Object Geometry Research Articles

Unsupervised 3D Object Segmentation of Point Clouds by Geometry Consistency.

In this paper, we study the problem of 3D object segmentation from raw point clouds. Unlike existing methods which usually require a large amount of human annotations for full supervision, we propose the first unsupervised method, called OGC, to simultaneously identify multiple 3D objects in a single forward pass, without needing any type of human annotations. The key to our approach is to fully leverage the dynamic motion patterns over sequential point clouds as supervision signals to automatically discover rigid objects. Our method consists of three major components, 1) the object segmentation network to directly estimate multi-object masks from a single point cloud frame,2)the auxiliary self-supervised scene flow estimator,and 3)our core object geometry consistency component. By carefully designing a series of loss functions, we effectively take into account the multi-object rigid consistency and the object shape invariance in both temporal and spatial scales. This allows our method to truly discover the object geometry even in the absence of annotations. We extensively evaluate our method on five datasets, demonstrating the superior performance for object part instance segmentation and general object segmentation in both indoor and the challenging outdoor scenarios. Our code and data are available at https://github.com/vLAR-group/OGC.

Structure tensor-based Gaussian kernel edge-adaptive depth map refinement with triangular point view in images

<span lang="EN-US">Image reconstruction is the process of restoring the image resolution. In 3D image reconstruction, the objects in different viewpoints are processed with the triangular point view (TPV) method to estimate object geometry structure for 3D model. This work proposes a depth refinement methodology in preserving the geometric structure of objects using the structure tensor method with a Gaussian filter by transforming a series of 2D input images into a 3D model. The computation of depth map errors can be found by comparing the masked area/patch with the distribution of the original image's greyscale levels using the error pixel-based patch extraction algorithm. The presence of errors in the depth estimation could seriously deteriorate the quality of the 3D effect. The depth maps were iteratively refined based on histogram bins number to improve the accuracy of initial depth maps reconstructed from rigid objects. The existing datasets such as the dataset tanks and unit (DTU) and Middlebury datasets, were used to build the model out of the object scene structure. The results of this work have demonstrated that the proposed patch analysis outperformed the existing state of the art models depth refinement methods in terms of accuracy.</span>

Validity of Thin Element Approximation in diffractometry of opaque thick objects

The Thin Element Approximation (TEA) is widely used in diffraction analyses since it can be applied in efficient plane-to-plane propagation algorithms. While refinements have been developed for dielectric objects to obtain more accurate results, TEA is assumed precise for opaque objects. However, through numerical simulations presented in this work, based on Wave Propagation Method, we analyze the tendency of TEA to overestimate the dimensions of opaque objects in diffractometry. This effect was acknowledged in the case of cylinders, and we obtain similar results for the case of rectangular thick strips. On the other hand, TEA demonstrates a high level of accuracy when applied to objects with thickness concentrated at the center and thin edges, such as the isosceles triangular obstacle. Finally, we analyze objects whose shape is defined using the superellipse function, which is chosen for its versatility in generating objects of equivalent width and maximum thickness but with different shapes just changing a single parameter. Our results highlight the importance of considering the object geometry when employing this approximation in diffraction studies of opaque three-dimensional objects.

Impact of [formula omitted] theory on the geometry of charged stellar objects

The main objective of this article is to study the viable charged compact stellar structures in f(R,φ,χ) theory, where R, φ and χ denote the Ricci scalar, scalar field and kinetic term, respectively. For this purpose, a static spherical metric with anisotropic matter configuration is considered to analyze the compact stellar structures. We consider a particular model of this modified theory to formulate the explicit expressions of energy density and pressure components that govern the relationship between matter and geometry. The unknown constants in the Finch–Skea solutions are determined by the smooth matching of interior and exterior spacetimes to analyze the configuration of the proposed stellar structures. Physical parameters such as matter variables, energy bounds and equation of state parameters are analyzed to examine the viability of the considered stellar objects. Further, we use sound speed and adiabatic index methods to examine the stability of the compact objects. The rigorous analysis and satisfaction of necessary conditions lead to the conclusion that the stellar objects studied in this framework are viable and stable in the presence of charge.

A feature selection method for multimodal multispectral LiDAR sensing

Optical remote sensing techniques can indicate the properties of objects by observing different modalities (physical quantities) of the backscattered light at different optical wavelengths. Established examples are reflectance, fluorescence, Raman, or depolarization spectroscopy. LiDAR sensing, on the other hand, allows acquiring the geometry of objects by measuring the propagation delay of optical probing signals. Multimodal multispectral (MM) LiDAR combines these capabilities and extends conventional monochromatic LiDAR in both spectral and modal dimensions within a single instrument, thus enriching point cloud data with non-geometric information. The potentially high dimension of MM LiDAR data, however, poses significant challenges for instrumental design, data acquisition, and data processing. MM LiDAR data are structured as several or all modalities are available in each of the spectral channels. The above challenges can thus be mitigated by feature selection (FS), if the structure of the features is taken into account, i.e., if entire spectral channels or entire modalities are selected or omitted. Herein, we focus on the feature selection method for MM LiDAR and propose a multiclass group feature selection algorithm (MGSVM FS) consisting of a structural sparsity-based embedded feature selection method with an all-in-one support vector machine (SVM). It tackles jointly the challenges arising from the high dimension of the MM data and the need for a multiclass classification task while exploiting the structure of the MM data. In addition, we introduce a complete workflow for evaluating the feature selection and for decision-making. We apply the framework to selecting an optimum spectral and modal configuration for remote material classification using an experimental MM LiDAR system that provides reflectance, distance, and degree of linear polarization in 28 spectral channels of 10 nm width. For the experimental investigation, we use MM LiDAR data obtained in a controlled lab environment from thirty specimens of four material classes relevant for construction. Using all three modalities, we find a configuration with only 3 spectral channels that achieves a classification mean-F1 score of 100% within this small dataset. Similar classification performance can also be achieved with only two modalities when using more spectral channels. MGSVM FS improves the classification mean-F1 score by up to 25% as compared to random selection and outperforms two other commonly used filter and embedded feature selection methods, in this application example. The proposed group feature selection algorithm and decision-making are useful for MM LiDAR, providing a link between instrumental design, data acquisition, and data processing. However, they are also transferable to other application fields related to multiclass classification, regression, and knowledge discovery, with features structured in groups. The collected MM feature dataset, the MGSVM FS algorithm, and the evaluation pipeline are accessible online.11https://github.com/yuhan-yhyh/Dataset_Code_MGSVM-FS-MM-LiDAR.git.

Evaluation of Sabo Infrastructure Using UAV/Drone Technology for Monitoring and Inspection Data (Case Study: Sabo Dam Bakalan, Cangkringan District, Sleman)

The sabo dam serves as a structure positioned along a river branch, intended to manage and contain sediment for either a temporary or permanent duration, functioning as a system to combat potential disasters caused by erosion and sedimentation. Given the significance of sabo infrastructure in mitigating sediment- related calamities, it is essential to uphold and advance these structures through continuous monitoring, necessitating timely access to detection data. However, the inspection and monitoring of sabo buildings present considerable challenges, including the extensive coverage area of the river and the difficulty in accessing various building locations.To address these challenges, alternative approaches are being employed for the inspection and monitoring of sabo buildings. One such approach involves the utilization of drone-based asset survey technology. This technology enables the recording of precise object geometries and the generation of structural information that can be validated on-site, particularly in the context of infrastructure conditions related to sabo dams. By integrating drone technology, it is anticipated that the process of inspecting and monitoring buildings and land areas surrounding sabo dams can be expedited, with increased precision and enhanced safety measures.

АНАЛІЗ АЛГОРИТМІВ ВИЯВЛЕННЯ ЗІТКНЕНЬ У ТРИВИМІРНИХ ВІРТУАЛЬНИХ СЕРЕДОВИЩАХ

The problem addressed in this paper concerns the real-time detection of collisions in virtual environments, which can consume a significant portion of computational re-sources, particularly in complex simulations with numerous objects. Ensuring a minimum frame rate of 30 FPS is crucial for user-friendly simulations. The focus is on the narrow phase of collision detection, where objects in close proximity are examined for potential collisions. This paper proposes a collision detection algorithm leveraging Directed Bounding Parallels (AABB) R-tree structure and Oriented Bounding Parallelepiped Inter-section (OAABB) method to address this phase efficiently. Experimental results demon-strate the effectiveness of the algorithm in detecting intersections with high interaction rates. Various publicly available toolkits exist for narrow phase collision detection, em-ploying different bounding volume hierarchies and constraint volumes. Comparing these approaches is challenging due to performance variations influenced by factors such as object shapes, contact types, and model sizes. Nonetheless, these algorithms are crucial for accurately detecting collisions in virtual environments and gaming applications. Bounding Volume Hierarchies (BVH), commonly used for collision detection, organ-ize object geometry and improve performance by reducing test pair numbers through vol-ume constraints. The proposed algorithm utilizes R-tree hierarchies of directed bounding parallelepipeds and OAABB to enhance collision detection efficiency by minimizing up-date and intersect operations. The choice of constraint volume type impacts collision de-tection performance, with oriented parallelepipeds offering faster intersections. To expedite collision detection, each feature is represented by an R-tree data struc-ture in its local coordinate system. Hierarchical trees are constructed by grouping adja-cent surfaces, with leaves indicating surface geometry. Additionally, R-trees are em-ployed to spatially organize triangles within surfaces to quickly discard non-intersecting triangles. The algorithm leverages OAABB, a concept involving the common volume between two oriented bounding parallelepipeds, to filter out primitives that cannot intersect. Tra-versal algorithms are utilized to reduce the number of node visits, addressing inefficien-cies observed in traditional schemes. OAABB contributes significantly to reducing volume refresh operations. Experimental evaluations demonstrate the proposed algorithm's efficacy in real-world industrial applications, achieving interactive performance. Comparisons with al-ternative methods highlight the algorithm's effectiveness in collision detection. Overall, the proposed approach offers a robust solution to the narrow phase collision detection problem in virtual environments.

A Reflective Object Reconstruction Method Based on Neural Radiance Field

We propose a neural rendering-based 3D reconstruction method for reconstructing the geometry and BRDF of reflective objects from multi-view images captured in unknown environments. Multi-view reconstruction of reflective objects is extremely challenging because specular reflections are view-dependent and therefore violate multi-view consistency, which is the cornerstone of most multi-view reconstruction methods. Recent neural rendering techniques can model the interaction between ambient light and object surfaces to adapt to view-dependent reflections, making it possible to reconstruct reflective objects from multi-view images. However, accurately modeling ambient light in neural rendering is difficult. We propose a two-step approach to solve this problem. First, by introducing view-dependent photometric losses, our method accurately reconstructs the geometry of reflective objects. Then, with the object geometry fixed, we use more accurate sampling to recover the BRDF of the ambient light and object. Experiments show that our method is able to accurately reconstruct the geometry and BRDF of reflective objects from only RGB images without knowing the ambient light and object masks.

Explicit3D: Graph network with spatial inference for single image 3D object detection

Indoor 3D object detection is an essential task in single image scene understanding, impacting spatial cognition fundamentally in visual reasoning. Existing works on 3D object detection from a single image either pursue this goal through independent predictions of each object or implicitly reason over all possible objects, failing to harness relational geometric information between objects. To address this problem, we propose a sparse graph-based pipeline named Explicit3D based on object geometry and semantics features. Taking the efficiency into consideration, we further define a relatedness score and design a novel dynamic pruning method via group sampling for sparse scene graph generation and updating. Furthermore, our Explicit3D introduces homogeneous matrices and defines new relative loss and corner loss to model the spatial difference between target pairs explicitly. Instead of using ground-truth labels as direct supervision, our relative and corner loss are derived from homogeneous transforms, which renders the model to learn the geometric consistency between objects. The experimental results on the SUN RGB-D dataset demonstrate that our Explicit3D achieves better performance balance than the-state-of-the-art.

Formal method for selecting rough datum in part machining using graphs of dimensional relationships

We set out to determine formal conditions for selecting rough datum surfaces and rules for specifying the relationships between the surfaces of the workpiece and the part machined by metal-cutting equipment. The research was based on the geometry of non-ideal objects, which represents the geometric configuration of the part or workpiece in the form of a set of surfaces (S) arranged in strict accordance with a set of linear and angular dimensional relationships (V) in a sixdimensional geometric space. The representation of dimensional relationships in each of the six dimensions was performed using graph theory. The algorithm described in the works of V.G. Starostin and V.E. Lelyukhin was used for modeling the process of sequential surface machining. The question of selection of rough datum surfaces was considered. Here, the selection criterion is the possibility of automatic formation of machining sequence without recalculation of the dimension chains defined in the drawing. This criterion eliminates the problem of significant toughening of tolerances and additional

Reconstruction of transparent objects using phase shifting profilometry based on diffusion models

Phase shifting profilometry is an important technique for reconstructing the three-dimensional (3D) geometry of objects with purely diffuse surfaces. However, it is challenging to measure the transparent objects due to the pattern aliasing caused by light refraction and multiple reflections inside the object. In this work, we analyze the aliasing fringe pattern formation for transparent objects and then, propose to learn the front surface light intensity distribution based on the formation principle by using the diffusion models for generating the non-aliased fringe patterns reflected from the front surface only. With the generated fringe patterns, the 3D shape of the transparent objects can be reconstructed via the conventional structured light. We show the feasibility and performance of the proposed method on the data of purely transparent objects that are not seen in the training stage. Moreover, we found it could be generalized to other cases with local-transparent and translucent objects, showing the potential capability of the diffusion based learnable framework in tackling the problems of transparent object reconstruction.

Classification of architectural and MEP BIM objects for building performance evaluation

Numerous factors in current workflows reduce the completeness, accuracy, and reliability of the information exchanged between Building Information Modelling (BIM) authoring tools and building performance simulation and analysis software. Automated classification of BIM objects could ameliorate most of the interoperability problems. However, architectural, structural, mechanical, electrical, and plumbing (MEP), and other building objects have a wide range of shapes, features, and properties, which makes identifying them reliably and accurately with any single AI tool difficult. This study explored methods and techniques for automated classification of architectural and MEP BIM objects that can significantly reduce or eliminate the manual effort required to correct data exchange and interoperability issues in pre-processing building models for performance evaluation. A series of ensemble models using a stacking mechanism of four classification tools (semantic keyword search, rule-based inferencing, machine learning using object geometry features, and deep learning using visual shape features) were implemented and tested. A BIM object dataset with 3,410 instances belonging to 40 classes was compiled for training and testing the models. The dataset contains diverse architecture and MEP objects with high-quality selected instances and is available for public use. We found that an ensemble learning approach that exploits the various types of information available in instance models may exhibit superior object classification performance than any individual tool. The ensemble model applying all four tools achieved 91.0 % accuracy (F1 score 0.88), suggesting that automated classification using ensemble learning is an effective strategy.

Impact of energy-momentum squared gravity on the geometry of stellar objects

This paper investigates the impact of energy–momentum squared gravity on the geometry of anisotropic compact stellar objects. In this perspective, we use the Tolman IV solution to examine the configuration of static spherically symmetric structures. The values of unknown constants are found by the first fundamental form of Darmois junction conditions. We consider four different models of this theory to analyze the behavior of physical quantities such as effective fluid parameters, anisotropy, energy constraints and equation of state parameters in the interior of considered compact stars. Sound speed and adiabatic index methods are used to determine the stability of proposed compact stars. It is found that the proposed compact stars are viable and stable in energy–momentum squared gravity.

In-Hand 3D Object Reconstruction from a Monocular RGB Video

Our work aims to reconstruct a 3D object that is held and rotated by a hand in front of a static RGB camera. Previous methods that use implicit neural representations to recover the geometry of a generic hand-held object from multi-view images achieved compelling results in the visible part of the object. However, these methods falter in accurately capturing the shape within the hand-object contact region due to occlusion. In this paper, we propose a novel method that deals with surface reconstruction under occlusion by incorporating priors of 2D occlusion elucidation and physical contact constraints. For the former, we introduce an object amodal completion network to infer the 2D complete mask of objects under occlusion. To ensure the accuracy and view consistency of the predicted 2D amodal masks, we devise a joint optimization method for both amodal mask refinement and 3D reconstruction. For the latter, we impose penetration and attraction constraints on the local geometry in contact regions. We evaluate our approach on HO3D and HOD datasets and demonstrate that it outperforms the state-of-the-art methods in terms of reconstruction surface quality, with an improvement of 52% on HO3D and 20% on HOD. Project webpage: https://east-j.github.io/ihor.

Learning Explicit Contact for Implicit Reconstruction of Hand-Held Objects from Monocular Images

Reconstructing hand-held objects from monocular RGB images is an appealing yet challenging task. In this task, contacts between hands and objects provide important cues for recovering the 3D geometry of the hand-held objects. Though recent works have employed implicit functions to achieve impressive progress, they ignore formulating contacts in their frameworks, which results in producing less realistic object meshes. In this work, we explore how to model contacts in an explicit way to benefit the implicit reconstruction of hand-held objects. Our method consists of two components: explicit contact prediction and implicit shape reconstruction. In the first part, we propose a new subtask of directly estimating 3D hand-object contacts from a single image. The part-level and vertex-level graph-based transformers are cascaded and jointly learned in a coarse-to-fine manner for more accurate contact probabilities. In the second part, we introduce a novel method to diffuse estimated contact states from the hand mesh surface to nearby 3D space and leverage diffused contact probabilities to construct the implicit neural representation for the manipulated object. Benefiting from estimating the interaction patterns between the hand and the object, our method can reconstruct more realistic object meshes, especially for object parts that are in contact with hands. Extensive experiments on challenging benchmarks show that the proposed method outperforms the current state of the arts by a great margin. Our code is publicly available at https://junxinghu.github.io/projects/hoi.html.

Three-dimensional object geometry of mitochondria-associated signal: 3-D analysis pipeline for two-photon image stacks of cerebrovascular endothelial mitochondria.

Increasing evidence indicates the role of mitochondrial and vascular dysfunction in aging and aging-associated pathologies; however, the exact mechanisms and chronological processes remain enigmatic. High-energy demand organs, such as the brain, depend on the health of their mitochondria and vasculature for the maintenance of normal functions, therefore representing vulnerable targets for aging. This methodology article describes an analysis pipeline for three-dimensional (3-D) mitochondria-associated signal geometry of two-photon image stacks of brain vasculature. The analysis methods allow the quantification of mitochondria-associated signals obtained in real time in their physiological environment. In addition, signal geometry results will allow the extrapolation of fission and fusion events under normal conditions, during aging, or in the presence of different pathological conditions, therefore contributing to our understanding of the role mitochondria play in a variety of aging-associated diseases with vascular etiology.NEW & NOTEWORTHY Analysis pipeline for 3-D mitochondria-associated signal geometry of two-photon image stacks of brain vasculature.

Three-Dimensional Reconstruction Pre-Training as a Prior to Improve Robustness to Adversarial Attacks and Spurious Correlation.

Ensuring robustness of image classifiers against adversarial attacks and spurious correlation has been challenging. One of the most effective methods for adversarial robustness is a type of data augmentation that uses adversarial examples during training. Here, inspired by computational models of human vision, we explore a synthesis of this approach by leveraging a structured prior over image formation: the 3D geometry of objects and how it projects to images. We combine adversarial training with a weight initialization that implicitly encodes such a prior about 3D objects via 3D reconstruction pre-training. We evaluate our approach using two different datasets and compare it to alternative pre-training protocols that do not encode a prior about 3D shape. To systematically explore the effect of 3D pre-training, we introduce a novel dataset called Geon3D, which consists of simple shapes that nevertheless capture variation in multiple distinct dimensions of geometry. We find that while 3D reconstruction pre-training does not improve robustness for the simplest dataset setting, we consider (Geon3D on a clean background) that it improves upon adversarial training in more realistic (Geon3D with textured background and ShapeNet) conditions. We also find that 3D pre-training coupled with adversarial training improves the robustness to spurious correlations between shape and background textures. Furthermore, we show that the benefit of using 3D-based pre-training outperforms 2D-based pre-training on ShapeNet. We hope that these results encourage further investigation of the benefits of structured, 3D-based models of vision for adversarial robustness.

О геометрических основах проектирования технического объекта

The purpose of the article is to propose basic statements (a conditional general name for law, regularity, principle and rule) about the geometry of technical objects and about the process of their design, which, together with existing and future statements, form the geometric foundations of design. 26 statements are presented and a classification, functions and properties of geometry are proposed from the point of view of distribution and the importance of the latter for the technical object and the design process.In their entirety, the presented statements are proof of the importance and influence of geometry in the design process. The work substantiates the possibility of obtaining partially or completely the geometry of any other part or assembled unit, conditionally called a recipient, from any part or assembled unit, conditionally called a donor. It is shown that any “item” (a term for naming anything, regardless of type, structures and characteristics) can be used to change the geometry of any technical object. The impact of the geometry on the flowing through and passing through the substance, the influence of the flows on the geometry, as well as the influence of the geometry on the properties of the substance are noted. It is emphasized that geometry is a fundamental „building block“ of both the technical object and the design process. The well-deserved placement of geometry at the center of the design activity gives a new perspective on the design process, which expands the possibilities and tools for its realization.

Intricacies of Opening Geometry Detection in Terrestrial Laser Scanning: An Analysis Using Point Cloud Data from BLK360

This study investigates the use of terrestrial laser scanning (TLS) in urban excavation sites, focusing on enhancing ground deformation detection by precisely identifying opening geometries, such as gaps between pavement blocks. The accuracy of TLS data, affected by equipment specifications, environmental conditions, and scanning geometry, is closely examined, especially with regard to the detection of openings between blocks. The experimental setup, employing the BLK360 scanner, aimed to mimic real-world paving situations with varied opening widths, allowing an in-depth analysis of how factors related to scan geometry, such as incidence angles and opening orientations, influence detection capabilities. Our examination of various factors and detection levels reveals the importance of the opening width and orientation in identifying block openings. We discovered the crucial role of the opening width, where larger openings facilitate detection in 2D cross-sections. The overall density of the point cloud was more significant than localized variations. Among geometric factors, the orientation of the local object geometry was more impactful than the incidence angle. Increasing the number of laser beam points within an opening did not necessarily improve detection, but beams crossing the secondary edge were vital. Our findings highlight that larger openings and greater overall point cloud densities markedly improve detection levels, whereas the orientation of local geometry is more critical than the incidence angle. The study also discusses the limitations of using a single BLK360 scanner and the subtle effects of scanning geometry on data accuracy, providing a thorough understanding of the factors that influence TLS data accuracy and reliability in monitoring urban excavations.

ARSIP: Automated Robotic System for Industrial Painting

This manuscript addresses the critical need for precise paint application to ensure product durability and aesthetics. While manual work carries risks, robotic systems promise accuracy, yet programming diverse product trajectories remains a challenge. This study aims to develop an autonomous system capable of generating paint trajectories based on object geometries for user-defined spraying processes. By emphasizing energy efficiency, process time, and coating thickness on complex surfaces, a hybrid optimization technique enhances overall efficiency. Extensive hardware and software development results in a robust robotic system leveraging the Robot Operating System (ROS). Integrating a low-cost 3D scanner, calibrator, and trajectory optimizer creates an autonomous painting system. Hardware components, including sensors, motors, and actuators, are seamlessly integrated with a Python and ROS-based software framework, enabling the desired automation. A web-based GUI, powered by JavaScript, allows user control over two robots, facilitating trajectory dispatch, 3D scanning, and optimization. Specific nodes manage calibration, validation, process settings, and real-time video feeds. The use of open-source software and an ROS ecosystem makes it a good choice for industrial-scale implementation. The results indicate that the proposed system can achieve the desired automation, contingent upon surface geometries, spraying processes, and robot dynamics.