High-precision Reconstruction Research Articles

Single-pixel deep phase-shifting incoherent digital holography

Incoherent digital holography technology reduces the requirement for coherence of light sources, greatly expanding the application range of digital holography. In this paper, we designed a Multi-head attention single-pixel (MHASP) phase-shifting network for incoherent digital holography. The trained network has the capability to effortlessly predict three interferograms, encompassing phase shifts of 0, 2/3 π, and 4/3 π, solely from one-dimensional input data. Utilizing the conventional three-step phase-shifting method, we are able to effectively eliminate the DC and twin terms from the holographic reconstruction process, subsequently achieving a high-fidelity reconstruction facilitated by the employment of the back propagation algorithm. The comprehensive experimental findings clearly indicate that, beyond facilitating high-precision reconstruction, the introduced MHASP phase-shifting approach efficiently preserves 3D information through calibrating the back propagation distance, even when confronted with a reduced volume of holographic data. Furthermore, the introduced approach uses a network to replace the actual phase shift operation, which can better improve the utilization of object light energy. This approach not only circumvented the constraints posed by area array sensors but also facilitated high-fidelity imaging with minimal data volume, thereby expanding the horizons of incoherent digital holography applications in the realm of 3D imaging.

A Globally Consistent Merging Method for House Point Clouds Based on Artificially Enhanced Features

In the process of using structured light technology to obtain indoor point clouds, due to the limited field of view of the device, it is necessary to obtain multiple point clouds of different wall surfaces. Therefore, merging the point cloud is necessary to acquire a complete point cloud. However, due to issues such as the sparse geometric features of the wall point clouds and the high similarity of multiple point clouds, the merging effect of point clouds is poor. In this paper, we leverage artificially enhanced features to improve the accuracy of registration in this scenario. Firstly, we design feature markers and present their layout criteria. Then, the feature information of the marker is extracted based on the Color Signature of Histograms of OrienTations (Color-SHOT) descriptor, and coarse registration is realized through the second-order similarity measure matrix. After that, precise registration is achieved using the Iterative Closest Point (ICP) method based on markers and overlapping areas. Finally, the global error of the point cloud registration is optimized by loop error averaging. Our method enables the high-precision reconstruction of integrated home design scenes lacking significant features at a low cost. The accuracy and validity of the method were verified through comparative experiments.

High Accuracy Reconstruction of Airborne Streak Tube Imaging LiDAR Using Particle Swarm Optimization

Airborne streak tube imaging LiDAR (STIL) consists of several different data-generating subsystems and introduces system errors each time it is installed on an aircraft. These errors change with each installation, which makes the parametric calibration of the LiDAR meaningless. In this study, we propose a high-precision reconstruction method for point clouds that can be used without calibrating the system parameters. In essence, after each remote sensing measurement, a self-checking process is performed with experimental data to replace the fixed system parameters. In this process, the splicing error of the same region measured under different conditions is used as a criterion to optimize the reconstruction parameters via a particle swarm optimization (PSO) algorithm. For a detection distance of 3000 m, the elevation error of the point cloud reconstruction reaches more than 1 m if the placement parameters are not optimized; after optimization, the elevation error can be controlled within 0.3 m.

Harmonic voltage measurement based on capacitive equipment dielectric equivalent model and responding current

Abstract With the increasing proportion of new energy and the power electronic equipment in the power grid, accurate measurement of harmonic voltage has become increasingly important for power quality monitoring. In order to solve the problem of high-precision measurement of harmonic voltage in the power grid, this manuscript proposes a high-precision harmonic voltage measurement method based on the dielectric equivalent model (DEM) of capacitive equipment and its responding current. Based on DEM, a voltage-current transfer function of the capacitive device is established, and harmonic voltage is reconstructed with the responding current. Considering the dielectric relaxation characteristics of capacitive device other than a pure capacitor model, this manuscript analyzes the fitting performance of different equivalent capacitance models and improves the traditional pure capacitance model to a more suitable DEM for harmonic voltage reconstruction. The DEM parameters of capacitive devices are obtained through the frequency domain spectroscopy (FDS) and intelligent parameter identification algorithms, which improved the measurement accuracy of harmonic voltage and reduced computational complexity. The harmonic voltage testing platform is established to test the simulated high-voltage harmonics and the harmonic voltage of the actual grid voltage. The results show that the proposed harmonic voltage measurement method can meet the high-precision reconstruction of harmonic voltage in the frequency range of 50~2500Hz, and the system testing error with sensors is less than 2%. The testing accuracy is higher than traditional voltage transformers and testing systems based on pure capacitance models.

Single-frame fringe pattern analysis with synchronous phase-shifting based on polarization interferometry phase measuring deflectometry (PIPMD)

In the domain of phase measuring deflectometry (or fringe projection profilometry), utilizing only a single-frame fringe pattern to achieve high-precision three-dimensional reconstruction has emerged as a focal point of ongoing research. To achieve four-step phase-shifting demodulation from a single-frame fringe pattern, this paper proposes a Polarization Interferometry Phase Measuring Deflectometry (PIPMD). This method primarily relies on a Michelson polarization interferometry structure to produce projected polarization interference fringes, which are then captured by a polarization camera as modulated single-frame deformed fringe patterns. These single-frame fringe patterns enable pixelated four-step phase shifting with adjacent 2 × 2 pixel units. To validate the proposed method, a series of experiments has been conducted, including surface shape detection of a concave spherical mirror and an off-axis parabolic mirror, as well as dynamic deformation measurements of a deformable mirror. All experimental results consistently indicate that the polarization interference-based fringe projection technique can achieve synchronized phase-shifting demodulation of single-frame fringe patterns, thereby facilitating high-precision reconstruction of the fringe patterns captured in a single frame. This synchronous phase-shifting technique can overcome the influence of air disturbances in traditional four-step phase-shifting methods, thereby enhancing the accuracy of phase demodulation. Additionally, this polarization interference-based Phase Measuring Deflectometry exhibits promising application prospects in dynamic measurements.

WITHDRAWN: Coronary artery segmentation based on ACMA-Net and unscented Kalman filter algorithm

Accurate segmentation of coronary arteries is a prerequisite for high-precision reconstruction of three-dimensional (3D) models of coronary arteries. With personalized 3D coronary anatomy, clinicians can more readily visually determine the location, type, and severity of a stenotic lesion. However, due to the complex structure and small size of coronary arteries, and the interference of image acquisition conditions, 3D models of segmented and reconstructed coronary arteries are noisy and prone to disconnection; accurate segmentation of coronary arteries is still a challenge.To overcome the above challenges, this study proposes a two-stage coronary segmentation algorithm. In the first stage, we added an atrous convolution feature fusion module (ACFFM) and a multi-axis attention module (MAM) to 3D U-Net, referred to as ACMA-Net, to enhance the feature expression ability of the network and effect the preliminary segmentation of coronary arteries. In the second stage, the preliminary segmentation results were skeletonized and endpoint detection was performed. The regions of coronary artery disconnection were determined by finding the minimum distance between the main trunk branch and the endpoint of each disconnected branch. The disconnected skeleton was repaired by reconnection using an unscented Kalman filter (UKF) algorithm.On the private CORO dataset and the public ASOCA dataset, our method obtains an average Dice coefficient of 0.818 and 0.731, respectively, so it outperforms most of the state-of-the-art algorithms compared, proving its excellent effectiveness and robustness.

A novel RCACycleGAN model is proposed for the high-precision reconstruction of sparse TFM images

The sparse total focusing method (TFM) has been shown to enhance the computational efficacy of ultrasound imaging but the image quality of ultrasound regrettably deteriorates with an increase in the sparsity rate of array elements. Deep learning has made remarkable advancements in image processing and cycle-consistent generative adversarial networks (CycleGANs) have been extensively employed to reconstruct diverse image categories. However, due to the incomplete extraction of image feature information by the generator and discriminator in a CycleGAN, high-quality sparse TFM images cannot be directly reconstructed using CycleGANs. There is also a risk of losing crucial feature information related to minor defects. As a result, this paper modifies the generator and discriminator in the CycleGAN to construct a new relativistic discriminator and coordinate attention CycleGAN (RCACycleGAN) model, which enables high-precision reconstruction of sparse TFM images. The addition of the coordinate attention module to the CycleGAN enhances the defective feature representation by fully considering the channel and spatial correlation between regions and using the fusion of spatially perceived feature maps in different directions. It solves the problem of easy loss of defective key feature information. The relativistic discriminator replaces the PatchGAN discriminator in the CycleGAN and evaluates the quality of both real and sparse TFM reconstructed images to ensure a relative image quality evaluation. This process solves the problem of unstable image quality of the sparse TFM reconstructed image. Experimental results demonstrate that RCACycleGAN can stably reconstruct sparse TFM images even in small sample dataset scenarios. The proposed network model reconstructs images with better accuracy, including in terms of structural similarity, defect roundness and area, and has a shorter training time than several existing network models.

High-precision teeth reconstruction based on automatic multimodal fusion with CBCT and IOS

In digital orthodontic treatment, the high-precision reconstruction of complete teeth, encompassing both the crown and the actual root, plays a pivotal role. Current mainstream techniques, prioritizing the high resolution of intraoral scanned models (IOS), are confined to using IOS data for orthodontic treatments. However, the lack of root information in the IOS data may lead to complications such as dehiscence. In contrast, Cone Beam Computed Tomography (CBCT) data encompasses comprehensive dental information with roots. Nonetheless, the radiative character of CBCT scans renders patients unsuitable for repeated examinations in a short time. In addition, lower scanning precision of CBCT leads to suboptimal teeth segmentation outcomes, hindering the accurate representation of dental occlusal relationships. Therefore, in order to fully utilize the complementarity between dental multimodal data, we propose a method for high-precision 3D teeth model reconstruction based on IOS and CBCT, which mainly consists of global rigid registration and local nonrigid registration. Specifically, we extract the priori information of dental arch curves for coarse alignment to provide a good initial position for the Iterative Closest Point (ICP) algorithm, and design a conformal parameterization method for a single tooth to effectively obtain the point correspondence between IOS and CBCT crowns. The rough crown of the CBCT will gradually fit towards the IOS through iterative optimization of nonrigid registration. The experimental results show that our method robustly fuses the advantageous features of IOS and CBCT. The 3D teeth model reconstructed by our method contains the high-precision crown of IOS and the real root of CBCT, which can be effectively used in clinical orthodontic treatment.

Bearing Fault Diagnosis via Stepwise Sparse Regularization with an Adaptive Sparse Dictionary.

Vibration monitoring is one of the most effective approaches for bearing fault diagnosis. Within this category of techniques, sparsity constraint-based regularization has received considerable attention for its capability to accurately extract repetitive transients from noisy vibration signals. The optimal solution of a sparse regularization problem is determined by the regularization term and the data fitting term in the cost function according to their weights, so a tradeoff between sparsity and data fidelity has to be made inevitably, which restricts conventional regularization methods from maintaining strong sparsity-promoting capability and high fitting accuracy at the same time. To address the limitation, a stepwise sparse regularization (SSR) method with an adaptive sparse dictionary is proposed. In this method, the bearing fault diagnosis is modeled as a multi-parameter optimization problem, including time indexes of the sparse dictionary and sparse coefficients. Firstly, sparsity-enhanced optimization is conducted by amplifying the regularization parameter, making the time indexes and the number of atoms adaptively converge to the moments when impulses occur and the number of impulses, respectively. Then, fidelity-enhanced optimization is carried out by removing the regularization term, thereby obtaining the high-precision reconstruction amplitudes. Simulations and experiments verify that the reconstruction accuracy of the SSR method outperforms other sparse regularization methods under most noise conditions, and thus the proposed method can provide more accurate results for bearing fault diagnosis.

A proposed reconstruction method of a 3D animation scene based on a fuzzy long and short-term memory algorithm.

With the development of computer technology leading to a broad range of virtual technology implementations, the construction of virtual tasks has become highly demanded and has increased rapidly, especially in animation scenes. Constructing three-dimensional (3D) animation characters utilizing properties of actual characters could provide users with immersive experiences. However, a 3D face reconstruction (3DFR) utilizing a single image is a very demanding operation in computer graphics and vision. In addition, limited 3D face data sets reduce the performance improvement of the proposed approaches, causing a lack of robustness. When datasets are large, face recognition, transformation, and animation implementations are relatively practical. However, some reconstruction methods only consider the one-to-one processes without considering the correlations or differences in the input images, resulting in models lacking information related to face identity or being overly sensitive to face pose. A face model composed of a convolutional neural network (CNN) regresses 3D deformable model coefficients for 3DFR and alignment tasks. The manuscript proposes a reconstruction method for 3D animation scenes employing fuzzy LSMT-CNN (FLSMT-CNN). Multiple collected images are employed to reconstruct 3D animation characters. First, the serialized images are processed by the proposed method to extract the features of face parameters and then improve the conventional deformable face modeling (3DFDM). Afterward, the 3DFDM is utilized to reconstruct animation characters, and finally, high-precision reconstructions of 3D faces are achieved. The FLSMT-CNN has enhanced both the precision and strength of the reconstructed 3D animation characters, which provides more opportunities to be applied to other animation scenes.

Accurate and semantic 3D reconstruction of maize leaves

The rapid advances in equipment and technology for crop three-dimensional (3D) data acquisition have enabled the high-throughput and high-quality acquisition of crop 3D data. However, the challenge now lies in comprehending unstructured crop 3D data and extracting phenotypes and knowledge. Extracting semantic feature points from plant leaves and achieving high-precision 3D reconstruction is a prevalent and formidable issue in this field. In this study, we present an accurate method for semantic 3D reconstruction of maize leaves. The algorithm utilizes 3D point cloud data of maize leaves as the initial input. Subsequently, the semantic 3D reconstruction of maize leaves is achieved by means of point cloud preprocessing, initial triangular meshing, hole filling, remeshing, mesh parameterization, two-dimensional (2D) edge detection, 2D semantic point interpolation, 3D semantic point selection, mesh generation, and optimization of feature-point position. A total of 56 leaves from five different maize cultivars were reconstructed utilizing this method. The results indicate that the average distance error index dCDMP between the reconstructed mesh vertices and the input point cloud is less than 0.3 cm2 for all five cultivars, and the mean of the maximum distance error index dHDMP for each cultivar is within the range of 0.5–0.8 cm, indicating it is high-accuracy. The visualization of leaves shows good consistency between the reconstructed mesh and corresponding point cloud. Additionally, the reconstructed 3D mesh of the leaves exhibits enhanced triangular facet consistency. Each vertex can be precisely identified as a leaf vein point, leaf edge point, leaf tip point, or leaf surface point, and includes semantic data such as the position on the leaf blade, which can be directly employed for phenotype estimations. High-precision reconstruction of 3D models of crop organs that include semantic information and cultivar resolution yields significant benefits. This technology can improve the resolution and accuracy of crop morphological and structural research, and it is also crucial for crop phenomics, functional-structural plant modelling, and fusion research between plant phenotyping and crop models.

High-precision reconstruction method based on MTS-GAN for electromagnetic environment data in SAGIoT

Equipment failures and communication interruptions of satellites, aircraft and ground devices lead to data loss in Space-Air-Ground Integrated Internet of Things (SAGIoT). The incomplete data affect the accuracy of data modeling, decision-making and spectrum prediction. Reconstructing the incomplete data of electromagnetic environment is a significant task in the SAGIoT. Most spectral data completion algorithms have the problem of limited accuracy and slow iterative optimization. In light of these challenges, a novel high-precision reconstruction method for electromagnetic environment data based on multi-component time series generation adversarial network (MTS-GAN) is proposed in this paper. MTS-GAN transforms the reconstruction method of electromagnetic environment data into the data generation problem of multiple time series. It extracts the time–frequency joint features and the overall distribution of electromagnetic environment data. To improve the reconstruction precision, MTS-GAN simulates the time irregularity of incomplete time series by applying a gate recursive element to adapt to the attenuation effect of discontinuous time series observations. Experimental results show that the proposed MTS-GAN provides high completion accuracy and achieves better results than competitive data completion algorithms.

High precision reconstruction for compressed ultrafast off-axis holography

Existing compressed ultrafast photography (CUP) mainly acquires the light intensity and loses the phase information that characterizes the spatial features. In this paper, we propose a compressed ultrafast holographic imaging system to achieve phase measurement in ultrafast dynamic samples. In the proposed imaging system, the Mach-Zehnder interference structure is incorporated into compressed ultrafast photography. Based on this imaging system, a reconstruction method combining the plug-and-play generalized alternating projection (PnP-GAP) framework and the depth filtering of prior FastDVDNet is proposed to recover the hologram sequence in ultrafast temporal resolution. FastDVDNet employs the correlation between frames to enhance denoising performance and maintain temporal continuity, thus obtaining better results for ultrafast hologram sequence reconstruction. The simulation results indicate that the proposed method outperforms other reconstruction methods in terms of average peak signal-to-noise ratio (PSNR) and structural similarity (SSIM).

Research on Scheme Design and Structure Optimization of High Speed and High Precision Vehicle Contour Detection Platform

To improve road traffic safety and reduce the incidence of unauthorized vehicle modifications, overloading, and oversizing, this study proposed a detection platform structure to support the quick measurement of key dimensions and high-precision reconstruction of local features using the automotive contour size system. Using CAE technology, static and dynamic characteristic analysis was performed on the platform structure, and optimization design was conducted on the column frame and gantry frame separately. The optimized column frame's first-order modal frequency increased by 243% from 5.16 Hz to 17.65 Hz, with an average optimization ratio of 187% for the first six modal frequencies. For the optimized gantry frame, the average optimization ratio of the key node displacement exceeded 46%, with the first-order modal frequency increasing by 13% from 36.43 Hz to 41.33 Hz, and an average optimization ratio of 21% for the first six modal frequencies. Ultimately, the optimized detection platform's key nodes achieved an average optimization ratio of nearly 60%, with the first-order modal frequency increasing by 240% from 5.16 Hz to 17.57 Hz and an average optimization ratio of 185% for the first six modal frequencies. The optimized platform structure provides robust support for the high-speed and high-precision vehicle contour detection system's implementation.

Data driven prediction of fatigue residual stiffness of braided ceramic matrix composites based on Latent-ODE

A Latent-ODE method is proposed for predicting fatigue residual stiffness of braided ceramic matrix composites, combining β-Variational Auto-encoder (β-VAE) and Neural Ordinary Differential Equation (Neural ODEs). β-VAE is used to extract and separate latent features of underlying fatigue behavior and Neural ODEs is used to learn the underlying dynamics behavior corresponding to the fatigue residual stiffness evolution mechanism. Firstly, the residual stiffness of two-dimensional C/SiC ceramic matrix composites under room temperature fatigue is predicted. Based on the potential variable interpolation method, the prediction results are in good agreement with the calculation results of the phenomenological model. The fatigue residual stiffness prediction method based on partial data retraining can obtain higher-precision subsequent residual stiffness prediction results only using the initial 10% fatigue residual stiffness data. In addition, the high temperature fatigue residual stiffness of two-dimensional braided ceramic matrix composites is predicted. The law of stiffness degradation can be learned by the neural network from the high temperature data, and realizing the high precision reconstruction of high temperature fatigue residual stiffness. The method based on partial data retraining only uses the first 30% of the residual stiffness data to predict the residual stiffness.

Shape-from-focus reconstruction using block processing followed by local heat-diffusion-based refinement

Shape from focus (SFF) is a method of recovering the three-dimensional shape of objects from the image sequence through various focusing measurement operators, and is widely used in the fields of medical diagnosis, PCB inspection, industrial manufacturing, and robotic operations. In SFF, the wrong focus measurement causes an inaccurate reconstruction of the object. Generally, to improve the accuracy of focusing measurements, many focus measure (FM) operators are proposed, which is a method that improves the focus volume (FV) performance. However, due to the influence of blur diffusion, which refers to the overlapping of blur circles between different regions, the calculation results of the FM operator in the local window often do not meet the stability requirements of complex scenarios. It is difficult to provide high-precision reconstruction results in practical applications. To overcome this limitation, we proposed an SFF framework based on block processing and heat-diffusion refinement to obtain a refined depth map (RDM). The acquisition of an RDM is mainly divided into two steps. First, the image is divided into blocks to reduce the effect of blur diffusion, and the FM operator is used to calculate the focus measurement value of each block to form the FV. The initial depth map (IDM) is obtained by searching for the best focus position in the FV. The second step is to refine the IDM based on the heat-diffusion principle to obtain the best focus position for all pixels in each block and derive the RDM. The results of experiments conducted on synthetic and real objects demonstrate the superiority of our method in terms of accuracy and its high stability in different application scenarios.

A Lightweight Monocular 3D Face Reconstruction Method Based on Improved 3D Morphing Models.

In the past few years, 3D Morphing Model (3DMM)-based methods have achieved remarkable results in single-image 3D face reconstruction. However, high-fidelity 3D face texture generation has been successfully achieved with this method, which mostly uses the power of deep convolutional neural networks during the parameter fitting process, which leads to an increase in the number of network layers and computational burden of the network model and reduces the computational speed. Currently, existing methods increase computational speed by using lightweight networks for parameter fitting, but at the expense of reconstruction accuracy. In order to solve the above problems, we improved the 3D deformation model and proposed an efficient and lightweight network model: Mobile-FaceRNet. First, we combine depthwise separable convolution and multi-scale representation methods to fit the parameters of a 3D deformable model (3DMM); then, we introduce a residual attention module during network training to enhance the network's attention to important features, guaranteeing high-fidelity facial texture reconstruction quality; and, finally, a new perceptual loss function is designed to better address smoothness and image similarity for the smoothing constraints. Experimental results show that the method proposed in this paper can not only achieve high-precision reconstruction under the premise of lightweight, but it is also more robust to influences such as attitude and occlusion.

Physics-guided neural network for channeled spectropolarimeter spectral reconstruction.

A reconstruction method incorporates the complete physical model into a traditional deep neural network (DNN) is proposed for channeled spectropolarimeter (CSP). Unlike traditional DNN-based methods that need to employ training datasets, the method starts from randomly initialized parameters which are constrained by the CSP physical model. It iterates through the gradient descent algorithm to obtain the estimation of the DNN parameters and then to obtain the mapping relationship. As a result, it eliminates the need for thousands of sets of ground truth data, while also leveraging the physical model to achieve high-precision reconstruction. As seen, the physical model participates in the optimization process of DNN parameters, thus achieving physical guidance for the DNN output results. Based on the characteristic of the network, we designate this method as the physics-guided neural network (PGNN). Both simulations and experiments demonstrate the superior performance of the proposed method. Our approach will further promote the practical application of CSP in a wider range of fields.

A Semantic Information Decomposition Network for Accurate Segmentation of Texture Defects

Defect detection on textured surfaces remains a challenging task in the field of industrial automation due to the wide range of textures and defects. Current unsupervised learning-based texture defect detection methods based on texture background reconstruction, cannot detect texture defects with high precision because it is difficult to guarantee a high-precision reconstruction of the texture background while suppressing the defect foreground. In this study, we propose a novel semantic information decomposition network (SIDN) for accurate texture defect segmentation. The SIDN is trained on artificial defective images produced by a defect generation module (DGM). First, the SIDN uses a feature extraction module (FEM) to extract latent features with both texture semantic information and defect semantic information. Then, a novel feature separation extraction module (FSEM) for decomposing the texture semantic information and defect semantic information from the feature map generated by the FEM is proposed, preventing the coupling of the texture and defect semantic information from affecting the final segmentation accuracy. Next, a novel global semantic relation module (GSRM) is proposed to determine the relevance of the global semantic information to comprehensively consider the context and improve the feature representation. Finally, a segmentation module (SM) that directly segments the textures and defects instead of reconstructing the texture background is proposed. The final detection result is obtained by calculating a weighted average of the texture and defect segmentation results. The extensive experimental tests with the most popular and most challenging texture defect dataset demonstrate that the SIDN achieves accurate segmentation of various texture defects without using real defect samples.

Fluorescence image deconvolution microscopy via generative adversarial learning (FluoGAN)

We propose FluoGAN, an unsupervised hybrid approach combining the physical modelling of fluorescence microscopy timelapse acquisitions with a generative adversarial learning procedure for the problem of image deconvolution. Differently from standard approaches combining a least-square data term based on one (long-time exposure) image with sparsity-promoting regularisation terms, FluoGAN relies on a data term being the distributional distance between the fluctuating observed timelapse (short-time exposure images) and the generative model. Such distance is computed by adversarial training of two competing architectures: a physics-inspired generator simulating the fluctuating behaviour as a Poisson process of the observed images combined with blur and undersampling, and a standard convolutional discriminator network. FluoGAN is a fully unsupervised approach requiring only a fluctuating sequence of blurred, undersampled and noisy images of the sample of interest as input. It can be complemented with prior knowledge on the desired solution such as sparsity, non-negativity etc. After having described the main ideas behind FluoGAN, we formulate the corresponding optimisation problem and report several results on simulated and real phantoms used by microscopy engineers to quantitatively assess spatial resolution. The comparison of FluoGAN with state-of-the-art methodologies shows improved resolution, allowing for high-precision reconstructions of fine structures in challenging real Ostreopsis cf Ovata data. The FluoGAN code is available at: https://github.com/cmayeul/FluoGAN.