High-fidelity Images Research Articles

Sub-50 nm optical imaging in ambient air with 10× objective lens enabled by hyper-hemi-microsphere

Optical microsphere nanoscope has great potential in the inspection of integrated circuit chips for semiconductor industry and morphological characterization in biology due to its superior resolving power and label-free characteristics. However, its resolution in ambient air is restricted by the magnification and numerical aperture (NA) of microsphere. High magnification objective lens is required to be coupled with microsphere for nano-imaging beyond the diffraction limit. To overcome these challenges, in this work, high refractive index hyper-hemi-microspheres with tunable magnification up to 10× are proposed and realized by accurately tailoring their thickness with focused ion beam (FIB) milling. The effective refractive index is put forward to guide the design of hyper-hemi-microspheres. Experiments demonstrate that the imaging resolution and contrast of a hyper-hemi-microsphere with a higher magnification and larger NA excel those of a microsphere in air. Besides, the hyper-hemi-microsphere could resolve ~50 nm feature with higher image fidelity and contrast compared with liquid immersed high refractive index microspheres. With a hyper-hemi-microsphere composed microscale compound lens configuration, sub-50 nm optical imaging in ambient air is realized by only coupling with a 10× objective lens (NA = 0.3), which enhances a conventional microscope imaging power about an order of magnitude.

Deep generative image priors for semantic face manipulation

Previous works on generative adversarial networks (GANs) mainly focus on how to synthesize high-fidelity images. In this paper, we present a framework to leverage the knowledge learned by GANs for semantic face manipulation. In particular, we propose to control the semantics of synthesized faces by adapting the latent codes with an attribute prediction model. Moreover, in order to achieve a more accurate estimation of different facial attributes, we propose to pretrain the attribute prediction model by inverting the synthesized face images back to the GAN latent space. As a result, our method explicitly considers the semantics encoded in the latent space of a pretrained GAN and is able to faithfully edit various attributes like eyeglasses, smiling, bald, age, mustache and gender for high-resolution face images. Extensive experiments show that our method has superior performance compared to state of the art for both face attribute prediction and semantic face manipulation.

Virtual wave based phasor field projection for photoacoustic imaging

The phasor field technique has been demonstrated as a powerful tool to improve imaging performance and reduce computational complexity in time of flight imaging. In this work, we show a similar description and propose phasor field photoacoustics (PAs), a framework for forward acoustic propagation and backward source reconstruction, using phasor representations of acoustic pressure and back projection events. Based on the linear propagation mechanism, this method employs complex phasor filters to decompose the photoacoustic wave into pairs of orthogonal virtual waves, wherein each pair of orthogonal waves corresponds to the real and imaginary parts of the quasi-monochromatic phasor field contribution. By performing phasor field projection (PFP) and thereafter conjugated multiplication in the spatial domain, the complex envelope containing local amplitude and phase information can be faithfully retrieved, attaining rigorous “unipolar” photoacoustic images without ambiguous negative absorption artifacts. Theoretical and experimental results demonstrate that the orthogonal virtual wave based phasor field photoacoustic method can effectively eliminate negative artifacts and improve imaging signal-to-noise ratio (SNR) without excessively increasing computational complexity. This work may pave the way for high-fidelity quantitative imaging, e.g., multispectral and molecular imaging applications.

Monocular metasurface camera for passive single-shot 4D imaging

It is a grand challenge for an imaging system to simultaneously obtain multi-dimensional light field information, such as depth and polarization, of a scene for the accurate perception of the physical world. However, such a task would conventionally require bulky optical components, time-domain multiplexing, and active laser illumination. Here, we experimentally demonstrate a compact monocular camera equipped with a single-layer metalens that can capture a 4D image, including 2D all-in-focus intensity, depth, and polarization of a target scene in a single shot under ambient illumination conditions. The metalens is optimized to have a conjugate pair of polarization-decoupled rotating single-helix point-spread functions that are strongly dependent on the depth of the target object. Combined with a straightforward, physically interpretable image retrieval algorithm, the camera can simultaneously perform high-accuracy depth sensing and high-fidelity polarization imaging over an extended depth of field for both static and dynamic scenes in both indoor and outdoor environments. Such a compact multi-dimensional imaging system could enable new applications in diverse areas ranging from machine vision to microscopy.

Alpha and beta diversity mapping in Indian tropical deciduous forests using high-fidelity imaging spectroscopy

The present study evaluates the potential of airborne hyperspectral and space-borne multispectral satellite datasets to determine alpha (α) and beta (β) diversity combining in-situ floristic composition in tropical deciduous forests (TDFs) of Mudumalai Tiger Reserve (MTR), India. 43 forest plots (each of 0.04 ha) were sampled to record the species diversity in MTR. The very high-resolution AVIRIS-NG hyperspectral images and temporal Sentinel-2 multispectral images were used to extract spectral variables by associating each field plot with corresponding pixels of the satellite images. A high positive correlation of field-based α-diversity (Shannon-Wiener diversity index (H′)) with AVIRIS-NG based α-diversity (R2: 0.83 (2016); R2: 0.82 (2018)) was observed compared to Sentinel-2 based α-diversity (R2: 0.50 to 0.63) with high correlation during post-monsoon (R2: 0.63). Principal coordinate analysis of AVIRIS-NG based β-diversity signifies a low diversity (H′: <1.00) in the eastern parts (0.13% of MTR) in contrast to moderate (H′: 1.00 to 2.00; 13.39% of MTR) to high diversity (H′ >2.00; 86.49% of MTR) in the remaining parts of MTR. The study highlights the application of high spectral-spatial AVIRIS-NG images for precise tree diversity mapping and the high temporal-spatial Sentinel-2 satellite images for assessing the phenological variations of the forest species. The integration of high spatial-hyperspectral and temporal multispectral satellite datasets with field-based observations for fine-scale tree species diversity mapping at geographical and temporal scales is the novelty of the study that may effectively contribute in devising effective forest management plans for biodiversity conservation.

Deep Generative Models: A Review

Objectives: To provide insight into deep generative models and review the most prominent and efficient deep generative models, including Variational Auto-encoder (VAE) and Generative Adversarial Networks (GANs). Methods: We provide a comprehensive overview of VAEs and GANs along with their advantages and disadvantages. This paper also surveys the recently introduced Attention-based GANs and the most recently introduced Transformer based GANs. Findings: GANs have been intensively researched because of their significant advantages over VAE. Furthermore, GANs are powerful generative models that have been widely employed in a variety of fields. Though GANs have a number of advantages over VAEs, but, despite their immense popularity and success, training GANs is still difficult and has experienced a lot of setbacks. These failures include mode collapse, where the generator produces the same set of outputs for various inputs, ultimately resulting in the loss of diversity; non-convergence due to oscillatory and diverging behaviors of the generator and discriminator during the training phase; and vanishing or exploding gradients, where learning either ceases to occur or occurs very slowly. Recently, some attention-based GANs and Transformer-based GANs have also been proposed for high-fidelity image generation. Novelty: Unlike previous survey articles, which often focus on all DGMs and dive into their complicated aspects, this work focuses on the most prominent DGMs, VAEs, and GANs and provides a theoretical understanding of them. Furthermore, because GAN is now the most extensively used DGM being studied by the academic community, the literature on it needs to be explored more. Moreover, while numerous articles on GANs are available, none have analyzed the most recent attention-based GANs and Transformer-based GANs. So, in this study, we review the recently introduced attention-based GANs and Transformer-based GANs, the literature related to which has not been reviewed by any survey paper. Keywords: Variational Autoencoder; Generative Adversarial Networks; Autoencoder; Transformer; Self-Attention

Toward high-fidelity imaging: Dynamic matching FWI and its applications

Full-waveform inversion (FWI) is firmly established within our industry as a powerful velocity model building tool. FWI carries significant theoretical advantages over conventional velocity model building methods such as refraction and reflection tomography. Specifically, by solving a nonlinear inverse problem through the wave equation, FWI is able to recover a broadband velocity model containing both high and low spatial wavenumbers, thus extending the approximation of residual moveout correction inherent in traditional velocity model building approaches. Moreover, FWI is capable of inverting information from the entire wavefield (i.e., early arrivals, reflections, refractions, and multiple energy) rather than from a subset as in conventional approaches (i.e., first break and primary reflections), thereby availing itself of more information to better constrain its model estimate. However, these theoretical benefits cannot be realized easily in practice because various complexities of real seismic data often conspire to violate algorithmic assumptions, leading to unsatisfactory results. Dynamic matching FWI (DMFWI) is a newly developed algorithm that solves an inversion problem that maximizes the cross correlation of two dynamically matched data sets — one recorded and the other synthetic. Dynamic matching of the two data sets de-emphasizes the amplitude impact, which allows the algorithm to focus on minimizing their kinematic differences rather than amplitude in the data-fitting process. The multichannel correlation makes the algorithm robust for data with low signal-to-noise ratio. Applications of DMFWI across different types of acquisition and geologic settings demonstrate that this novel FWI approach can resolve complex velocity errors and provide high-quality migrated images that exhibit a high degree of geologic plausibility. Additionally, reflectivity images can be obtained in a straightforward manner as natural byproducts through computation of the directional derivative of the inverted FWI velocity models.

Process optimization of contact hole patterns via a simulated annealing algorithm in extreme ultraviolet lithography.

The critical dimension (CD), roughness, and sensitivity are extremely significant indicators for evaluating the imaging performance of photoresists in extreme ultraviolet lithography. As the CD gradually shrinks, tighter indicator control is required for high fidelity imaging. However, current research primarily focuses on the optimization of one indicator of one-dimensional line patterns, and little attention has been paid to two-dimensional patterns. Here, we report an image quality optimization method of two-dimensional contact holes. This method takes horizontal and vertical contact widths, contact edge roughness, and sensitivity as evaluation indicators, and uses machine learning to establish the corresponding relationship between process parameters and each indicator. Then, the simulated annealing algorithm is applied to search for the optimal process parameters, and finally, a set of process parameters with optimum image quality is obtained. Rigorous imaging results of lithography demonstrate that this method has very high optimization accuracy and can improve the overall performance of the device, dramatically accelerating the development of the lithography process.

Echocardiographic imaging of a bifurcated double barrel coronary sinus

BackgroundThe coronary sinus (CS) is the terminal collecting vessel of the myocardial venous network, which returns deoxygenated blood used by the heart to the right atrium. The advent of high-fidelity imaging via CT and transesophageal echocardiography (TEE) has further defined the anatomy of the CS and its multiple tributaries. Understanding this anatomy is crucial for cardiac surgical cases that require the cannulation of the coronary sinus to deliver retrograde cardioplegia. However, anatomical variants of the CS may frustrate surgical retrograde catheter placement, in turn increasing the risk of CS injury or leading to inadequate cardioplegia delivery. Here, we present an especially unique CS presentation, a bifurcated, double-barrel CS, which was discovered via intraoperative TEE imaging that revealed a CS with two smaller lumens instead of the singular large os.Case presentationA 67-year-old male presented for ascending aortic dissection repair, aortic valve replacement, and single vessel coronary artery bypass graft. On the pre-bypass TEE exam, the anesthesiologist noted a bifurcated CS with two small lumens. The surgeon utilized this information to select a smaller diameter retrograde catheter to avoid damage or perforation of the vessel. With TEE guidance, the surgeon successfully cannulated one of the CS lumens. However, it was noted upon dosing of retrograde cardioplegia that all tributary vessels attached to the non-cannulated lumen remained devoid of cardioplegia. The surgeon was forced to repeatedly administer anterograde cardioplegia via a handheld catheter through the coronary ostium throughout the case. The operative field was also flooded with topical ice saline slush to ensure cardiac protection. Ultimately, the operation was completed without incident despite the non-ideal conditions resulting from this anatomic variant.ConclusionsDiscovery of this patient’s double-barrel CS during the pre-bypass TEE was incidental, showing that such anatomical variants may be completely asymptomatic and benign in the non-operative setting. However, the delivery of cardioplegia proved challenging for this patient, highlighting some degree of risk with certain cardiac interventions. This case demonstrates the utility of intraoperative TEE to quickly ascertain unforeseen anatomical variants of the CS which could compromise the safety of cardiac surgery cases.

Dataset generation and validation for spacecraft pose estimation via monocular images processing

Recent studies demonstrate the possibility of navigating in proximity of uncooperative space resident objects by using only monocular images. Despite the results achieved, the development and testing of new algorithms are strongly constrained by the availability of spaceborne image datasets. To overcome this, a new algorithm embedded in a tool to generate synthetic high-fidelity spaceborne image datasets is presented here. The architecture developed can be tailored to a wide range of scenarios and it is based on an open-source ray-tracing software. All assumptions and simplifications adopted are discussed in detail for the different models considered, including a trade-off between accuracy and rendering time. The new method described is subsequently adapted to a baseline scenario where the optical properties of a reference spacecraft model are tuned. Both qualitative and quantitative validations are detailed and successfully carried out for the baseline case, demonstrating the high photo-realism achievable with the proposed method. As a consequence of this main outcome, the paper details the generation of labeled spaceborne image datasets publicly available and reports the analyses that confirm the high level of representativeness, making them suitable for training and testing image-based navigation algorithms. As another outcome, the most comprehensive multi-purpose labeled dataset of validated spaceborne synthetic images currently publicly available is presented.

Geostationary Full-Spectrum Wide-Swath High-Fidelity Imaging Spectrometer: Optical Design and Prototype Development

The optical system of an imaging spectrometer working on a geostationary earth orbit (GEO) covering a full optical spectrum of 0.3–12.5 μm is analyzed and designed. It enables a ground coverage of 400 × 400 km by internal scanning and achieves a high spatial resolution of 25 m. The full spectrum is divided into five sub-bands, and each band adopts four spectrometers to splice in the field of view to achieve the ultra-long slit required by the wide swath. The total length of the slit is up to 241.3 mm. This paper focuses on compact spectrometers with long slits that can meet the splicing requirements and points out that low spectral distortions, low stray light, high signal-to-noise ratio, and uniform spectral response are necessary for high-fidelity performance. The Offner and Wynne–Offner high-fidelity spectrometers based on convex blazed gratings are designed, and prototypes of each band are developed as well. The properties of long slits and convex blazed gratings are presented. The maximum length of a single slit is 61.44 mm. The groove density of gratings for five bands ranges from 8.8 lp/mm to 312.1 lp/mm, and the peak efficiency is up to 86.4%. The alignment and test of the spectrometers are introduced. Results show that the developed spectrometers have high fidelity and fulfill all requirements.

DO-VTON: a details-oriented virtual try-on network

PurposeThe paper aims to transfer the item image of a given clothing product to a corresponding area of the user image. Existing classical methods suffer from unconstrained deformation of clothing and occlusion caused by hair or poses, which leads to loss of details in the try-on results. In this paper, the authors present a details-oriented virtual try-on network (DO-VTON), which allows synthesizing high-fidelity try-on images with preserved characteristics of target clothing.Design/methodology/approachThe proposed try-on network consists of three modules. The fashion parsing module (FPM) is designed to generate the parsing map of a reference person image. The geometric matching module (GMM) warps the input clothing and matches it with the torso area of the reference person guided by the parsing map. The try-on module (TOM) generates the final try-on image. In both FPM and TOM, attention mechanism is introduced to obtain sufficient features, which enhances the performance of characteristics preservation. In GMM, a two-stage coarse-to-fine training strategy with a grid regularization loss (GR loss) is employed to optimize the clothing warping.FindingsIn this paper, the authors propose a three-stage image-based virtual try-on network, DO-VTON, that aims to generate realistic try-on images with extensive characteristics preserved.Research limitations/implicationsThe authors’ proposed algorithm can provide a promising tool for image based virtual try-on.Practical implicationsThe authors’ proposed method is a technology for consumers to purchase favored clothes online and to reduce the return rate in e-commerce.Originality/valueTherefore, the authors’ proposed algorithm can provide a promising tool for image based virtual try-on.

High-fidelity diabetic retina fundus image synthesis from freestyle lesion maps.

Retina fundus imaging for diagnosing diabetic retinopathy (DR) is an efficient and patient-friendly modality, where many high-resolution images can be easily obtained for accurate diagnosis. With the advancements of deep learning, data-driven models may facilitate the process of high-throughput diagnosis especially in areas with less availability of certified human experts. Many datasets of DR already exist for training learning-based models. However, most are often unbalanced, do not have a large enough sample count, or both. This paper proposes a two-stage pipeline for generating photo-realistic retinal fundus images based on either artificially generated or free-hand drawn semantic lesion maps. The first stage uses a conditional StyleGAN to generate synthetic lesion maps based on a DR severity grade. The second stage then uses GauGAN to convert the synthetic lesion maps into high resolution fundus images. We evaluate the photo-realism of generated images using the Fréchet inception distance (FID), and show the efficacy of our pipeline through downstream tasks, such as; dataset augmentation for automatic DR grading and lesion segmentation.

Automated seizure onset zone locator from resting-state functional MRI in drug-resistant epilepsy.

Accurate localization of a seizure onset zone (SOZ) from independent components (IC) of resting-state functional magnetic resonance imaging (rs-fMRI) improves surgical outcomes in children with drug-resistant epilepsy (DRE). Automated IC sorting has limited success in identifying SOZ localizing ICs in adult normal rs-fMRI or uncategorized epilepsy. Children face unique challenges due to the developing brain and its associated surgical risks. This study proposes a novel SOZ localization algorithm (EPIK) for children with DRE. EPIK is developed in a phased approach, where fMRI noise-related biomarkers are used through high-fidelity image processing techniques to eliminate noise ICs. Then, the SOZ markers are used through a maximum likelihood-based classifier to determine SOZ localizing ICs. The performance of EPIK was evaluated on a unique pediatric DRE dataset (n = 52). A total of 24 children underwent surgical resection or ablation of an rs-fMRI identified SOZ, concurrently evaluated with an EEG and anatomical MRI. Two state-of-art techniques were used for comparison: (a) least squares support-vector machine and (b) convolutional neural networks. The performance was benchmarked against expert IC sorting and Engel outcomes for surgical SOZ resection or ablation. The analysis was stratified across age and sex. EPIK outperformed state-of-art techniques for SOZ localizing IC identification with a mean accuracy of 84.7% (4% higher), a precision of 74.1% (22% higher), a specificity of 81.9% (3.2% higher), and a sensitivity of 88.6% (16.5% higher). EPIK showed consistent performance across age and sex with the best performance in those < 5 years of age. It helped achieve a ~5-fold reduction in the number of ICs to be potentially analyzed during pre-surgical screening. Automated SOZ localization from rs-fMRI, validated against surgical outcomes, indicates the potential for clinical feasibility. It eliminates the need for expert sorting, outperforms prior automated methods, and is consistent across age and sex.

Derisking geologic carbon storage from high-resolution time-lapse seismic to explainable leakage detection

Geologic carbon storage represents one of the few truly scalable technologies capable of reducing the CO2 concentration in the atmosphere. While this technology has the potential to scale, its success hinges on our ability to mitigate its risks. An important aspect of risk mitigation concerns assurances that the injected CO2 remains within the storage complex. Among the different monitoring modalities, seismic imaging stands out due to its ability to attain high-resolution and high-fidelity images. However, these superior features come at prohibitive costs and time-intensive efforts that potentially render extensive seismic monitoring undesirable. To overcome this shortcoming, we present a methodology in which time-lapse images are created by inverting nonreplicated time-lapse monitoring data jointly. By no longer insisting on replication of the surveys to obtain high-fidelity time-lapse images and differences, extreme costs and time-consuming labor are averted. To demonstrate our approach, hundreds of realistic synthetic noisy time-lapse seismic data sets are simulated that contain imprints of regular CO2 plumes and irregular plumes that leak. These time-lapse data sets are subsequently inverted to produce time-lapse difference images that are used to train a deep neural classifier. The testing results show that the classifier is capable of detecting CO2 leakage automatically on unseen data with reasonable accuracy. We consider the use of this classifier as a first step in the development of an automatic workflow designed to handle the large number of continuously monitored CO2 injection sites needed to help combat climate change.

High-fidelity imaging of intracellular microRNA via a bioorthogonal nanoprobe.

The spatiotemporal visualization of intracellular microRNA (miRNA) plays a critical role in the diagnosis and treatment of malignant disease. Although DNAzyme-based biosensing has been regarded as the most promising candidate, inefficient analytical resolution is frequently encountered. Here, we propose a bioorthogonal approach toward high-fidelity imaging of intracellular miRNA by designing a multifunctional nanoprobe that integrates MnO2 nanosheet-mediated intracellular delivery and activation by a fat mass and obesity-associated protein (FTO)-switched positive feedback. MnO2 nanosheets facilitate nanoprobe delivery and intracellular DNAzyme cofactors are released upon glutathione-triggered reduction. Meanwhile, an m6A-caged DNAzyme probe could be bioorthogonally activated by intracellular FTO to eliminate potential off-target activation. Therefore, the activated DNAzyme probe and substrate probe could recognize miRNA to perform cascade signal amplification in the initiation of the release of Mn2+ from MnO2 nanosheets. This strategy realized high-fidelity imaging of intracellular aberrant miRNA within tumor cells with a satisfactory detection limit of 9.7 pM, paving the way to facilitate clinical tumor diagnosis and prognosis monitoring.

Acceleration of high-quality Raman imaging via a locality enhanced transformer network.

Raman imaging (RI) is an outstanding technique that enables molecular-level medical diagnostics and therapy assessment by providing characteristic fingerprint and morphological information about molecules. However, obtaining high-quality Raman images generally requires a long acquisition time, up to hours, which is prohibitive for RI applications of timely cytopathology and histopathology analyses. To address this issue, image super-resolution (SR) based on deep learning, including convolutional neural networks and transformers, has been widely recognized as an effective solution to reduce the time required for achieving high-quality RI. In this study, a locality enhanced transformer network (LETNet) is proposed to perform Raman image SR. Specifically, the general architecture of the transformer is adopted with the replacement of self-attention by convolution to generate high-fidelity and detailed SR images. Additionally, the convolution in the LETNet is further optimized by utilizing depth-wise convolution to improve the computational efficiency of the model. Experiments on hyperspectral Raman images of breast cancer cells and Raman images of a few channels of brain tumor tissues demonstrate that the LETNet achieves superior 2×, 4×, and 8× SR with fewer parameters compared with other SR methods. Consequently, high-quality Raman images can be obtained with a significant reduction in time, ranging from 4 to 64 times. Overall, the proposed method provides a novel, efficient, and reliable solution to expedite high-quality RI and promote its application in real-time diagnosis and therapy.

U-shape Transformer for Underwater Image Enhancement.

The light absorption and scattering of underwater impurities lead to poor underwater imaging quality. The existing data-driven based underwater image enhancement (UIE) techniques suffer from the lack of a large-scale dataset containing various underwater scenes and high-fidelity reference images. Besides, the inconsistent attenuation in different color channels and space areas is not fully considered for boosted enhancement. In this work, we built a large scale underwater image (LSUI) dataset, which covers more abundant underwater scenes and better visual quality reference images than existing underwater datasets. The dataset contains 4279 real-world underwater image groups, in which each raw image's clear reference images, semantic segmentation map and medium transmission map are paired correspondingly. We also reported an U-shape Transformer network where the transformer model is for the first time introduced to the UIE task. The U-shape Transformer is integrated with a channel-wise multi-scale feature fusion transformer (CMSFFT) module and a spatial-wise global feature modeling transformer (SGFMT) module specially designed for UIE task, which reinforce the network's attention to the color channels and space areas with more serious attenuation. Meanwhile, in order to further improve the contrast and saturation, a novel loss function combining RGB, LAB and LCH color spaces is designed following the human vision principle. The extensive experiments on available datasets validate the state-of-the-art performance of the reported technique with more than 2dB superiority. The dataset and demo code are available on https://bianlab.github.io/.

Engineering fluorescent protein chromophores with an internal reference for high-fidelity ratiometric G4 imaging in living cells.

G-quadruplexes (G4s) are significant nucleic acid secondary structures formed by guanine-rich sequences. Many single-emission G4 fluorescent probes that are lit up by inhibiting intramolecular rotation have been reported. However, they are non-fluorescent unless structurally rigidified, making them sensitive to other intracellular crowding and confinement environments in the cell, like viscosity. Ratiometric measurements provide built-in self-calibration for signal correction, enabling more sensitive and reliable detection. Herein, we structurally modulate green fluorescent protein (GFP)-like chromophores by integrating the imidazolidinone scaffold of the GFP chromophore and coumarin 6H, obtaining a G4 responsive dual-emission chromophore, called NHCouI. The red emission signal of NHCouI can specifically respond to parallel G4s, while its green emission signal is inert and acts as an internal reference signal. NHCouI-G4 complexes feature high fluorescence quantum yield and excellent anti-photobleaching properties. NHCouI can self-calibrate the signal and avoid viscosity disturbances within the range of major subcellular organelles during G4 imaging in living cells. It is also applied to reflect the difference between apoptosis and ferroptosis via tracking G4s. To the best of our knowledge, NHCouI is the first small molecule G4 probe enabled by internal reference correction capability, opening up new avenues for dual-emission chromophore development and high-fidelity and reliable analysis in G4 imaging research.

Evaluation of Key Spatiotemporal Learners for Print Track Anomaly Classification Using Melt Pool Image Streams

Recent applications of machine learning in metal additive manufacturing (MAM) have shown great potential to resolve critical barriers to MAM's widespread adoption. Recent research on the topic highlights the significance of using melt pool signatures to predict defects on-the-fly. While high-fidelity melt pool image data has the potential to enable accurate predictions, hardly any work exists on the use of state-of-the-art spatiotemporal models to leverage the information embedded in the transient and sequential nature of the additive process. This work introduces and implements some of the major deep spatiotemporal learners that can be adapted to classify melt pool image streams from different materials, systems, and applications. In this regard, two-stream networks with a spatial and temporal stream, a recurrent spatial network, and a factorized 3D convolutional neural network were investigated herein. The generalization abilities of these models to perturbations in the melt pool image data are tested using data perturbation techniques that are grounded in palpable process situations. The implemented architectures exhibit the ability to learn the spatiotemporal features of the melt pool image sequences. However, only the Kinetics400 pre-trained SlowFast network, which belongs to the two-stream category, showed strong generalisation abilities to data perturbations.