Geometric Details Research Articles

StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

This work addresses the challenge of high-quality surface normal estimation from monocular colored inputs (i.e., images and videos), a field which has recently been revolutionized by repurposing diffusion priors. However, previous attempts still struggle with stochastic inference, conflicting with the deterministic nature of the Image2Normal task, and costly ensembling step, which slows down the estimation process. Our method, StableNormal, mitigates the stochasticity of the diffusion process by reducing inference variance, thus producing "Stable-and-Sharp" normal estimates without any additional ensembling process. StableNormal works robustly under challenging imaging conditions, such as extreme lighting, blurring, and low quality. It is also robust against transparent and reflective surfaces, as well as cluttered scenes with numerous objects. Specifically, StableNormal employs a coarse-to-fine strategy, which starts with a one-step normal estimator (YOSO) to derive an initial normal guess, that is relatively coarse but reliable, then followed by a semantic-guided refinement process (SG-DRN) that refines the normals to recover geometric details. The effectiveness of StableNormal is demonstrated through competitive performance in standard datasets such as DIODE-indoor, iBims, ScannetV2 and NYUv2, and also in various downstream tasks, such as surface reconstruction and normal enhancement. These results evidence that StableNormal retains both the "stability" and "sharpness" for accurate normal estimation. StableNormal represents a baby attempt to repurpose diffusion priors for deterministic estimation. To democratize this, code and models have been publicly available in hf.co/Stable-X.

Spatial Attention-Based Kernel Point Convolution Network for Semantic Segmentation of Transmission Corridor Scenarios in Airborne Laser Scanning Point Clouds

Accurate semantic segmentation in transmission corridor scenes is crucial for the maintenance and inspection of power infrastructure, facilitating the timely detection of potential hazards. In this study, we propose SA-KPConv, an advanced segmentation model specifically designed for transmission corridor scenarios. Traditional approaches, including Random Forest and point-based deep learning models such as PointNet++, demonstrate limitations in segmenting critical infrastructure components, particularly power lines and towers, primarily due to their inadequate capacity to capture complex spatial relationships and local geometric details. Our model effectively addresses these challenges by integrating a spatial attention module with kernel point convolution, enhancing both global context and local feature extraction. Experiments demonstrate that SA-KPConv outperforms state-of-the-art methods, achieving a mean Intersection over Union (mIoU) of 89.62%, particularly excelling in challenging terrains such as mountainous areas. Ablation studies further validate the significance of our model’s components in enhancing overall performance and effectively addressing class imbalance. This study presents a robust solution for semantic segmentation, with considerable potential for monitoring and maintaining power infrastructure.

Free Vibration of Axially Functionally Graded Porous Beams with Varying Cross-Section

This study aims to determine the natural frequencies of axially functionally graded porous material (FGPM) beams with non-uniform cross-sections under a variety of boundary conditions. Two types of pore distribution were used: even and uneven. Initially, an analytical method was used to determine the natural frequencies of FGPM beams with different cross-sections. The Fredholm integral approach was used to obtain the characteristic equations. Furthermore, the collected results are confirmed and compared to the existing literature. The artificial neural network (ANN) technique is then used to predict the fluctuations in the natural frequency of a clamped–simply supported axially FGPM beam with a non-uniform cross-section. The prediction of natural frequencies by ANN is based on a large dataset of over 1[Formula: see text]100 data points acquired from the analytical solution obtained in this study and data available in the literature. This research conducts a parametric analysis to evaluate the influence of numerous aspects, including as beam characteristics, material properties, geometric details, gradient parameters, and porosity distribution, on functionally graded (FG) beam vibration behavior. Finally, both ANN and computational analysis demonstrate that porosity distributions and non-uniform cross-sectional area have a substantial effect on the natural frequencies of axially FG beams.

CWGA-Net: Center-Weighted Graph Attention Network for 3D object detection from point clouds

The precision of 3D object detection from unevenly distributed outdoor point clouds is critical in autonomous driving perception systems. Current point-based detectors employ self-attention and graph convolution to establish contextual relationships between point clouds; however, they often introduce weakly correlated redundant information, leading to blurred geometric details and false detections. To address this issue, a novel Center-weighted Graph Attention Network (CWGA-Net) has been proposed to fuse geometric and semantic similarities for weighting cross-attention scores, thereby capturing precise fine-grained geometric features. CWGA-Net initially constructs and encodes local graphs between foreground points, establishing connections between point clouds from geometric and semantic dimensions. Subsequently, center-weighted cross-attention is utilized to compute the contextual relationships between vertices within the graph, and geometric and semantic similarities between vertices are fused to weight attention scores, thereby extracting strongly related geometric shape features. Finally, a cross-feature fusion Module is introduced to deeply fuse high and low-resolution features to compensate for the information loss during downsampling. Experiments conducted on the KITTI and Waymo datasets demonstrate that the network achieves superior detection capabilities, outperforming state-of-the-art point-based single-stage methods in terms of average precision metrics while maintaining good speed.

Feature fusion and context interaction for RGB-D indoor semantic segmentation

Depth information in indoor scenes is crucial to understanding the spatial and occluding relationships of objects. Depth information contains rich geometric details and is unaffected by lighting, texture, and color, significantly enhancing traditional color images. RGB images and depth images have been widely applied in various image analysis. However, effectively leveraging the complementary information from both modalities remains a challenge. To address this issue, we propose a unified and effective feature fusion and context interaction network (FCINet). It includes three modules. Firstly, we construct a multi-modal feature fusion module (MFFM), which can achieve the aggregation of two modalities along spatial and channel dimensions. Secondly, we construct a global and local information interaction context module (GLCM) to encode rich semantic information. Finally, we construct a feature alignment and fusion module (FAFM), which integrates upsampled low-level features with high-level features to mitigate spatial information loss. Experimental results indicate that the model achieved favorable outcomes on both the NYU Depth v2 dataset and the more complex SUN RGB-D dataset.

TaNSR:Efficient 3D Reconstruction with Tetrahedral Difference and Feature Aggregation

AbstractNeural surface reconstruction methods have demonstrated their ability to recover 3D surfaces from multiple images. However, current approaches struggle to rapidly achieve high‐fidelity surface reconstructions. In this work, we propose TaNSR, which inherits the speed advantages of multi‐resolution hash encodings and extends its representation capabilities. To reduce training time, we propose an efficient numerical gradient computation method that significantly reduces additional memory access overhead. To further improve reconstruction quality and expedite training, we propose a feature aggregation strategy in volume rendering. Building on this, we introduce an adaptively weighted aggregation function to ensure the network can accurately reconstruct the surface of objects and recover more geometric details. Experiments on multiple datasets indicate that TaNSR significantly reduces training time while achieving better reconstruction accuracy compared to state‐of‐the‐art nerual implicit methods.

DSGI‐Net: Density‐based Selective Grouping Point Cloud Learning Network for Indoor Scene

AbstractIndoor scene point clouds exhibit diverse distributions and varying levels of sparsity, characterized by more intricate geometry and occlusion compared to outdoor scenes or individual objects. Despite recent advancements in 3D point cloud analysis introducing various network architectures, there remains a lack of frameworks tailored to the unique attributes of indoor scenarios. To address this, we propose DSGI‐Net, a novel indoor scene point cloud learning network that can be integrated into existing models. The key innovation of this work is selectively grouping more informative neighbor points in sparse regions and promoting semantic consistency of the local area where different instances are in proximity but belong to distinct categories. Furthermore, our method encodes both semantic and spatial relationships between points in local regions to reduce the loss of local geometric details. Extensive experiments on the ScanNetv2, SUN RGB‐D, and S3DIS indoor scene benchmarks demonstrate that our method is straightforward yet effective.

GS‐Octree: Octree‐based 3D Gaussian Splatting for Robust Object‐level 3D Reconstruction Under Strong Lighting

AbstractThe 3D Gaussian Splatting technique has significantly advanced the construction of radiance fields from multi‐view images, enabling real‐time rendering. While point‐based rasterization effectively reduces computational demands for rendering, it often struggles to accurately reconstruct the geometry of the target object, especially under strong lighting conditions. Strong lighting can cause significant color variations on the object's surface when viewed from different directions, complicating the reconstruction process. To address this challenge, we introduce an approach that combines octree‐based implicit surface representations with Gaussian Splatting. Initially, it reconstructs a signed distance field (SDF) and a radiance field through volume rendering, encoding them in a low‐resolution octree. This initial SDF represents the coarse geometry of the target object. Subsequently, it introduces 3D Gaussians as additional degrees of freedom, which are guided by the initial SDF. In the third stage, the optimized Gaussians enhance the accuracy of the SDF, enabling the recovery of finer geometric details compared to the initial SDF. Finally, the refined SDF is used to further optimize the 3D Gaussians via splatting, eliminating those that contribute little to the visual appearance. Experimental results show that our method, which leverages the distribution of 3D Gaussians with SDFs, reconstructs more accurate geometry, particularly in images with specular highlights caused by strong lighting. The source code can be downloaded from https://github.com/LaoChui999/GS-Octree.

Experimental and numerical investigations of forced convection impingement heat transfer on plate-fin heat sinks using three different electronic cooling fans

An experimental and numerical study was conducted for plate-fin heat sinks subjected to impinging air jets produced by electronic cooling fans. One axial and two different radial fans were used and their distance to the heat sink was varied. The aluminum heat sinks had either plain fins or fins with sinusoidal surface structures, were heated by heat sources either distributed over the entire base plate or concentrated in the center. In total, temperature measurements for 264 settings were performed, and numerical simulations were carried out for 19 selected cases. The results show that the axial fan outperforms the radial fans for the investigated fan distances, that the structured fins lead to lower base plate temperatures and that significant asymmetries in the heat sink temperature distribution can occur in certain cases. The numerical simulations are used to gain a better understanding of the trends observed in the measurements. Particularly, the impact of the velocity profiles at the fan outlets and the influence of certain geometrical details of the fan design on the heat flux distributions and the airflow into the fin channels are explored. The results highlight practical problems that need to be considered when optimizing heat sink-fan combinations.

Conceptual Model of Graph-based Individual Tree and Its Utilization in Digital Twin and Metaverse of Urban Forest

Abstract. 3D city models are an important cornerstone in the development of digital twin cities, allowing for various analyses and simulations. CityGML, as an open standard for 3D city models, emphasizes five main aspects: scale or level of detail (LoD), semantics, geometry, topology, and appearance. One of the important elements in CityGML 3D city models is representation of vegetation. Vegetation in CityGML, especially individual trees, is still limited in terms of detail and resolution, reducing its effectiveness for specific applications. This paper proposes a graph-based conceptual model for individual trees that conforms to the CityGML v2.0 specification. The model refers to the morphological structure of a tree consisting of roots, trunk, and crown (including branches, twigs, and leaves), and considers the five main aspects of CityGML. By enhancing semantic information and geometric details, the model aims to provide an information-rich and realistic representation of individual trees in a 3D city environment. The 3D tree model created based on this conceptual model may be applicable in the development of digital twin urban forests and virtual forest simulations that utilize immersive technologies such as the metaverse. This research opens up new opportunities in the development of solitary vegetation objects through CityGML ADE by including more detailed semantic and topological information.

EIDU-Net: edge-preserved inception DenseGCN U-Net for LiDAR point cloud segmentation

With the development of laser scanners and machine learning, point cloud semantic segmentation plays a significant role in autonomous driving, scene reconstruction, human-computer interaction, and other fields. In recent years, point cloud semantic segmentation based on deep learning has become one of the key research directions in point cloud processing. Due to the limited ability to exploit geometric details and contextual information in point clouds, most methods that adopt encoder-decoder architecture lose local structural information easily, especially detailed features, and extract features insufficiently. To address this issue, the edge-preserving inception DenseGCN U-Net (entitled as EIDU-Net) is proposed. EIDU-Net makes full use of the complementation between geometric details in the original point cloud and high-level features. The edge-preserved graph pooling (EGP) layer, the key module of the EIDU-Net, is designed to retain additional edge feature information from the original point cloud during pooling operations. Accordingly, the edge-preserved graph unpooling (EGU) layer can restore the feature graph more efficiently based on the additionally retained edge features. Extensive experiments demonstrate that our proposed EIDU-Net has remarkable improvements on semantic segmentation tasks under whatever S3DIS or Terracotta Warrior fragments. Our code is publicly available at https://github.com/caoxin918/EIDU-Net.

The Concept of Levels of Detail for 3D Niche Models in CityGML

Abstract. Buddhist niches in grottoes can be represented in three-dimensional (3D) for their detailed geometries on surfaces by using triangular meshes generated from point clouds. However, not all applications require 3D models with high geometric detail. The mesh models of niches have drawbacks such as large data volumes, lack of semantic information, and absence of spatial relationships between structural components and members within niches. Those limitations make mesh models suitable only for visualization and challenging to use directly in tasks like spatial analysis, simulation experiments, mechanical analysis, and disease investigation. To address this problem, this study defines four Levels of Detail (LoDs) for Buddhist niches, ranging from LoD0 to LoD3, drawing on the concept of LoDs for urban buildings in CityGML 3.0. As the LoD level increases, 3D models contain more detailed geometries, including spatial points, bounding boxes, niche structural components, and component members. Those 3D models at different LoDs can represent niches with varying degrees of abstraction, making them suitable for different applications and guiding the production of standardized 3D semantic models. To validate the feasibility of the LoDs definition for Buddha niches, this paper reconstructs 3D models of niches at different LoDs based on high-precision mesh models. Finally, a comparison is made between the original mesh model and models at different LoDs in terms of data size and potential application scenarios.

Isothermal Flow Field Characterization of a Full-Scale Sector Combustor at Elevated Pressures

Abstract An experimental investigation in a sector (20 deg) of full-scale annular gas turbine combustor is performed. The sector combustor is optically accessible for the flow and flame visualization of the primary and exit zones of the combustor. The distinctive feature of the experimental setup is that it preserves the geometrical details of an annular combustor that includes the casing, dome and combustor liner. The combustor design features a series of primary and secondary dilution holes with multiple film cooling strips on the outer and inner liner. In the present study, the combustor is operated at inlet Mach numbers of 0.02–0.3 at operating absolute pressures of 1–5 bar. Static pressure measurements are performed at multiple locations in the rig to characterize the pressure drop across the combustor. Two-dimensional particle image velocimetry (PIV) is performed to measure the velocity fields of the primary and exit zones of the combustor simultaneously. The results show the presence of a central recirculation zone (CRZ), high-velocity annular jets, and a pair of dilution jets in the primary zone of the combustor. The steady-state flow structures are invariant of inlet Mach number and pressures. The relationship between the relative pressure drop across the combustor and the combustor inlet condition is obtained. Mass flowrate and momentum flux are calculated for the flow through the swirler, central recirculation zone, the primary dilution jets, and the exit zone. The paper shows how the flow structures in a realistic combustor change with variations in global combustor parameters.

Semantic Enrichment of Non-Graphical Data of a BIM Model of a Public Building from the Perspective of the Facility Manager

Building information modeling (BIM) is undeniably the most important trend in the digitization of the construction sector in recent years. BIM models currently being built are extremely geometrically rich, that is, they are modeled at a high level of detail in terms of geometry. Thanks to object-oriented programming paradigms, BIM models include high-level relationships to ensure interactions between objects, rapid view generation, and documentation. However, these models are not always equally rich in non-graphical data. This is true for parameters at the library object level, with which building object models are saturated, but also at the project, site, building, or floor levels according to the structure of the interoperable industry foundation classes (IFC) format. The current state of knowledge also lacks a clear methodology for inputting such data. For this reason, experimental work was undertaken on semantic enrichment in non-graphical data of a public building (a public kindergarten, Secemin, Poland), which has its BIM model at a high level of geometric detail but is poor in non-graphical data. As a result of the research and development work, all levels of the IFC structure were saturated with non-graphical data and validated, and the possibilities of their use were shown from the perspective of the facility manager. Documentation from the manager was used to achieve this goal, and selected analyses and simulations were performed on the enriched model. This article contributes to the discussion on semantic enrichment from CAD3D to BIM by presenting a detailed process for entering non-graphical data into a BIM model. The presented data entry method can be used by both modelers and facility managers. Thus, this paper fills an important research gap related to semantic enrichment in non-graphical data at different levels of the IFC structure.

Numerical assessments of geometry, proximity and multi-electrode effects on electroporation in mitochondria and the endoplasmic reticulum to nanosecond electric pulses

Most simulations of electric field driven bioeffects have considered spherical cellular geometries or probed symmetrical structures for simplicity. This work assesses cellular transmembrane potential build-up and electroporation in a Jurkat cell that includes the endoplasmic reticulum (ER) and mitochondria, both of which have complex shapes, in response to external nanosecond electric pulses. The simulations are based on a time-domain nodal analysis that incorporates membrane poration utilizing the Smoluchowski model with angular-dependent changes in membrane conductivity. Consistent with prior experimental reports, the simulations show that the ER requires the largest electric field for electroporation, while the inner mitochondrial membrane (IMM) is the easiest membrane to porate. Our results suggest that the experimentally observed increase in intracellular calcium could be due to a calcium induced calcium release (CICR) process that is initiated by outer cell membrane breakdown. Repeated pulsing and/or using multiple electrodes are shown to create a stronger poration. The role of mutual coupling, screening, and proximity effects in bringing about electric field modifications is also probed. Finally, while including greater geometric details might refine predictions, the qualitative trends are expected to remain.

Beyond the root: Geometric characterization for the diagnosis of syndromic heritable thoracic aortic diseases

Syndromic heritable thoracic aortic diseases (sHTAD), such as Marfan (MFS) or Loeys–Dietz (LDS) syndromes, involve high risk of life threatening aortic events. Diagnosis of syndromic features alone is difficult, and negative genetic tests do not necessarily exclude a genetic or hereditary condition. Periodic 3D imaging of the aorta is recommended in patients with aortic disease. Thus, an imaging-based approach aimed at identifying unique features of aortic geometry can be highly effective for diagnosing sHTAD and assessing risk. In this study, we present a method that can help identify the manifestations of sHTAD by focusing on the entire geometry of the thoracic aorta, rather than only using measurements of dilation of the aortic root. We analyze the geometric phenotype of 97 patients with genetically confirmed sHTAD (79 MF and 18 LDS) and of 45 healthy volunteers, using 3D aorta meshes obtained from phase contrast-enhanced magnetic resonance angiograms computed from 4D flow cardiac magnetic resonance. We build a geometric encoding of the aorta, based on a vessel coordinate system, and use several mathematical models to discriminate between controls and patients with sHTAD: a baseline scenario, based on aortic root dimensions only, a descriptor typically used in sHTAD patients; a low dimensional scenario, with a reduce encoding using principal component analysis; and a high-dimensional scenario, which included the full coefficient representation for geometry encoding, aiming to capture finer geometric details. The results indicate that considering the anatomy of the whole thoracic aorta can improve predictive ability. We achieve precision and sensitivity values over 0.8, with a specificity of over 70% in all the models used, while a single value classifiers (based only on aortic root diameter) demonstrated a trade-off between sensitivity and specificity. Using the mathematical properties of the vessel coordinate system representation, feature importance is mapped onto a set of anatomical traits that are used by the models to do the classification, thus providing interpretability of the results. This analysis indicates that in addition to the diameter of the aortic root, aortic elongation and a narrowing of the descending thoracic aorta may be markers of positive sHTAD.

DCW-YOLO: An Improved Method for Surface Damage Detection of Wind Turbine Blades

Wind turbine blades (WTBs) are prone to damage from their working environment, including surface peeling and cracks. Early and effective detection of surface defects on WTBs can avoid complex and costly repairs and serious safety hazards. Traditional object detection methods have disadvantages of insufficient detection capabilities, extended model inference times, low recognition accuracy for small objects, and elongated strip defects within WTB datasets. In light of these challenges, a novel model named DCW-YOLO for surface damage detection of WTBs is proposed in this research, which leverages image data collected by unmanned aerial vehicles (UAVs) and the YOLOv8 algorithm for image analysis. Firstly, Dynamic Separable Convolution (DSConv) is introduced into the C2f module of YOLOv8, allowing the model to more effectively focus on the geometric structural details associated with damage on WTBs. Secondly, the upsampling method is replaced with the content-aware reassembly of features (CARAFE), which significantly minimizes the degradation of image characteristics throughout the upsampling process and boosts the network’s ability to extract features. Finally, the loss function is substituted with the WIoU (Wise-IoU) strategy. This strategy allows for a more accurate regression of the target bounding boxes and helps to improve the reliability in the localization of WTBs damages, especially for low-quality examples. This model demonstrates a notable superiority in surface damage detection of WTBs compared to the original YOLOv8n and has achieved a substantial improvement in the mAP@0.5 metric, rising from 91.4% to 93.8%. Furthermore, in the more rigorous mAP@0.5–0.95 metric, it has also seen an increase from 68.9% to 71.2%.

Generalized Lipschitz Tracing of Implicit Surfaces

AbstractWe present a versatile and robust framework to render implicit surfaces defined by black‐box functions that only provide function value queries. We assume that the input function is locally Lipschitz continuous; however, we presume no prior knowledge of its Lipschitz constants. Our pre‐processing step generates a discrete acceleration structure, a Lipschitz field, that provides data to infer local and directional Lipschitz upper bounds. These bounds are used to compute safe step sizes along rays during rendering. The Lipschitz field is constructed by generating local polynomial approximations to the input function, then bounding the derivatives of the approximating polynomials. The accuracy of the approximation is controlled by the polynomial degree and the granularity of the spatial resolution used during fitting, which is independent from the resolution of the Lipschitz field. We demonstrate that our process can be implemented in a massively parallel way, enabling straightforward integration into interactive and real‐time modelling workflows. Since the construction only requires function value evaluations, the input surface may be represented either procedurally or as an arbitrarily filtered grid of function samples. We query the original implicit representation upon ray trace, as such, we preserve the geometric and topological details of the input as long as the Lipschitz field supplies conservative estimates. We demonstrate our method on both procedural and discrete implicit surfaces and compare its exact and approximate variants.

NeRF-based Polarimetric Multi-view Stereo

In this paper, we introduce NeRF-based Polarimetric Multi-view Stereo (NPMVS), a novel 3D reconstruction method that combines the advantages of neural radiance field (NeRF) and shape-from-polarization (SfP) to address the challenge posed by textureless areas while preserving the fine-scale geometric details. Our method first leverages neural rendering to yield depth priors for each input view, subsequently estimates more accurate depths and normals using polarimetric refinement. We further introduce a pixel-wise depth rectification process to address the scaling problem inherent to the polarimetric refinement procedure. In addition, we contribute a new realistic pBRDF-based multi-view synthetic dataset, comprised of RGB and polarization images rendered under real-world lighting conditions, which will serve as a valuable resource for future research in this field. Experimental evaluations on both synthetic and real-world datasets validate the superiority of NPMVS, demonstrating its advantage over other state-of-the-art multi-view stereo and shape-from-polarization methods.

Knowledge-based model generation for aircraft cabin noise prediction from pre-design data

The climate targets set out in the “European Green Deal” call for the consideration and implementation of climate-friendly propulsion concepts and sustainable fuels in future aircraft configurations. This puts the use of very efficient propeller engines into the focus of aircraft design. However, these pose major challenges, especially to cabin acoustics, due to high, tonal sound pressure levels on the fuselage. The design of noise control measures requires the competence to predict the resulting interior noise as early as possible in the design process of the vehicle. This requires a high level of geometric and structural detail regarding the fuselage structure and cabin components. With increasing frequency range, the necessary structural details also increase, which have to be resolved in the simulation models due to the associated decreasing structural wavelength. Especially in the context of aircraft pre-design, there is usually not enough information available for a detailed vibro-acoustic modeling of the fuselage and cabin components, which allows a meaningful prediction of the vibrations and thus the cabin noise. Therefore, the knowledge-based tool Fuselage Geometry Assembler (FUGA) is developed for the targeted enrichment of preliminary design data with knowledge for detailed numerical analyses. This paper describes the knowledge-based geometry and model generation in FUGA, which can consider the necessary (increasing) level of detail for the vibro-acoustic prediction already in the preliminary design. For this purpose, aircraft data sets in the preliminary design data format Common Parametric Aircraft Configuration Schema (CPACS) form the modeling basis. Originating from the aircraft preliminary design, these initially describe the outer shell of the vehicle and are extended by detailed structural information that defines the geometric boundary conditions for component placement in cabin design. For the cabin components, the open-source geometry kernel Open Cascade Technology (OCCT) is used to provide geometries at the level of detail required for subsequent analyses. The geometry models are then discretized in open source (e.g. Gmsh) or commercial meshers and further used for numerical analysis. Finally, the prediction of cabin noise is demonstrated as a Proof of Concept using the example of a short-haul propeller-driven aircraft and the feasibility of the proposed method is indicated by investigating the sensitivity of resulting simulation models to the fuselage skin thickness.