Texture Information Research Articles

No-Reference Quality Assessment Based on Dual-Channel Convolutional Neural Network for Underwater Image Enhancement

Underwater images are important for underwater vision tasks, yet their quality often degrades during imaging, promoting the generation of Underwater Image Enhancement (UIE) algorithms. This paper proposes a Dual-Channel Convolutional Neural Network (DC-CNN)-based quality assessment method to evaluate the performance of different UIE algorithms. Specifically, inspired by the intrinsic image decomposition, the enhanced underwater image is decomposed into reflectance with color information and illumination with texture information based on the Retinex theory. Afterward, we design a DC-CNN with two branches to learn color and texture features from reflectance and illumination, respectively, reflecting the distortion characteristics of enhanced underwater images. To integrate the learned features, a feature fusion module and attention mechanism are conducted to align efficiently and reasonably with human visual perception characteristics. Finally, a quality regression module is used to establish the mapping relationship between the extracted features and quality scores. Experimental results on two public enhanced underwater image datasets (i.e., UIQE and SAUD) show that the proposed DC-CNN method outperforms a variety of the existing quality assessment methods.

Highly Responsive Polar Vortices in All-Ferroelectric Heterostructures.

The discovery of polar vortices and skyrmions in ferroelectric-dielectric superlattices [such as (PbTiO3)n/(SrTiO3)n] has ushered in an era of novel dipolar topologies and corresponding emergent phenomena. The key to creating such emergent features has generally been considered to be related to counterpoising strongly polar and non-polar materials thus creating the appropriate boundary conditions. This limits the utility these materials can have, however, by rendering (effectively) half of the structure unresponsive to applied stimuli. Here, using advanced thin-film deposition and an array of characterization and simulation approaches, polar vortices are realized in all-ferroelectric trilayers, multilayers, and superlattices built from the fundamental building block of (PbTiO3)n/(PbxSr1- xTiO3)n wherein in-plane ferroelectric polarization in the PbxSr1- xTiO3 provides the appropriate boundary conditions. These superlattices exhibit substantially enhanced electromechanical and ferroelectric responses in the out-of-plane direction that arise from the ability of the polarization in both layers to rotate to the out-of-plane direction under field. In the in-plane direction, the layers are found to be strongly coupled during switching and when heterostructured with ferroelectric-dielectric building blocks, it is possible to produce multistate switching. This approach expands the realm of systems supporting emergent dipolar texture formation and does so with entirely ferroelectric materials thus greatly improving their responses.

Modeling and characterizing of surface texture produced by scraping process

Abstract Scraping technology is widely used in the guideways manufacturing of high-precision machine tools, yet the scraped surface texture formation mechanism is still not fully understood owing to the complexity and randomness of the scraping process, which limits the study of the tribological properties of scraped bond surfaces. To reveal the formation mechanism of the scraped surface texture, this study adopts the stratified theory to model and characterize scraped surfaces based on the characteristics of the scraping process. The research found tri-Gaussian stratification features in a scraped surface texture and establishes surface stratified model. Tri-Gaussian segmented separation and continuous separation methods are proposed to calculate the component surface parameters for characterizing the scraped surface texture. Segmented and continuous separation methods are respectively applied to analyze and reconstruct simulated tri-Gaussian stratified surfaces and experimental scraped surfaces. The results indicate that the continuous separation method is superior to the segmented separation method and leads to almost the same height and process parameters as the measured surface in the surface reconstruction. This verifies the feasibility and accuracy of the scraped surface texture model and characterization methods. This paper reveals the surface texture formation mechanism from the viewpoint of the scraping process and provides new insights for modeling and characterizing research on scraped surface texture.

An Efficient Dense Reconstruction Algorithm from LiDAR and Monocular Camera

Dense reconstruction have been studied for decades in the fields of computer vision and robotics, in which LiDAR and camera are widely used. However, vision-based methods are sensitive to illumination variation and lack direct depth, and LiDAR-based methods are limited by sparse LiDAR measurement and lacking color and texture information. In this paper, we propose a novel 3D reconstruction algorithm based on LiDAR and a monocular camera, which realizes dense reconstruction. In the algorithm, a LiDAR odometry is used to get accurate poses and poses calculated by the odometry module are used in the calculation of depth maps and fusion of depth maps, and then mesh and texture mapping are implemented. In addition, a semantic segmentation network and a depth completion network are used to obtain dense and accurate depth maps. The concept of symmetry is utilized to generate 3D models of objects or scenes; that is, the reconstruction and camera imaging of these objects or scenes are symmetrical. Experimental results on public dataset show that the proposed algorithm achieves higher accuracy, efficiency and completeness than existing methods.

Lightweight Reference-Based Video Super-Resolution Using Deformable Convolution

Super-resolution is a technique for generating a high-resolution image or video from a low-resolution counterpart by predicting natural and realistic texture information. It has various applications such as medical image analysis, surveillance, remote sensing, etc. However, traditional single-image super-resolution methods can lead to a blurry visual effect. Reference-based super-resolution methods have been proposed to recover detailed information accurately. In reference-based methods, a high-resolution image is also used as a reference in addition to the low-resolution input image. Reference-based methods aim at transferring high-resolution textures from the reference image to produce visually pleasing results. However, it requires texture alignment between low-resolution and reference images, which generally requires a lot of time and memory. This paper proposes a lightweight reference-based video super-resolution method using deformable convolution. The proposed method makes the reference-based super-resolution a technology that can be easily used even in environments with limited computational resources. To verify the effectiveness of the proposed method, we conducted experiments to compare the proposed method with baseline methods in two aspects: runtime and memory usage, in addition to accuracy. The experimental results showed that the proposed method restored a high-quality super-resolved image from a very low-resolution level in 0.0138 s using two NVIDIA RTX 2080 GPUs, much faster than the representative method.

Low-Cost and Contactless Survey Technique for Rapid Pavement Texture Assessment Using Mobile Phone Imagery

Collecting pavement texture information is crucial to understand the characteristics of a road surface and to have essential data to support road maintenance. Traditional texture assessment techniques often require expensive equipment and complex operations. To ensure cost sustainability and reduce traffic closure times, this study proposes a rapid, cost-effective, and non-invasive surface texture assessment technique. This technology consists of capturing a set of images of a road surface with a mobile phone; then, the images are used to reconstruct the 3D surface with photogrammetric processing and derive the roughness parameters to assess the pavement texture. The results indicate that pavement images taken by a mobile phone can reconstruct the 3D surface and extract texture features with accuracy, meeting the requirements of a time-effective documentation. To validate the effectiveness of this technique, the surface structure of the pavement was analyzed in situ using a 3D structured light projection scanner and rigorous photogrammetry with a high-end reflex camera. The results demonstrated that increasing the point cloud density can enhance the detail level of the real surface 3D representation, but it leads to variations in road surface roughness parameters. Therefore, appropriate density should be chosen when performing three-dimensional reconstruction using mobile phone images. Mobile phone photogrammetry technology performs well in detecting shallow road surface textures but has certain limitations in capturing deeper textures. The texture parameters and the Abbott curve obtained using all three methods are comparable and fall within the same range of acceptability. This finding demonstrates the feasibility of using a mobile phone for pavement texture assessments with appropriate settings.

Coupling design features of material surface treatment for ceramic products based on ResNet

Abstract Ceramic products is one of the important carriers of various civilizations, reflecting the lifestyle, aesthetic concepts, and technological level of society at that time. In order to study the surface treatment design features of ceramic craft products, this article analyzed the ceramic features through computer vision technology and used residual neural networks to detect the surface treatment features of ceramic craft products. The extracted texture features were classified to study and analyze the coupling features of different glazes, colors, and shapes on the formation of different textures. This study used ResNeXt50-SSD, which combined ResNeXt50 and SSD (Single Shot MultiBox Detector) algorithms, to compare feature detection with LeNet-5, VGG-16, and MobileNetV2 network models. From the experimental findings, it can be concluded that ResNeXt50-SSD was the most effective for feature recognition of ceramic craft products, with precision, recall, and mAP of 94.3, 92.1, and 89.5%, respectively. Therefore, the combination of ResNeXt50 and SSD algorithms is an effective method for detecting surface treatment features of ceramic craft products.

GSEditPro: 3D Gaussian Splatting Editing with Attention‐based Progressive Localization

AbstractWith the emergence of large‐scale Text‐to‐Image(T2I) models and implicit 3D representations like Neural Radiance Fields (NeRF), many text‐driven generative editing methods based on NeRF have appeared. However, the implicit encoding of geometric and textural information poses challenges in accurately locating and controlling objects during editing. Recently, significant advancements have been made in the editing methods of 3D Gaussian Splatting, a real‐time rendering technology that relies on explicit representation. However, these methods still suffer from issues including inaccurate localization and limited manipulation over editing. To tackle these challenges, we propose GSEditPro, a novel 3D scene editing framework which allows users to perform various creative and precise editing using text prompts only. Leveraging the explicit nature of the 3D Gaussian distribution, we introduce an attention‐based progressive localization module to add semantic labels to each Gaussian during rendering. This enables precise localization on editing areas by classifying Gaussians based on their relevance to the editing prompts derived from cross‐attention layers of the T2I model. Furthermore, we present an innovative editing optimization method based on 3D Gaussian Splatting, obtaining stable and refined editing results through the guidance of Score Distillation Sampling and pseudo ground truth. We prove the efficacy of our method through extensive experiments.

Revisiting representation learning of color information: Color medical image segmentation incorporating quaternion

Currently, color medical image segmentation methods commonly extract color and texture features mixed together by default, however, the distribution of color information and texture information is different: color information is represented differently in different color channels of a color image, while the distribution of texture information remains the same. Such a simple and brute-force feature extraction pattern will inevitably result in a partial bias in the model's semantics understanding. In this paper, we decouple the representation learning for color-texture information, and propose a novel network for color medical image segmentation, named CTNet. Specifically, CTNet introduces the Quaternion CNN (QCNN) module to capture the correlation among different color channels of color medical images to generate color features, and uses a designed local-global texture feature integrator (LoG) to mine the textural features from local to global. Moreover, a multi-stage features interaction strategy is proposed to minimize the semantic understanding gap of color and texture features in CTNet, so that they can be subsequently fused to generate a unified and robust feature representation. Comparative experiments on four different color medical image segmentation benchmark datasets show that CTNet strikes an optimal trade-off between segmentation accuracy and computational overhead when compared to current state-of-the-art methods. We also conduct extensive ablation experiments to verify the effectiveness of the proposed components. Our code will be available at https://github.com/Notmezhan/CTNet.

Detecting Water Stress in Winter Wheat Based on Multifeature Fusion from UAV Remote Sensing and Stacking Ensemble Learning Method

The integration of remote sensing technology and machine learning algorithms represents a new research direction for the rapid and large-scale detection of water stress in modern agricultural crops. However, in solving practical agricultural problems, single machine learning algorithms cannot fully explore the potential information within the data, lacking stability and accuracy. Stacking ensemble learning (SEL) can combine the advantages of multiple single machine learning algorithms to construct more stable predictive models. In this study, threshold values of stomatal conductance (gs) under different soil water stress indices (SWSIs) were proposed to assist managers in irrigation scheduling. In the present study, six irrigation treatments were established for winter wheat to simulate various soil moisture supply conditions. During the critical growth stages, gs was measured and the SWSI was calculated. A spectral camera mounted on an unmanned aerial vehicle (UAV) captured reflectance images in five bands, from which vegetation indices and texture information were extracted. The results indicated that gs at different growth stages of winter wheat was sensitive to soil moisture supply conditions. The correlation between the gs value and SWSI value was high (R2 > 0.79). Therefore, the gs value threshold can reflect the current soil water stress level. Compared with individual machine learning models, the SEL model exhibited higher prediction accuracy, with R2 increasing by 6.67–17.14%. Using a reserved test set, the SEL model demonstrated excellent performance in various evaluation metrics across different growth stages (R2: 0.69–0.87, RMSE: 0.04–0.08 mol m−2 s−1; NRMSE: 12.3–23.6%, MAE: 0.03–0.06 mol m−2 s−1) and exhibited excellent stability and accuracy. This research can play a significant role in achieving large-scale monitoring of crop growth status through UAV, enabling the real-time capture of winter wheat water deficit changes, and providing technical support for precision irrigation.

Tracking HFSE associated with high salinity fluid during HP metamorphism in the Zavkhan Terrane, Western Mongolia

Garnets often exhibit high concentrations of heavy rare-earth elements, which provide crucial insights into element mobility and fluid dynamics during metamorphism. This research reports on the distributions of trace and major elements in garnets from the Khungui eclogite of the Zavkhan Terrane in Western Mongolia. Within the eclogite sample, two types of garnets were identified, featuring dissimilar microstructures and compositional zoning: aggregate-type garnet with asymmetric zoning (Grt1) and euhedral garnet with concentric zoning (Grt2). Previous studies determined that Grt2 formation occurred in the pre-eclogite stage to eclogite facies (2.1–2.2 GPa and 580–610 °C), associated with the infiltration of high-saline fluids. The hexagonal-shaped pseudomorphs of Ti-bearing minerals associated with Grt1 suggest that the nucleation of titanite and garnet was simultaneously accelerated by the destabilization of Ti-augite during pre-eclogite metamorphism. This process could have contributed to the formation of aggregation textures, where Ti-bearing minerals are closely associated with Grt1 in the Khungui eclogite. Based on major divalent elemental composition zoning and trace element characteristics, both Grt1 and Grt2 in the Khungui eclogite are formed simultaneously from the pre-eclogite to eclogite stages. The cores (high Fe + Mg + Mn; Y + REE) of Grt1 and Grt2 are attributed to Rayleigh fractionation or a diffusion-limited uptake process. In contrast, the growth mechanisms of the Grt1 rim and Grt2 rim are distinct during the eclogite stage. The Grt1 rim is explained by a dissolution–reprecipitation, which resulted in the atoll texture observed in Grt1. The Grt2 rim (high Ca; low Y + REE) grew through a mechanism consistent with that of the Grt2 core. The major and trace element zonings of these garnets provide insights into element mobility related to Ti-bearing minerals and infiltration of high salinity fluids at different stages: (1) the mobilization of Ti and V increased under eclogite facies conditions (growth stage of garnet) compared to the pre-eclogite stage, with the mobility of Ti, Nb, Ta elements being pronounced under the exhumation stage (Rt–Ilm–Ttn2), possibly because of the infiltration of high-saline fluids and an increase in temperature, and (2) post-growth compositional modification of Grt1 was induced by a localized transport of Fe, Mg, Mn, and Ca elements in response to the replacement of ilmenite by titanite during decompression (0.1–0.5 GPa and 421–534 °C). The contrasting zoning of garnet in Khungui eclogite indicates dissimilar scales of element mobility under eclogite facies conditions (over a thin-section scale) and during decompression (up to several centimeters or beyond).

Microstructure-sensitive crystal plasticity and phase-field modeling of deformation and fracture in polycrystalline ice

The formation of crevasses in Greenland and Antarctica is primarily driven by the brittle failure of ice at low strain rates. Understanding this phenomenon requires exploring the effect of microstructural heterogeneity and anisotropic elastoplastic deformation on the fracture behavior of ice. Here, we have developed a microstructure-sensitive coupled crystal plasticity and phase-field model. This model allows us to study the plastic deformation, damage initiation and propagation under various strain rates in hexagonal open-packed polycrystalline ice, the prevailing phase on Earth. By employing a Bayesian optimization method, we derived the material parameters for the micromechanical model based on experimental results. The modeling results reveal that the activation of basal dislocations results in a brittle to ductile transition in ice at a low strain rate of 10-7s-1 under tension. At higher strain rates, the intrinsic plastic anisotropy of ice leads to heterogeneous deformation among grains and stress concentration near grain boundaries, triggering crack initiation and exacerbating the brittleness of ice. Under compression, cracks usually do not propagate throughout the specimen due to a significant decrease in stress around the crack tip upon propagation. Moreover, we found that the formation of the shear-induced basal texture at the bottom of ice layers and along glacier valley sides intensifies the brittleness of ice. This study provides insights into the micromechanical deformation and fracture mechanisms of ice, elucidating the intricate process of crevasse development in polar ice sheets.

MABDT: Multi-scale attention boosted deformable transformer for remote sensing image dehazing

Owing to the heterogeneous spatial distribution and non-uniform morphological characteristics of haze in remote sensing images (RSIs), conventional dehazing algorithms struggle to precisely recover the fine-grained details of terrestrial objects. To address this issue, a novel multi-scale attention boosted deformable Transformer (MABDT) tailored for RSI dehazing is proposed. This framework synergizes the multi-receptive field features elicited by convolutional neural network (CNN) with the long-term dependency features derived from Transformer, which facilitates a more adept restitution of texture and intricate detail information within RSIs. Firstly, spatial attention deformable convolution is introduced for computation of multi-head self-attention in the Transformer block, particularly in addressing complex haze scenarios encountered in RSIs. Subsequently, a multi-scale attention feature enhancement (MAFE) block is designed, tailored to capture local and multi-level detailed information features using multi-receptive field convolution operations, thereby accommodating non-uniform haze. Finally, a multi-level feature complementary fusion (MFCF) block is proposed, leveraging both shallow and deep features acquired from all encoding layers to augment each level of reconstructed image. The dehazing performance is evaluated on 6 open-source datasets, and quantitative and qualitative experimental results demonstrate the advancements of the proposed method in both metrical scores and visual quality. The source code is available at https://github.com/ningjin00/MABDT.

DAG‐Net: Dual‐Branch Attention‐Guided Network for Multi‐Scale Information Fusion in Lung Nodule Segmentation

ABSTRACTThe development of deep learning has played an increasingly crucial role in assisting medical diagnoses. Lung cancer, as a major disease threatening human health, benefits significantly from the use of auxiliary medical systems to assist in segmenting pulmonary nodules. This approach effectively enhances both the accuracy and speed of diagnosis for physicians, thereby reducing the risk of patient mortality. However, pulmonary nodules are characterized by irregular shapes and a wide range of diameter variations. They often reside amidst blood vessels and various tissue structures, posing significant challenges in designing an automated system for lung nodule segmentation. To address this, we have developed a three‐dimensional dual‐branch attention‐guided network (DAG‐Net) for multi‐scale information fusion, aimed at segmenting lung nodules of various types and sizes. First, a dual‐branch encoding structure is employed to provide the network with prior knowledge about nodule texture information, which aids the network in better identifying different types of lung nodules. Next, we designed a structure to extract global information, which enhances the network's ability to localize lung nodules of different sizes by fusing information from multiple resolutions. Following that, we fused multi‐scale information in a parallel structure and used attention mechanisms to guide the network in suppressing the influence of non‐nodule regions. Finally, we employed an attention‐based structure to guide the network in achieving more accurate segmentation by progressively using high‐level semantic information at each layer. Our proposed network achieved a DSC value of 85.6% on the LUNA16 dataset, outperforming state‐of‐the‐art methods, demonstrating the effectiveness of the network.

Multi-Scale convolutional neural network for finger vein recognition

With the continuous advancement of science and technology, an increasing number of deep learning methods are being applied in the field of finger vein recognition to describe the structural characteristics of finger veins. However, some deep learning methods fail to adequately extract longer texture features. during the feature extraction process, resulting in a decrease in the uniqueness of extracted finger vein features. Additionally, these methods tend to extract global information while neglecting the importance of local texture information. To address the aforementioned issues, this paper introduces a multiscale convolution network (MCNet) model based on finger vein structure. On one hand, a multiscale feature extraction (MFE) model based on the rectangular and square convolution kernels are employed to extract structural information from finger veins and to simultaneously enhance the features of longer texture features. On the other hand, the paper introduces a cross-information fusion attention (CFA) block that combines spatial and channel information, in order to enhance local details information and the network’s ability to extract vein patterns. The experimental results on the public datasets FV-USM, SDUMLA-HMT, and HKPU validate the effectiveness of MCNet with the recognition rates of 99.86%, 99.11%, and 99.15% respectively.

Multilevel Stimuli-Responsive Smart "Sandwich" Label with Physical Unclonable Functions Bionic Wrinkles and Space-Selective Fluorescence Patterns.

With the increasing popularity of the internet, it brings convenience to lives while also increases security risks. Physical Unclonable Functions (PUFs) can generate random, unclonable, and unique identifiers using their inherent physical characteristics, which have broad prospects in anti-counterfeiting. Herein, inspired by the irregular tree bark fissures and random skin wrinkles found in nature, a method for creating complex micro-wrinkles with unclonable random patterns is proposed by simply stretching hydrogels. The random texture information contained in the micro-wrinkles is digitized into binary codes using an adaptive threshold algorithm. Additionally, a novel "sandwich" label with a multilevel intelligent anti-counterfeiting system is proposed. The first-level involves photoluminescence encryption with adjustable luminescence within visible light range and modulated luminescence at different excitation wavelengths; the second-level includes strain-related mechanical encryption, and the third-level consists of highly random and unclonable micro-wrinkles. The certification difficulty increases as the anti-counterfeiting grade increases, thereby enhancing label security. Furthermore, space-selective doping of rare earth metal-organic framework (RE-MOF) fluorescent materials in hydrogels is achieved through the use of screen-printing technology. The concept of novel multilevel smart anti-counterfeiting PUF labels will further enhance current levels of counterfeiting prevention.

In-situ synchrotron high energy X-ray diffraction study on the deformation mechanisms of D019-α2 phase during high-temperature compression in a TiAl alloy

The α2 phase with an ordered hexagonal structure has a strong mechanical anisotropy. The limited plasticity interacting with crystallographic texture formation undoubtedly complicate the deformation mechanisms of the α2 phase. Taking advantage of in-situ synchrotron high energy X-ray diffraction (HEXRD), this study unveils the origin of the α2 texture and its correlation with plastic deformation. Upon loading at 800 °C, the dislocation glide in the γ phase initiates at a stress of 370 MPa and that in the α2 phase at a stress of 670 MPa. Nevertheless, the texture evolution of the α2 phase sets in in parallel with that of the γ phase, and these textures are preliminarily established at a stress of 650 MPa. A main <11 2‾ 0> fiber texture with the c axis of the α2 unit cell aligned vertically to the compression axis has been unexpectedly evolved. This texture forms primarily via rigid body rotation and is correlated with glide and twin activation in the neighboring γ phase. The preferential orientation primarily favors double prismatic glide in α2 and in addition triggers the tensile twin activation. The grain rotation caused by the tensile twin slightly affects the α2 transverse texture evolution. The results unveil a complex interaction between the α2 phase deformability, texture evolution and the combined elastic-plastic deformation of the phases γ and α2 in TiAl alloys.

Asymmetric Deformable Spatio-temporal Framework for Infrared Object Tracking

The Infrared Object Tracking (IOT) task aims to locate objects in infrared sequences. Since color and texture information is unavailable in infrared modality, most existing infrared trackers merely rely on capturing spatial contexts from the image to enhance feature representation, where other complementary information is rarely deployed. To fill this gap, we in this article propose a novel Asymmetric Deformable Spatio-Temporal Framework (ADSF) to fully exploit collaborative shape and temporal clues in terms of the objects. Firstly, an asymmetric deformable cross-attention module is designed to extract shape information, which attends to the deformable correlations between distinct frames in an asymmetric manner. Secondly, a spatio-temporal tracking framework is coined to learn the temporal variance trend of the object during the training process and store the template information closest to the tracking frame when testing. Comprehensive experiments demonstrate that ADSF outperforms state-of-the-art methods on three public datasets. Extensive ablation experiments further confirm the effectiveness of each component in ADSF. Furthermore, we conduct generalization validation to demonstrate that the proposed method also achieves performance gains in RGB-based tracking scenarios.

Multi-Modal LiDAR Point Cloud Semantic Segmentation with Salience Refinement and Boundary Perception

Point cloud segmentation is essential for scene understanding, which provides advanced information for many applications, such as autonomous driving, robots, and virtual reality. To improve the accuracy and robustness of point cloud segmentation, many researchers have attempted to fuze camera images to complement the color and texture information. The common fusion strategy is the combination of convolutional operations with concatenation, element-wise addition or element-wise multiplication. However, conventional convolutional operators tend to confine the fusion of modal features within their receptive fields, which can be incomplete and limited. In addition, the inability of encoder–decoder segmentation networks to explicitly perceive segmentation boundary information results in semantic ambiguity and classification errors at object edges. These errors are further amplified in point cloud segmentation tasks, significantly affecting the accuracy of point cloud segmentation. To address the above issues, we propose a novel self-attention multi-modal fusion semantic segmentation network for point cloud semantic segmentation. Firstly, to effectively fuze different modal features, we propose a self-cross fusion module (SCF), which models long-range modality dependencies and transfers complementary image information to the point cloud to fully leverage the modality-specific advantages. Secondly, we design the salience refinement module (SR), which calculates the importance of channels in the feature maps and global descriptors to enhance the representation capability of salient modal features. Finally, we propose the local-aware anisotropy loss measure the element-level importance in the data and explicitly provide boundary information for the model, which alleviates the inherent semantic ambiguity problem in segmentation networks. Extensive experiments on two benchmark datasets demonstrate that our proposed method surpasses current state-of-the-art methods.

Magnetic ordering and dynamics in monolayers and bilayers of chromium trihalides: atomistic simulations approach

We analyze magnetic properties of monolayers and bilayers of chromium iodide, \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\hbox {CrI}_3$$\\end{document}, in two different stacking configurations: AA and rhombohedral ones. Our main focus is on the corresponding Curie temperatures, hysteresis curves, equilibrium spin structures, and spin wave excitations. To obtain all these magnetic characteristic, we employ the atomistic spin dynamics and Monte Carlo simulation techniques. The model Hamiltonian includes isotropic exchange coupling, magnetic anisotropy, and Dzyaloshinskii-Moriya interaction. As the latter interaction is relatively weak in pristine \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\hbox {CrI}_3$$\\end{document}, we consider a more general case, when the Dzyaloshinskii-Moriya interaction is enhanced externally (e.g. due to gate voltage, mechanical strain, or proximity effects). An important issue of the analysis is the correlation between hysteresis curves and spin configurations in the system, as well as formation of the skyrmion textures.