gesture-based sign language dataset and recognize sign language through smart watch data in real time, in order to break the communication barrier for the sign language users.

Lens-free motion analysis via neuromorphic laser speckle imaging.

Laser speckle imaging (LSI) is a powerful tool for motion analysis owing to the high sensitivity of laser speckles. Traditional LSI techniques rely on identifying changes from the sequential intensity speckle patterns, where each pixel performs synchronous measurements. However, a lot of redundant data of the static speckles without motion information in the scene will also be recorded, resulting in considerable resources consumption for data processing and storage. Moreover, the motion cues are inevitably lost during the "blind" time interval between successive frames. To tackle such challenges, we propose neuromorphic laser speckle imaging (NLSI) as an efficient alternative approach for motion analysis. Our method preserves the motion information while excluding the redundant data by exploring the use of the neuromorphic event sensor, which acquires only the relevant information of the moving parts and responds asynchronously with a much higher sampling rate. This neuromorphic data acquisition mechanism captures fast-moving objects on the order of microseconds. In the proposed NLSI method, the moving object is illuminated using a coherent light source, and the reflected high frequency laser speckle patterns are captured with a bare neuromorphic event sensor. We present the data processing strategy to analyze motion from event-based laser speckles, and the experimental results demonstrate the feasibility of our method at different motion speeds.

Holographic 3D particle reconstruction using a one-stage network.

Volumetric reconstruction of a three-dimensional (3D) particle field with high resolution and low latency is an ambitious and valuable task. As a compact and high-throughput imaging system, digital holography (DH) encodes the 3D information of a particle volume into a two-dimensional (2D) interference pattern. In this work, we propose a one-stage network (OSNet) for 3D particle volumetric reconstruction. Specifically, by a single feed-forward process, OSNet can retrieve the 3D coordinates of the particles directly from the holograms without high-fidelity image reconstruction at each depth slice. Evaluation results from both synthetic and experimental data confirm the feasibility and robustness of our method under different particle concentrations and noise levels in terms of detection rate and position accuracy, with improved processing speed. The additional applications of 3D particle tracking are also investigated, facilitating the analysis of the dynamic displacements and motions for micro-objects or cells. It can be further extended to various types of computational imaging problems sharing similar traits.

Temporal compressive imaging reconstruction based on a 3D-CNN network.

In temporal compressive imaging (TCI), high-speed object frames are reconstructed from measurements collected by a low-speed detector array to improve the system imaging speed. Compared with iterative algorithms, deep learning approaches utilize a trained network to reconstruct high-quality images in a short time. In this work, we study a 3D convolutional neural network for TCI reconstruction to make full use of the temporal and spatial correlation among consecutive object frames. Both simulated and experimental results demonstrate that our network can achieve better reconstruction quality with fewer number of layers.

Deep learning for digital holography: a review.

Recent years have witnessed the unprecedented progress of deep learning applications in digital holography (DH). Nevertheless, there remain huge potentials in how deep learning can further improve performance and enable new functionalities for DH. Here, we survey recent developments in various DH applications powered by deep learning algorithms. This article starts with a brief introduction to digital holographic imaging, then summarizes the most relevant deep learning techniques for DH, with discussions on their benefits and challenges. We then present case studies covering a wide range of problems and applications in order to highlight research achievements to date. We provide an outlook of several promising directions to widen the use of deep learning in various DH applications.

Event-based laser speckle correlation for micro motion estimation: erratum.

We present an erratum to our Letter [Opt. Lett.46, 3885 (2021)OPLEDP0146-959210.1364/OL.430419]. This erratum corrects an inadvertent error in Eq. (4). The corrections have no influence on the results and conclusions of the original Letter.

Event-based laser speckle correlation for micro motion estimation.

Micro motion estimation has important applications in various fields such as microfluidic particle detection and biomedical cell imaging. Conventional methods analyze the motion from intensity images captured using frame-based imaging sensors such as the complementary metal-oxide semiconductor (CMOS) and the charge-coupled device (CCD). Recently, event-based sensors have evolved with the special capability to record asynchronous light changes with high dynamic range, high temporal resolution, low latency, and no motion blur. In this Letter, we explore the potential of using the event sensor to estimate the micro motion based on the laser speckle correlation technique.

Light Field View Synthesis via Aperture Disparity and Warping Confidence Map.

This paper presents a learning-based approach to synthesize the view from an arbitrary camera position given a sparse set of images. A key challenge for this novel view synthesis arises from the reconstruction process, when the views from different input images may not be consistent due to obstruction in the light path. We overcome this by jointly modeling the epipolar property and occlusion in designing a convolutional neural network. We start by defining and computing the aperture disparity map, which approximates the parallax and measures the pixel-wise shift between two views. While this relates to free-space rendering and can fail near the object boundaries, we further develop a warping confidence map to address pixel occlusion in these challenging regions. The proposed method is evaluated on diverse real-world and synthetic light field scenes, and it shows better performance over several state-of-the-art techniques.

Digital holographic imaging and classification of microplastics using deep transfer learning.

We devise an inline digital holographic imaging system equipped with a lightweight deep learning network, termed CompNet, and develop the transfer learning for classification and analysis. It has a compression block consisting of a concatenated rectified linear unit (CReLU) activation to reduce the channels, and a class-balanced cross-entropy loss for training. The method is particularly suitable for small and imbalanced datasets, and we apply it to the detection and classification of microplastics. Our results show good improvements both in feature extraction, and generalization and classification accuracy, effectively overcoming the problem of overfitting. This method could be attractive for future in situ microplastic particle detection and classification applications.