Accurately identifying rock mass discontinuities and understanding distribution, characteristics, and properties are crucial for assessing slope stability and mitigating the risk of collapse or sliding. The automated identification of discontinuities efficiently provides valuable information such as spacing and volumetric joint count. However, determining the optimal number of clusters automatically for complex rock mass discontinuities remains a technical bottleneck. To address this difficulty, this study introduces an approach based on the fast search and find density peaks (3D-SFDP) algorithm, which autonomously determines the number of clusters by analysing spatial density distributions. Furthermore, traditional clustering algorithms struggle with nonspherical clusters when identifying rock discontinuities using 3D point clouds. In this study, a 3D Gaussian mixture model (3D-GMM) based on 3D pole projection density mapping is presented. This model is designed for handling non-spherical clustering scenarios. Combined with the DBSCAN algorithm, this approach enables precise identification of individual discontinuities. More importantly, the study innovatively introduces discontinuity density cloud maps. Building upon this identification methodology and integrating it with the geological strength index (GSI) for open-pit mine slopes, we analyse high-risk areas prone to rock sliding from a global perspective. This research provides effective data support for slope stability analysis in mining operations.

Containers are widely deployed in clouds. There are two common container architectures: operating system-level (OS-level) container and virtual machine-level (VM-level) container. Typical examples are runc and Kata. It is well known that VM- level containers provide better isolation than OS-level containers, but at a higher overhead. Although there are quantitative analyses of the performance gap between these two container architectures, they rarely discuss the performance gap under the constrained resources nrovisioned to containers. Since the high-density deployment of containers is demanding in the cloud, each container is provisioned with limited resources specified by the cgroup mechanism. In this paper, we provide an in-depth analysis of the storage and network (two key aspects) performance differences between runc and Kata under varying resource constraints. We identify configuration implications that are crucial to performance and find that some of them are not exposed by the Kata interfaces. Based on that, we propose a profiling tool to automatically offer configuration suggestions for optimizing container performance. Our evaluation shows that the auto-generated configuration can improve the performance of MySQL by up to 107% in the TPCC benchmark compared with the default Kata setup.

Abstract The rapid development of the online apparel shopping industry demands innovative solutions for high‐quality digital apparel sample displays with virtual avatars. However, developing such displays is prohibitively expensive and prone to the well‐known “uncanny valley” effect, where a nearly human‐looking artifact arouses eeriness and repulsiveness, thus affecting the user experience. To effectively mitigate the “uncanny valley” effect and improve the overall authenticity of digital apparel sample displays, we present a novel photo‐realistic portrait generation framework. Our key idea is to employ transfer learning to learn an identity‐consistent mapping from the latent space of rendered portraits to that of real portraits. During the inference stage, the input portrait of an avatar can be directly transferred to a realistic portrait by changing its appearance style while maintaining the facial identity. To this end, we collect a new dataset, Daz‐Rendered‐Faces‐HQ (DRFHQ), specifically designed for rendering‐style portraits. We leverage this dataset to fine‐tune the StyleGAN2‐FFHQ generator, using our carefully crafted framework, which helps to preserve the geometric and color features relevant to facial identity. We evaluate our framework using portraits with diverse gender, age, and race variations. Qualitative and quantitative evaluations, along with ablation studies, highlight our method's advantages over state‐of‐the‐art approaches.

At present, the mainstream technology for leachate detection in landfills is electrical resistivity tomography (ERT), known for its efficiency and nondestructive nature. However, the conventional ERT data interpretation primarily uses inversion based on structured grids, which cannot accurately simulate the complex and thin impermeable layers of landfills, leading to unreliable results. To address this issue, we propose a novel ERT observation system and a new 3-D inversion technology. In our observation system, all measuring electrodes are placed around the landfill at once, and only a limited number of transmitting sources are needed to sequentially inject current, which effectively reduces the time for data acquisition. For 3-D inversions, we employ an unstructured tetrahedral grid for fine discretization of structures at various scales. The node-based finite-element method is used for high-precision forward and adjoint forward calculations, while the gradient filtering method in combination with limited-memory quasi-Newtonian (L-BFGS) algorithm is used to update the inversion model. Numerical experiments indicate that the proposed method can mitigate the influence of thin impermeable landfill layers and provide more accurate imaging results compared to the conventional methods. In addition, we also test the effects of water-bearing layers, faults, and near-surface interferences on the leakage inversion results. The results show that the proposed method can achieve reliable high-resolution imaging under various conditions, making it an effective technique for landfill leachate detection.

The choice of data misfit measure has a great impact on the convergence of electromagnetic inversion. The conventional measure based onl2-norm tends to excessively amplify the weights of a larger misfit, inadvertently neglecting data with a smaller misfit during the inversion process, thereby diminishing the resolution to a certain degree. To solve this problem, we propose a robust inversion strategy based onl1-norm data misfit and adaptive moment estimation (Adam). In this scheme, we use the Ekblom-typel1-norm to simplify the derivative computation of the absolute value function. The Adam algorithm is further applied to optimize this type of non-smooth objective function, which incorporates momentum terms and adaptive steps, allowing it to better adapt to the irregularities in gradient changes. The inversion results obtained from both synthetic models and field measurements demonstrate that the Adam method performs considerably better than the Broyden-Fletcher-Goldfarb-Shanno (BFGS) method for optimizing thel1-l2norm of objective function. Compared with the conventionall2-norm data misfit, thel1-norm data misfit can effectively avoid excessive optimization of data with large misfits and achieve high-resolution inversion results.

Airborne electromagnetic (AEM) technology is an efficient geophysical exploration tool for investigating subsurface electrical structures. In recent years, 3-D inversion of AEM data has been developed rapidly, but it still faces challenges such as low resolution and computational efficiency. To solve these problems, we propose a multiscale shearlet-based regularization inversion algorithm by establishing the relationship between spatial resolution and shearlet coefficients in the inversion process. In the initial stage of inversion, the coarse grids and sparse measurement points data are used to recover the main subsurface structure. When the data misfit reaches a certain level, the previous results are used as the coarse scale model in the shearlet domain to recover the model with fine grids and dense measurements. By building this coarse-to-fine inversion scheme, we can well utilize the multiscale information in AEM data and effectively achieve high-resolution inversions. We demonstrate the effectiveness and practicality of our 3-D MS inversion algorithm using two synthetic examples and a field dataset from Norway. The numerical experiments show that our inversion method can effectively reduce the computational time and improve inversion resolution.

The conventional geo-electromagnetic data inversions are mostly based on gradient optimization methods. However, this type of method can only provide a single “optimal” inverse model under specific prior conditions, which cannot effectively evaluate the reliability and uncertainty of the inversion results. The widely used uncertainty quantification (UQ) methods are based on the theory of Bayesian inference. Although they have achieved success in many applications, they suffer from the curse of dimensionality and low efficiency. To overcome these problems, we propose a novel UQ strategy for geo-electromagnetic inversions based on Bayesian processes and surrogate modeling with adaptive deep neural network (DNN). In this method, an embedded DNN is used for forward modeling in the Bayesian inference to improve computational efficiency. The training of the DNN is divided into two stages. First, a predesigned small training set is used and the resulting DNN only gives a low-accuracy result. Second, this DNN is fine-tuned dynamically during the Metropolis-Hastings (M-H) sampling process, in which the training set is adaptively supplemented according to the modeling errors. Compared to the conventional data-driven approach, this dynamically adaptive constructing method of the training set can greatly reduce the training set and constantly maintain high accuracy in forward modeling. We demonstrate the effectiveness and practicality of our surrogate modeling Bayesian and analyze the effects of different sampling numbers, noise levels, prior distributions, and sampling radius. Compared with Occam’s inversion and conventional Bayesian inversions, our method shows good robustness and high accuracy, making it an effective Bayesian inversion technique.

Previous works have demonstrated that inverting magnetotelluric (MT) data jointly with gravity data can synergize the high lateral resolution of gravity and the vertical resolution of MT. However, the existing joint stabilizers usually work for structured grids instead of unstructured ones that are more powerful for characterizing complex geology. Here, we utilize the local Pearson correlation coefficient (LPCC) for the joint inversion of gravity and MT data based on unstructured grids. We first establish a background mesh by discretizing the research area into virtual rectangular grids and then enhance the structured similarity between density and resistivity via the LPCC. Compared to existing joint constraints, our method is more flexible in solving multiscale joint inversions thanks to the adjustable subdomain size. The synthetic experiments show that the joint stabilizer can recover the subsurface targets at a higher resolution, especially for gravity data, than the standalone inversions. This method is further applied to the joint inversion of gravity and MT data from the Yellowstone area and the inverted density and resistivity models are structurally consistent. Then, based on the inverted subsurface structures and incorporating the existing research, we infer that the two inverted zones with low density and low resistivity correspond to the partially molten rhyolitic and basaltic, respectively. The proposed joint constraint can be further extended to the inversion of other geophysical data.

Increased usage of additive manufacturing (AM) in various industries has solidified its role as an advanced manufacturing technique. However, there is an inherent lack of reliability in AM processes, particularly common in extrusion or deposition-based methods due to the stochastic nature of ma-terial deposition. This necessitates an intelligent manufacturing solution to address the drawbacks of AM. Thus, we propose a novel layer-wise approach toward closed-loop AM, which is capable of in-situ monitoring and repairing geometric defects. In this paper, we present a system that uses a robotic AM experimental platform that mimics a conventional open-loop fabrication setup, which we augment into a closed-loop system using two add-ons: in-situ inspection subsystem and online process correction subsystem. The in-situ inspection subsystem collects 3D point cloud scans and compares them against a reference CAD model, categorizing geometric deviations as positive or negative defects. Then the subsequent online process correction subsystem uses a re-plan and/or repair strategy to address the positive and/or negative defects, respectively. To evaluate this idea, we conducted three experiments on parts with manually induced defects to investigate the system's ability to repair those parts, thereby reducing defects, improving part accuracy, and enhancing mechanical properties. Comparing the defective and repaired parts, we observe a reduction in defect percent by volume from 10.7% to 1.3%, an improvement in geometric tolerance from 3.86% error to 0.08% error, and an increase in the part's breaking load from 4.77 kN to 6.31 kN. These experiments prove that our layer-wise closed-loop additive manufacturing approach improves the quality, tolerance, and reliability of plastic 3D printed parts, with the potential to extend to other extrusion/deposition-based AM processes, or even subtractive manufacturing and hybrid manufacturing methods.

Robotic solutions for pipeline inspection promise enhancement of human labor by automating data acquisition for pipe condition assessments, which are vital for the early detection of pipe anomalies and the prevention of hazardous leakages and explosions. Through simultaneous localization and mapping (SLAM), colorized 3D reconstructions of the pipe's inner surface can be generated, providing a more comprehensive digital record of the pipes compared to conventional vision-only inspection. Designed for generic environments, most SLAM methods suffer limited accuracy and substantial accumulative drift in confined and featureless spaces such as pipelines, due to a lack of suitable sensor hardware and state estimation techniques. In this research, we present VILL-SLAM: a dense RGB-D SLAM algorithm that combines a monocular camera (V), an inertial sensor (I), a ring-shaped laser profiler (L), and a Lidar (L) into a compact sensor package optimized for in-pipe operations. By fusing complementary visual and depth information from the color camera, laser profiling, and Lidar measurement, our method overcomes the challenges of metric scale mapping in conventional SLAM methods, despite its monocular configuration. To further improve localization accuracy, we utilize the pipe geometry to formulate two unique optimization factors that effectively constrain odometer drift. To validate our method, we conducted real-world experiments in physical pipes, comparing the performance of our approach against other state-of-the-art algorithms. The proposed SLAM framework achieved 6.6 times drift improvement with 0.84% mean odometry drift over 22 meters and a mean pointwise 3D scanning error of 0.88mm in 12-inch diameter pipes. This research represents a significant advancement in miniature in-pipe inspection, localization, and mapping sensing techniques. It has the potential to become a core enabling technology for the next generation of highly capable in-pipe robots, capable of reconstructing photo-realistic 3D pipe scans and providing disruptive pipe locating and georeferencing capabilities.

This paper presents a Video Inpainting algorithm that enables monocular-camera-laser-based pipeline inspection robots to capture both color and 3D information using only one video stream. Conventional monocular-camera-laser inspection methods are limited to capture either 2D color images or 3D point clouds since the laser tends to overexpose the actual color of the scanning area. We propose a real-time Video Inpainting method to solve this problem with minimal hardware needs that can be easily integrated with conventional pipeline profiling robots. The algorithm is accelerated by two components: a lightweight network that directly predicts the complete optical flow and simplifies the algorithm pipeline, and the Polar coordinate transformation, which significantly reduces the image processing compexity. Real-world experiments demonstrate that our online algorithm has comparable or better color estimation accuracy against state-of-the-art offline algorithms, while is capable of running at 23 frames per second (FPS) on a laptop computer with a resolution of 1024 × 1024 pixels. In addition, we verify that this method can be used for video pre-processing for downstream tasks that require high-quality visual inputs, such as Simultaneously Localization and Mapping (SLAM). To the best of our knowledge, this is the first real-time Video Inpainting algorithm that can be used for in-pipe environments, serving as an important building block for highly compact RGB-D inspection sensors and robots for the pipeline industry.

In a heterogeneous medium (usually called a rough medium) with fractured formations, the propagation of an electromagnetic (EM) field is a type of subdiffusion. Current mainstream geophysical EM data processing methods cannot be applied to data acquired on heterogeneous Earth, as they are not governed by the classic diffusion theory. To evaluate the influence of roughness on the transient EM (TEM) signal for a complex model and contribute to data inversion, we proposed a novel three-dimensional (3-D) forward modeling scheme for TEM in rough media. First, we derived the governing equation with a fractional-order time derivative for the subdiffusion of EM waves in rough media. Then, we proposed a novel time discretization using an unequal step length for the Caputo operator, which significantly reduces the total number of time steps. Finally, an implicit time-domain finite-element method using unstructured tetrahedron discretization was adopted to solve the 3-D forward problem. Furthermore, an efficient time segmentation strategy combined with parallel RHS construction was proposed to accelerate modeling. The numerical results prove that the proposed method is accurate and efficient, and will be a powerful numerical method for analyzing TEM wave propagation and processing TEM data in areas with multiscale fractures or porosity.

The flight altitude has a large effect on the airborne electromagnetic (AEM) responses. Due to the dynamic environment of the aircraft, the recorded sensor altitudes may contain errors. Research demonstrates that the AEM responses caused by a several meters altitude errors can be larger than caused by some anomalous body. Ignoring these errors will create erroneous results in AEM data interpretation. Considering that there is not yet a published 3D AEM inversion method that takes into account the flight altitude, we develop in this paper a 3D inversion algorithm for AEM with the flight height treated as an inversion parameter. For the forward modeling we use the finite element method, while for the inversion we use the Gauss-Newton optimization method. To make our inversion works for variable flight altitudes, we propose a scheme of 3D Jacobean matrix calculation for both the resistivities and flight altitudes without much increasing the computational cost. The numerical simulation result confirms that the flight altitude really has a large effect on the AEM responses. The inversions of synthetic data show that our 3D inversion method can both recover the resistivity distribution in the underground and decrease the altitude errors recorded, while the field data inversion demonstrates that our method can deliver a better inversion model with a smaller data misfit.

Abstract We present the first synthetic eyebrow matting datasets and a domain adaptation eyebrow matting network for learning domain‐robust feature representation using synthetic eyebrow matting data and unlabeled in‐the‐wild images with adversarial learning. Different from existing matting methods that may suffer from the lack of ground‐truth matting datasets, which are typically labor‐intensive to annotate or even worse, unable to obtain, we train the matting network in a semi‐supervised manner using synthetic matting datasets instead of ground‐truth matting data while achieving high‐quality results. Specifically, we first generate a large‐scale synthetic eyebrow matting dataset by rendering avatars and collect a real‐world eyebrow image dataset while maximizing the data diversity as much as possible. Then, we use the synthetic eyebrow dataset to train a multi‐task network, which consists of a regression task to estimate the eyebrow alpha mattes and an adversarial task to adapt the learned features from synthetic data to real data. As a result, our method can successfully train an eyebrow matting network using synthetic data without the need to label any real data. Our method can accurately extract eyebrow alpha mattes from in‐the‐wild images without any additional prior and achieves state‐of‐the‐art eyebrow matting performance. Extensive experiments demonstrate the superior performance of our method with both qualitative and quantitative results.

Abstract Commonly used convolutional neural networks (CNNs) usually compress high‐resolution input images. Although it reduces the computation requirements into a reasonable range, the downsampling operation causes information loss, which affects the accuracy of image classification. How to adopt high‐resolution image inputs to improve the quality of input information and thus improve the classification accuracy without changing the overall structure of the pre‐defined CNN model or increasing the model parameters is an important issue. Here, a CNN model with wavelet domain inputs is proposed to provide a solving scheme. Specifically, the proposed method applies wavelet packet transform or dual‐tree complex wavelet transform to extract information from input images with higher resolutions in the image pre‐processing stage. Some subband image channels are selected as the inputs of conventional CNNs where the first several convolutional layers are removed, so that the networks directly learn in the wavelet domain. Experiment results on the Caltech‐256 dataset and the Describable Textures Dataset with the ResNet‐50 show that the classification accuracy of our method can have a maximum improvement of 2.15% and 10.26%, respectively. These validate the effectiveness of our proposed scheme. This code is publicly available at https://github.com/BeBeBerr/wavelet‐cnn .

As an efficient geophysical exploration method, the time-domain airborne electromagnetic (AEM) data often show sign reversal in late-time channels due to induced polarization (IP) effect. The traditional imaging and inversion methods without considering the IP effect cannot recover the true electrical structure of the earth, so it is necessary to develop 3D EM forward modeling and inversion techniques with IP effect. In this paper, we propose a 3D forward modeling method for time-domain AEM with IP effect based on unstructured finite-element (FE) method. To describe the IP effect of a medium, we introduce the Cole-Cole model and transform it into fractional derivative form using frequency-time conversion. Then, we discretize it using the difference discretization format of Caputo fractional derivative. Finally, we use the vector FE method based on unstructured tetrahedral mesh and unconditionally stable second-order backward Euler’s scheme to discretize Maxwell’s equations in space and time. In this way, we can solve the 3D forward modeling problem for AEM with IP effect in time domain. We verify the accuracy of our algorithm by comparing it with the 1D semi-analytical solution for a half-space model, and then calculate EM responses for typical abnormal models and analyze the characteristics of IP effect.

Eyelashes play a crucial part in the human facial structure and largely affect the facial attractiveness in modern cosmetic design. However, the appearance and structure of eyelashes can easily induce severe artifacts in high-fidelity multi-view 3D face reconstruction. Unfortunately it is highly challenging to remove eyelashes from portrait images using both traditional and learning-based matting methods due to the delicate nature of eyelashes and the lack of eyelash matting dataset. To this end, we present EyelashNet, the first eyelash matting dataset which contains 5,400 high-quality eyelash matting data captured from real world and 5,272 virtual eyelash matting data created by rendering avatars. Our work consists of a capture stage and an inference stage to automatically capture and annotate eyelashes instead of tedious manual efforts. The capture is based on a specifically-designed fluorescent labeling system. By coloring the eyelashes with a safe and invisible fluorescent substance, our system takes paired photos with colored and normal eyelashes by turning the equipped ultraviolet (UVA) flash on and off. We further correct the alignment between each pair of photos and use a novel alpha matte inference network to extract the eyelash alpha matte. As there is no prior eyelash dataset, we propose a progressive training strategy that progressively fuses captured eyelash data with virtual eyelash data to learn the latent semantics of real eyelashes. As a result, our method can accurately extract eyelash alpha mattes from fuzzy and self-shadow regions such as pupils, which is almost impossible by manual annotations. To validate the advantage of EyelashNet, we present a baseline method based on deep learning that achieves state-of-the-art eyelash matting performance with RGB portrait images as input. We also demonstrate that our work can largely benefit important real applications including high-fidelity personalized avatar and cosmetic design.

Aiming at the problems of poor adaptability of traditional target detection algorithms and high computational resources of deep learning algorithms, a BP neural network target detection algorithm based on histogram statistics is proposed. It is based on the principle that similar areas have similar histograms. In this algorithm, the two-dimensional image information converts to the one-dimensional histogram information. We establish a three-layer neural network model, and the histogram is used as the input of the BP neural network. Compared to the traditional target detection algorithms, its complexity is low, and its efficiency and accuracy is high. The experimental results show that the fewer classification categories, the higher target detection probability. The computational complexity of the BP neural network is low, so the computational efficiency is quite high. The accuracy of target recognition is higher than 97% with SAR and optical images.

Abstract We present a novel and intuitive sketch‐based tree animation technique, targeting on generating a new type of special effect of smoothly transforming leafy trees into morphologically different new shapes. Both topological consistencies of branches and meaningful in‐between crown shapes are preserved during the transformation. Specifically, it takes a leafy tree and a user's sketch describing the silhouette of the desired crown shape under a certain viewpoint as the input. Based on a self‐adaptive multiscale cage tree representation, branches are locally transformed through a series of topology‐aware deformations, and the resulting tree conforms to the user‐designed shape, demonstrating better aesthetics compared to global single‐cage‐based methods. By interpolating the transformations, we are able to create visually pleasing shape‐preserving animations of trees transforming between two crown shapes. Our proposed framework also provides an efficient way to interactively edit leafy trees toward desired shapes, demonstrating its potential to leverage existing tree modeling frameworks by providing flexible and intuitive tree editing operations.

Abstract We present a novel morphing technique to generate pleasing visual effects between 2 topologically varying trees while preserving the topological consistency and botanical meanings of any in‐between shapes as natural trees. Specifically, we first efficiently convert leafy trees into botanically inspired chain‐lobe representations in an automatic way. With the aid of branching‐pattern aware, one‐to‐many correspondences between branches and leaves, we hierarchically interpolate branches of in‐between trees while maintaining their topological consistencies. Finally, we simultaneously interpolate foliage, specifically every single leaf, during the morphing process, avoiding the generation of unpleasant “floating” leaves. We demonstrate the effectiveness of our approach by creating visually compelling tree morphing animations, even between cross‐species.