期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到392篇文章
< 1 2 … 20 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Pre-process algorithm for satellite laser ranging data based on curve recognition from points cloud 认领 引用
1
作者 Liu Yanyu Zhao Dongming Wu Shan 《Geodesy and Geodynamics》 2012年第2期53-59,共7页
The satellite laser ranging （SLR） data quality from the COMPASS was analyzed, and the difference between curve recognition in computer vision and pre-process of SLR data finally proposed a new algorithm for SLR was ... The satellite laser ranging （SLR） data quality from the COMPASS was analyzed, and the difference between curve recognition in computer vision and pre-process of SLR data finally proposed a new algorithm for SLR was discussed data based on curve recognition from points cloud is proposed. The results obtained by the new algorithm are 85 % （or even higher） consistent with that of the screen displaying method, furthermore, the new method can process SLR data automatically, which makes it possible to be used in the development of the COMPASS navigation system. 展开更多
关键词 satellite laser ranging （SLR） curve recognition points cloud pre-process algorithm COM- PASS screen displaying
暂未订购 下载PDF
An enhanced segmentation method for 3D point cloud of tunnel support system using PointNet++t and coverage-voted strategy algorithms 认领 引用 被引量：3
2
作者 Wenju Liu Fuqiang Gao +4 位作者 Shuangyong Dong Xiaoqing Wang Shuwen Cao Wanjie Wang Xiaomin Liu 《Journal of Rock Mechanics and Geotechnical Engineering》 SCIE CSCD 2026年第2期1653-1660,共8页
3D laser scanning technology is widely used in underground openings for high-precision,rapid,and nondestructive structural evaluations.Segmenting large 3D point cloud datasets,particularly in coal mine roadways with m... 3D laser scanning technology is widely used in underground openings for high-precision,rapid,and nondestructive structural evaluations.Segmenting large 3D point cloud datasets,particularly in coal mine roadways with multi-scale targets,remains challenging.This paper proposes an enhanced segmentation method integrating improved PointNet++with a coverage-voted strategy.The coverage-voted strategy reduces data while preserving multi-scale target topology.The segmentation is achieved using an enhanced PointNet++algorithm with a normalization preprocessing head,resulting in a 94%accuracy for common supporting components.Ablation experiments show that the preprocessing head and coverage strategies increase segmentation accuracy by 20%and 2%,respectively,and improve Intersection over Union(IoU)for bearing plate segmentation by 58%and 20%.The accuracy of the current pretraining segmentation model may be affected by variations in surface support components,but it can be readily enhanced through re-optimization with additional labeled point cloud data.This proposed method,combined with a previously developed machine learning model that links rock bolt load and the deformation field of its bearing plate,provides a robust technique for simultaneously measuring the load of multiple rock bolts in a single laser scan. 展开更多
关键词 Point cloud segmentation Improved PointNet++ Tunnel laser scanning Rock bolt automatic recognition
暂未订购 下载PDF
A point cloud reconstruction method based on uncertainty feature enhancement for aerodynamic shape optimization 认领 引用
3
作者 Junlin LI Yang ZHANG +2 位作者 Bo PANG Junqiang BAI Jiakuan XU 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2026年第6期143-161,共19页
The precision of shape representation and the dimensionality of the design space significantly influence the cost and outcomes of aerodynamic optimization.The design space can be represented more compactly by maintain... The precision of shape representation and the dimensionality of the design space significantly influence the cost and outcomes of aerodynamic optimization.The design space can be represented more compactly by maintaining geometric precision while reducing dimensions,hence enhancing the cost-effectiveness of the optimization process.This research presents a new point cloud Autoencoder Based on Uncertainty Feature Enhancement(AE-BUFE)architecture,designed to attain efficient and precise generalized representations of 3D aircraft through uncertainty analysis of the deformation relationships among surface grid points.The deep learning architecture consists of two components:the uncertainty index-based feature enhancement module and the point cloud autoencoder module.It learns the shape features of the point cloud geometric representation to establish a low-dimensional latent space.To assess and evaluate the efficiency of the method,a comparison was conducted with the prevailing point cloud autoencoder architecture and the proper orthogonal decomposition linear dimensionality reduction method under conditions of complex shape deformation.The results show that the new architecture significantly improves the extraction effect of the low-dimensional latent space.Then,this paper developed the surrogate-based optimization framework based on the AE-BUFE parameterization method and completed a multi-objective aerodynamic optimization design for a wide-speed-range vehicle considering volume and moment constraints.While ensuring the take-off and landing performance,the aerodynamic performance is improved under transonic and hypersonic conditions,which verifies the efficiency and engineering practicability of this method. 展开更多
关键词 Deep learning Design space dimensionality reduction Flight vehicle design Point cloud autoencoder Sensitivity analysis Wide speed range
暂未订购 下载PDF
Federated Dynamic Aggregation Selection Strategy-Based Multi-Receptive Field Fusion Classification Framework for Point Cloud Classification 认领 引用
4
作者 Yuchao Hou Biaobiao Bai +3 位作者 Shuai Zhao Yue Wang Jie Wang Zijian Li 《Computers, Materials & Continua》 SCIE EI 2026年第2期1889-1918,共30页
Recently,large-scale deep learning models have been increasingly adopted for point cloud classification.However,thesemethods typically require collecting extensive datasets frommultiple clients,which may lead to priva... Recently,large-scale deep learning models have been increasingly adopted for point cloud classification.However,thesemethods typically require collecting extensive datasets frommultiple clients,which may lead to privacy leaks.Federated learning provides an effective solution to data leakage by eliminating the need for data transmission,relying instead on the exchange of model parameters.However,the uneven distribution of client data can still affect the model’s ability to generalize effectively.To address these challenges,we propose a new framework for point cloud classification called Federated Dynamic Aggregation Selection Strategy-based Multi-Receptive Field Fusion Classification Framework(FDASS-MRFCF).Specifically,we tackle these challenges with two key innovations:(1)During the client local training phase,we propose a Multi-Receptive Field Fusion Classification Model(MRFCM),which captures local and global structures in point cloud data through dynamic convolution and multi-scale feature fusion,enhancing the robustness of point cloud classification.(2)In the server aggregation phase,we introduce a Federated Dynamic Aggregation Selection Strategy(FDASS),which employs a hybrid strategy to average client model parameters,skip aggregation,or reallocate local models to different clients,thereby balancing global consistency and local diversity.We evaluate our framework using the ModelNet40 and ShapeNetPart benchmarks,demonstrating its effectiveness.The proposed method is expected to significantly advance the field of point cloud classification in a secure environment. 展开更多
关键词 Point cloud classification federated learning multi-receptive field fusion dynamic aggregation
暂未订购 下载PDF
Analysis of cracking behaviors of five clayey materials using 3D point cloud data 认领 引用
5
作者 Xin Wei Pengsen Wang +1 位作者 Yao Gao Ling Xu 《Journal of Rock Mechanics and Geotechnical Engineering》 SCIE CSCD 2026年第7期5731-5743,共13页
In recent years,drought-induced soil cracking has become increasingly prevalent,posing significant challenges to geotechnical engineering applications due to the associated hazards.Previous studies have investigated s... In recent years,drought-induced soil cracking has become increasingly prevalent,posing significant challenges to geotechnical engineering applications due to the associated hazards.Previous studies have investigated soil cracking behaviors and mechanisms via multi-scale methods.However,research on the spatial distribution characteristics of soil cracks and their depth evolution mechanisms is still rare.This paper analyzes the three-dimensional(3D)deformation of fiveclayey materials.In this study,3D surface elevation data of soil samples were acquired using a Gocator 3110 structured-light sensor.The reconstruction process involved point cloud acquisition and rasterization,Delaunay triangulation meshing,and calculation of crack depth.Different cracking behaviors are investigated,such as cracking in opening mode and shearing mode,coalescence and bifurcation of cracks,etc.The mineralogical analysis is carried out to reveal different cracking behaviors of clays.It is concluded that the crack depth of montmorillonite is larger than that of kaolin,reflectingits strong shrinkage characteristic,which makes the crack evolve deeper than the other materials.This technique enables multi-dimensional observation of soil crack propagation.The mineralogical analysis is carried out to reveal the different cracking behaviors of clays.It is concluded that microstructure and mineralogy are key factors influencingcracking behavior.Understanding soil cracking behaviors is significantfor engineering protection,geohazard prevention,and geological monitoring. 展开更多
关键词 Clay Free desiccation Laser scanning technique Three-dimensional(3D)point cloud data Cracking behavior
暂未订购 下载PDF
An improved Alpha-shape algorithm for extracting section contours of the super-high steel bridge tower using point clouds 认领 引用
6
作者 ZHANG Yiming ZHAO Tianhao +2 位作者 LIAO Ruixuan LI Haoqing WANG Hao 《Journal of Southeast University(English Edition)》 EI CAS 2026年第1期26-35,共10页
The virtual preassembly of super-high steel bridge towers faces a challenge in the efficient and precise extraction of complex cross-sectional features.Factors such as fabrication errors,gravity-induced deformations,a... The virtual preassembly of super-high steel bridge towers faces a challenge in the efficient and precise extraction of complex cross-sectional features.Factors such as fabrication errors,gravity-induced deformations,and temperature fluctuations can compromise the accuracy of contour extraction.To address these limitations,an improved Alpha-shape-based point cloud contour extraction method is proposed.The proposed approach uses a hierarchical strategy to process three-dimensional laser scanning point clouds.The processed data are then subjected to curvatureadaptive voxel filtering to reduce acquisition noise.In addition,an enhanced iterative closest point(ICP)variant with correspondence validation accurately aligns the discrete point cloud segments.The proposed curvature-responsive Alpha-shape framework enables multiscale contour delineation through topology-adaptive threshold modulation,which resolves boundary ambiguities in geometrically complex cross-sections.The method was experimentally validated using field-acquired measurement datasets from the Zhangjinggao Yangtze River Bridge tower segments,confirming its capability to reconstruct noncanonical cross-sectional geometries.Three contour extraction methods,including Poisson reconstruction,the conventional Alpha-shape algorithm,and random sample consensus with ICP(RANSAC-ICP),were compared to evaluate the performance of the proposed Alpha-shape algorithm.The results demonstrate that the proposed method achieves superior contour extraction accuracy and data reduction efficiency,highlighting its effectiveness in contour extraction tasks. 展开更多
关键词 super-high steel bridge tower point cloud contour extraction improved Alpha-shape algorithm
暂未订购 下载PDF
PointNMSA: An Improved PointNeXt Network with Non-Local Multi-Scale Aggregation for 3D Point Cloud Semantic Segmentation 认领 引用
7
作者 Aihua Wu Chenlu Huang 《Computers, Materials & Continua》 SCIE EI 2026年第8期1632-1649,共18页
Three-dimensional(3D)point cloud semantic segmentation is a core task in indoor scene understanding,providing detailed semantic information about spatial structures and object categories in indoor environments.Althoug... Three-dimensional(3D)point cloud semantic segmentation is a core task in indoor scene understanding,providing detailed semantic information about spatial structures and object categories in indoor environments.Although methods based on deep learning have made steady progress in recent years,accurately segmenting complex indoor scenes remains challenging due to the unordered nature of point clouds and variations across large scales.Most existing networks have limited capability for multi-scale feature aggregation and struggle to balance local geometric details with global semantic context.These issues are further exacerbated by hierarchical downsampling,which often leads to the loss of fine-grained structural information.Moreover,feature interaction restricted to local neighborhoods may limit the capture of non-local semantic dependencies in complex indoor scenes.To address these limitations,we propose PointNMSA(PointNeXt with Non-local Multi-Scale Aggregation),an improved semantic segmentation network built upon the PointNeXt backbone.A Multi-Scale Feature Enhancement(MSFE)module is introduced in the decoding stage to fuse features from different encoding levels,and further refines the fused features to produce more stable multi-scale representations,which preserves geometric details across scales.In addition,a Convolution-Attention Mixing(CA-Mix)module is designed to jointly integrate local spatial structures and non-local contextual dependencies via dual-stream aggregation and multi-dimensional attention fusion,thereby enabling more discriminative feature representations.Experiments on the Stanford Large-Scale 3D Indoor Spaces(S3DIS)benchmark demonstrate the effectiveness of PointNMSA.On the Area 5 test split,PointNMSA achieves a mean intersection over union(mIoU)of 65.10%,outperforming the PointNeXt baseline by 1.59%,while introducing only a modest increase in computational cost(latency from 42.24 to 45.18 ms and parameters from 3.16 to 8.67M).Despite the noticeable growth in parameter count,the increase in inference latency remains relatively limited,indicating a favorable trade-off between segmentation accuracy and computational efficiency.Additional cross-dataset experiments on ScanNet further verify that PointNMSA maintains stable gains under different indoor scene distributions.Such performance gains suggest that PointNMSA provides a more robust and generalizable solution for semantic segmentation in large-scale indoor environments with complex structural layouts. 展开更多
关键词 3D point cloud semantic segmentation indoor scene understanding multi-scale feature aggregation non-local context integration PointNeXt
暂未订购 下载PDF
Prediction of pressure coefficient distributions for basic aerodynamic configurations via point cloud characterization 认领 引用 被引量：1
8
作者 Qiming Guan Weiwei Zhang 《Acta Mechanica Sinica》 SCIE EI CAS CSCD 2026年第7期19-35,共17页
Data-driven approaches have shown great advantage in rapidly and accurately predicting pressure coefficient distributions,which is of crucial importance to efficient aircraft design.Nevertheless,most data-driven appro... Data-driven approaches have shown great advantage in rapidly and accurately predicting pressure coefficient distributions,which is of crucial importance to efficient aircraft design.Nevertheless,most data-driven approaches still encounter limitations in characterizing diverse aerodynamic configurations and adapting to varying grid densities,which have hindered their engineering applicability.In response to these challenges,this work adopts point clouds,a specific type of geometric data structure that is inherently suitable for uniformly characterizing diverse 2D/3D geometric shapes as the input for deep learning-based prediction of pressure coefficient distribution.By augmenting the dimensions of point cloud coordinates for local feature enhancement and utilizing the symmetric function“max pooling”to extract global features,the proposed aerodynamic model establishes the mapping between point cloud coordinates and pressure coefficients.Basic aerodynamic configurations like airfoils and wings are employed as test cases,the results demonstrate that the proposed model achieves both high accuracy and robust generalizability across variable geometries.For class-shape transformation-perturbed airfoils,the prediction error can be reduced to one-third of that of the conventional parameterization-based model.For airfoils selected in the University of Illinois Urbana-Champaign airfoil dataset,among which airfoil profiles are widely distributed,the average error of the proposed approach remains approximately 1.5%,whereas the parameterization-based model may fail.For wings,the prediction error still stays below 2.5%.Finally,the model exhibits strong robustness and generalizability across different point cloud densities.In conclusion,this work makes a breakthrough in predicting pressure coefficient distribution for variable geometric configurations,establishing the foundational framework for designing a large model capable of predicting distributed aerodynamic loads in aerospace applications. 展开更多
关键词 Data-driven Deep learning Pressure coefficient distribution prediction Point cloud Point cloud-based machine learning
暂未订购 下载PDF
Normal vector estimation method for rock mass point clouds with sharp feature preservation via local geometric adjustment 认领 引用
9
作者 Mingming Ren Manchao He +4 位作者 Jie Hu Hongru Li Yuxiang Ding Xinhao Miao Hongyi Zhang 《Journal of Rock Mechanics and Geotechnical Engineering》 SCIE CSCD 2026年第5期3722-3741,共20页
Accurate extraction of rock mass discontinuity parameters is crucial for stability assessment and engineering safety.High-resolution remote sensing facilitates automated extraction,but its effectiveness relies heavily... Accurate extraction of rock mass discontinuity parameters is crucial for stability assessment and engineering safety.High-resolution remote sensing facilitates automated extraction,but its effectiveness relies heavily on precise normal estimation to ensure geometric reliability.Conventional methods struggle to preserve sharp features such as edges and corners,thereby reducing accuracy.To address this,we propose a normal estimation method based on local geometric adjustment that enhances feature extraction while maintaining sharp geometries.The approach consists of four steps:(1)classifying points,(2)applying normal and axial projections,(3)fitting segmentation lines via least squares,and(4)refining normals by optimizing local neighborhoods.The proposed method was evaluated on computer-aided design(CAD)models,real objects,and rock mass point clouds,and benchmarked against eight representative algorithms,including principal component analysis(PCA),2-Jet PCA,Voronoi-based PCA,PCPNet,neural gradient function(NeuralGF),low rank representation(LRR),normal estimation via shifted neighborhood(NSN)and pair consistency voting(PCV).Experimental results demonstrate that our method achieves superior accuracy and efficiency,significantly improving structural plane extraction and ensuring better preservation of sharp geometric features. 展开更多
关键词 Rock mass point cloud Normal vector estimation Sharp feature Rock engineering
暂未订购 下载PDF
3D Single Object Tracking in Point Clouds: A Review 认领 引用
10
作者 Yihao Kuang Hong Zhang +2 位作者 Jiaqi Wang Lingyu Jin Bo Huang 《Computers, Materials & Continua》 SCIE EI 2026年第6期118-142,共25页
3D single object tracking(SOT)based on point clouds is a fundamental task for environmental perception in autonomous driving and dynamic scene understanding in robotics.Recent technological advancements in this field ... 3D single object tracking(SOT)based on point clouds is a fundamental task for environmental perception in autonomous driving and dynamic scene understanding in robotics.Recent technological advancements in this field have significantly bolstered the environmental interaction capabilities of intelligent systems.This field faces persistent challenges,including feature degradation induced by point cloud sparsity,representation drift caused by non-rigid deformation,and occlusion in complex scenarios.Traditional appearance matching methods,particularly those relying on Siamese networks,are severely constrained by point cloud characteristics,often failing under rapid motions or structural ambiguities among similar objects.In response,the research paradigm has progressively evolved toward motion-centric modeling approaches.These emerging frameworks utilize spatio-temporal joint modeling and geometric shape completion to attain notable performance gains.Furthermore,the incorporation of attention mechanisms and State Space Model(SSM)has enabled more effective multi-scale spatio-temporal feature association,which is particularly beneficial for long-term tracking scenarios.To the best of our knowledge,this is the first comprehensive survey dedicated to 3D single object tracking in point clouds.We provide a detailed analysis of current tracking methods,scrutinizing their limitations regarding multi-object interference and analyzing the trade-off between accuracy and computational efficiency.Finally,we discuss potential future directions,including the development of lightweight models for edge deployment and the integration of cross-modal fusion strategies. 展开更多
关键词 Point cloud 3D single object tracking autonomous driving sparsity spatio-temporal feature
暂未订购 下载PDF
TQU-GraspingObject:3D Common Objects Detection,Recognition,and Localization on Point Cloud for Hand Grasping in Sharing Environments 认领 引用
11
作者 Thi-Loan Nguyen Huy-Nam Chu +2 位作者 The-Thanh Hua Trung-Nghia Phung Van-Hung Le 《Computers, Materials & Continua》 SCIE EI 2026年第5期1701-1722,共22页
To support the process of grasping objects on a tabletop for the blind or robotic arm,it is necessary to address fundamental computer vision tasks,such as detecting,recognizing,and locating objects in space,and determ... To support the process of grasping objects on a tabletop for the blind or robotic arm,it is necessary to address fundamental computer vision tasks,such as detecting,recognizing,and locating objects in space,and determining the position of the grasping information.These results can then be used to guide the visually impaired or to execute grasping tasks with a robotic arm.In this paper,we collected,annotated,and published the benchmark TQUGraspingObject dataset for testing,validation,and evaluation of deep learning(DL)models for detecting,recognizing,and localizing grasping objects in 2D and 3D space,especially 3D point cloud data.Our dataset is collected in a shared room,with common everyday objects placed on the tabletop in jumbled positions by Intel RealSense D435(IR-D435).This dataset includes more than 63k RGB-D pairs and related data such as normalized 3D object point cloud,3D object point cloud segmented,coordinate system normalizationmatrix,3D object point cloud normalized,and hand pose for grasping each object.At the same time,we also conducted experiments on fourDL networks with the best performance:SSD-MobileNetV3,ResNet50-Transformer,ResNet101-Transformer,and YOLOv12.The results present that YOLOv12 has the most suitable results in detecting and recognizing objects in images.All data,annotations,toolkit,source code,point cloud data,and results are publicly available on our project website:http://gffzz188fe103f8f1460asfccnxf5ob05c6bw0.ffgz.tsg.suse.edu.cn/HuaTThanhIT2327Tqu/datasetv2. 展开更多
关键词 Grasping object of blind/Robot arm TQU-graspingobject benchmark dataset 3D point cloud data deep learning(DL) object detectionecognition intel realsense D435(IR-D435)
暂未订购 下载PDF
Less-parametric point cloud upsampling network 认领 引用
12
作者 Aihua Ling Hongfang Liu +1 位作者 Junwen Wang Ruyu Liu 《Optoelectronics Letters》 EI 2026年第1期53-57,共5页
In the field of aircraft design and maintenance,with the innovation of cabin cable three-dimensional(3D)scanning and sensor technology,high-precision cabin point cloud data has become the key to improving the accuracy... In the field of aircraft design and maintenance,with the innovation of cabin cable three-dimensional(3D)scanning and sensor technology,high-precision cabin point cloud data has become the key to improving the accuracy of cabin navigation and building a realistic virtual reality environment.In the face of largescale point cloud data,how to efficiently and uniformly construct a realistic virtual reality environment has become a challenge.In this paper,we propose a new low-parametric point cloud upsampling network(LPNet),which is based on the no-learn model to learn the complementary geometric knowledge between point clouds based on some simple data transformations,to efficiently retain the geometric properties of point clouds,and then input the results into the up-sampling module,and simply insert a few layers of multilayer perceptron(MLP)to efficiently generate high-resolution point clouds.It is able to efficiently generate high-resolution point clouds,showing great flexibility and realizing the efficient use of computational resources. 展开更多
关键词 aircraft design maintenancewith sensor technologyhigh precision building realistic virtual reality environmentin virtual reality environment point cloud upsampling aircraft design maintenance D scanning low parametric network
暂未订购 下载PDF
Cross-source point cloud registration network with low overlap based on multi-scale features and attention mechanisms 认领 引用
13
作者 ZHONG Xingjian WANG Peng +3 位作者 LI Yue LI Lin FU Luhua SUN Changku 《Journal of Measurement Science and Instrumentation》 CAS CSCD 2026年第2期183-194,共12页
Machine vision-based detection methods have been widely applied in the detection of aircraft skin damage.During drone inspection processes,a key step is to spatially locate high-resolution detailed images of aircraft ... Machine vision-based detection methods have been widely applied in the detection of aircraft skin damage.During drone inspection processes,a key step is to spatially locate high-resolution detailed images of aircraft skin from multiple angles onto a threedimensional point cloud model of the aircraft.This relies on the rigid registration of image center position coordinate point cloud with the aircraft 3D point cloud.To address the issues of low accuracy and poor robustness encountered by existing registration algorithms when dealing with heterogeneous point clouds with significant differences in density and low overlap,this paper presents a novel cross-source point cloud registration network.The network integrates multi-scale information from the point cloud and employs an attention mechanism to identify representative overlapping points.First,the network achieves initial correspondences using the multi-scale geometric features and positional information of the point cloud.Then,an overlapping feature guidance module predicts the overlapping score of the point cloud.By utilizing information interaction through the attention mechanism,the network combines point overlapping scores with fused features to filter out representative overlapping points,achieving precise correspondences in the point cloud.The network employs weighted singular value decomposition(SVD)to estimate two sets of transformation matrices,yielding the relative pose parameters of the point cloud.Experiments were conducted in an unsupervised manner.The experimental results on the ModelNet40 dataset and the aero object dataset aircraft measurement data showed that,compared to other existing traditional and learning-based methods,this approach demonstrated excellent performance in terms of registration accuracy and robustness. 展开更多
关键词 visual inspection point cloud registration spatial localization machine learning cross-source registration unsupervised learning
暂未订购 下载PDF
Feed-forward 3 D reconstruction with point-cloud representations:From DUSt 3 R to VGGT and beyond 认领 引用
14
作者 Zeyi ZHENG Xiong YANG +1 位作者 Ran YI Lizhuang MA 《虚拟现实与智能硬件（中英文）》 EI CSCD 2026年第3期265-282,共18页
This survey reviews feed-forward,point-cloud 3D reconstruction methods from DUSt3R to VGGT and their recent variants.Here,feed-forward primarily refers to predicting dense geometry and,when applicable,camera poses thr... This survey reviews feed-forward,point-cloud 3D reconstruction methods from DUSt3R to VGGT and their recent variants.Here,feed-forward primarily refers to predicting dense geometry and,when applicable,camera poses through learned network inference,without relying on classical per-scene SfM+MVS optimization as the main inference mechanism.We first formalize the reconstruction task in pose-aware and pose-free settings,and contrast feed-forward point-map regression with classical Structure-from-Motion and Multi-View Stereo pipelines.Building on this,we organize existing methods into three stages:early pairwise models typified by DUSt3R,DUSt3R-style extensions that enhance multi-view consistency,streaming,efficiency,and dynamic-scene handling,and large unified transformers such as VGGT that process tens to hundreds of views jointly,while noting differences in their inference paradigms.We analyze these models along shared axes,including scene representation,correspondence reasoning,pose regression,fusion strategies,and the role of large-scale training data.We summarize widely used 3D datasets and evaluation metrics,and provide a case study on the DTU benchmark for multi-view depth and point map estimation,highlighting accuracy-efficiency trade-offs between optimization-based and feed-forward approaches.Finally,we discuss open challenges in data scarcity,sparse-view reconstruction,non-Lambertian structures,dynamic scenes,long-context processing,and resource-efficient deployment,and outline future directions that combine feed-forward architectures with differentiable rendering,generative priors,and safety mechanisms to enable scalable and trustworthy 3D reconstruction systems. 展开更多
关键词 Feed-forward 3D reconstruction Point cloud Point-map Vision Transformer Multi-view depth estimation Dynamic scene reconstruction Virtual reality
暂未订购 下载PDF
A Fully-Actuated Pose Adjustment Method for Wing-Fuselage Assembly via Point-Cloud Gap Optimization 认领 引用
15
作者 Xiao Xu Yang Zhang +4 位作者 Runze Liu Haoyu Wu Qihang Chen Yongkang Lu Wei Liu 《Instrumentation》 2026年第2期109-124,共16页
Wing-fuselage assembly is a critical process in aircraft manufacturing,and the gap distribution of the wing-fuselage assembly frames directly determines the stress state of the connection interface and the structural ... Wing-fuselage assembly is a critical process in aircraft manufacturing,and the gap distribution of the wing-fuselage assembly frames directly determines the stress state of the connection interface and the structural load-carrying capacity after assembly.However,most existing pose adjustment methods either do not consider the global gap distribution or optimize the gap only based on theoretical computer-aided design(CAD)models,making it difficult to effectively control the actual gap distribution under real manufacturing errors.In addition,traditional positioners adopt a master-slave driving mode,in which passive axes suffer from following errors due to the lack of independent control,thereby limiting the execution accuracy of pose adjustment.To address these problems,this paper proposes a fullyactuated pose adjustment method for wing-fuselage assembly via point-cloud gap optimization.First,point cloud data of the wing-fuselage assembly frames in a unified assembly coordinate system are obtained through laser scanning combined with Enhanced Reference System(ERS)reference point registration.Assembly gaps are then defined along prescribed region-wise assembly directions,and a multi-surface global gap evaluation model is established.Second,a two-stage optimization strategy combining coarse pre-alignment and fine pose adjustment is adopted,in which insertion-depth correction is decoupled from rotational gap-uniformity optimization to solve the optimal target assembly pose.Finally,the optimized pose is converted into multi-axis synchronous motion commands for fully-actuated positioners through fifth-order polynomial trajectory planning and inverse kinematic mapping,and the force-position data of the positioners are effectively monitored throughout the pose adjustment process.The proposed method is compared with a traditional manual assembly method on a wing-fuselage assembly experimental platform.The results show that the proposed method reduces the in-plane gap standard deviations of the upper and right assembly surfaces from 2.19 mm and 1.34 mm to 1.70 mm and 1.04 mm,respectively,significantly improving gap uniformity.Meanwhile,the positioner motion remains continuous and smooth during pose adjustment,and no abnormal force fluctuations occur at the support points.The proposed method provides an integrated and executable solution for highprecision wing-fuselage assembly by linking measured-point-cloud-based global gap optimization,fully-actuated pose adjustment,and real-time force-position monitoring,thereby supporting assembly safety assessment and quality traceability. 展开更多
关键词 wing-fuselage assembly 3D point cloud measurement assembly gap pose optimization fully-actuated pose adjustment
暂未订购 下载PDF
Three-dimensional affordance segmentation for object point cloud driven by language instructions 认领 引用
16
作者 Jiaxuan DU Hao WU +3 位作者 Qing MA Guohui TIAN Zhixian ZHAO Shuwen LENG 《ENGINEERING Information Technology & Electronic Engineering》 SCIE EI CSCD 2026年第4期17-26,共10页
The location where a robot grasps an object is closely related to the task type.For the same object,different user requirements may necessitate different grasping strategies.Visual affordance serves as a reliable sour... The location where a robot grasps an object is closely related to the task type.For the same object,different user requirements may necessitate different grasping strategies.Visual affordance serves as a reliable source of prior knowledge for manipulation.Existing methods learn affordance from images or videos,but planar affordance lacks the spatial information required for 6-degree-of-freedom(6-DoF)manipulation.Furthermore,current approaches are limited to affordances associated with predefined categories and cannot directly infer affordances from user instructions.To address such limitations,we propose a novel task:instruction-driven three-dimensional(3D)object affordance segmentation.To support this research,we introduce an instruction–affordance dataset(IAD),a challenging dataset consisting of 7190 object instances across 20 common object categories,paired with 624 manipulation instructions that specify the corresponding affordances.To evaluate generalization to novel commands,our dataset includes both seen and unseen settings.Building on this,we design an instruction-driven 3D affordance segmentation(IDAS)network,which extracts point cloud features and integrates instruction features layer by layer.Given a user instruction,our method segments suggested manipulation regions on the object’s point cloud,thereby guiding the selection of optimal grasp poses.Experimental results show that our method outperforms other related approaches under both seen and unseen settings,demonstrating generalization ability to diverse user commands and unknown affordances. 展开更多
关键词 Visual affordance Point cloud segmentation Open vocabulary Multimodal fusion Service robot
暂未订购 下载PDF
Attention and Mamba Based Iterative Registration Network for Low-Overlap and Large-Scale Point Cloud 认领 引用
17
作者 Haotian Cao Qingsheng Zhu 《Computers, Materials & Continua》 SCIE EI 2026年第8期1358-1381,共24页
Point Cloud Registration(PCR)is a basic task in computer vision,mobile robotics,and autonomous driving.PCR primarily faces challenges,including insufficient registration performance in low-overlap scenarios and high c... Point Cloud Registration(PCR)is a basic task in computer vision,mobile robotics,and autonomous driving.PCR primarily faces challenges,including insufficient registration performance in low-overlap scenarios and high computational resource consumption in large-scale point cloud scenarios.Most recent PCR methods are transformer-based.Methods like transformers have quadratic computational complexity O(n2d),,leading to rapid increases in computational cost with large-scale point cloud data.To address these problems,an iterative PCR method named Attention and Mamba Based Iterative Registration Network(AMBIR)is proposed,overcoming the shortcomings of the current PCR method on low-overlap and large-scale scenarios.Specifically,an iterative network architecture is introduced that learns overlap experience from prior registration results,thereby enhancing registration performance by leveraging knowledge from the preceding step.Additionally,to convert 3-D point cloud data into linear sequences suitable for the Mamba encoder,the Prior-Informed Co-aligned Serialization is proposed to ensure that points with adjacent indices after serialization are spatial neighbors,thereby improving the efficiency and robustness of the subsequent registration process.Lastly,a Consistency-Aware Mamba Encoder is introduced to leverage its linear computational complexity,making the method more suitable for large-scale point clouds.This method simultaneously overcomes the shortcomings of existing methods,including insufficient registration performance in low-overlap and large-scale point cloud scenarios.It performs well on the 3DMatch dataset,3DLoMatch low-overlap dataset,and KITTI large-scale scene dataset,demonstrating high practical value. 展开更多
关键词 Point cloud registration deep learning computer vision attention mechanism mamba model iterative network
暂未订购 下载PDF
Multiple point cloud encryption based on principal component analysis and fractional Fourier transform 认领 引用
18
作者 LI Xinze YU Lei +1 位作者 NIE Jiafa SUN Yan 《Journal of Systems Engineering and Electronics》 SCIE CSCD 2026年第2期393-411,共19页
In view of the large amount of data and dense pixel points in point cloud files,this article proposes a multiple point cloud file encryption algorithm based on principal component analysis(PCA)and fractional Fourier t... In view of the large amount of data and dense pixel points in point cloud files,this article proposes a multiple point cloud file encryption algorithm based on principal component analysis(PCA)and fractional Fourier transform(FrFT).In this method,a point cloud data matrix(PCDM)is generated by extracting the coordinates and color information of the point cloud,then using PCA to reduce the dimension of a sequence of PCDMs,which are spliced and scrambled to produce a feature vector matrix and a dimension-reduced matrix(DRM)for encryption and reconstruction.Then using the hyperchaotic Lorenz system to generate the random phase masks and the orders of the FrFT.These two parameters will be used as keys to encrypt the point cloud feature vector matrix.The simulation results verify that the encryption algorithm can quickly encrypt multiple point cloud files,and the quality of the point cloud files obtained by decryption and reconstruction is good.The algorithm also has a large enough key space and highly sensitive keys,which means it has good security and strong robustness to different attacks. 展开更多
关键词 image encryption point cloud hyperchaotic system principal component analysis fractional Fourier Transform
暂未订购 下载PDF
2D3D-DiffMatch:Detector-Free Image and Point Cloud Matching via Diffusion-Guided Cross-Modal Consistency 认领 引用
19
作者 Yashuai Ji Zhitao Fu +2 位作者 Han Nie Bin Luo Bo-Hui Tang 《Journal of Beijing Institute of Technology》 EI CAS 2026年第3期306-328,共23页
In the realms of computer vision and remote sensing,the matching of images and point clouds poses significant challenges due to modality discrepancies.This study introduces a crossmodal consistency network,detector-fr... In the realms of computer vision and remote sensing,the matching of images and point clouds poses significant challenges due to modality discrepancies.This study introduces a crossmodal consistency network,detector-free image and point cloud matching via diffusion-guided crossmodal consistency,2D3D-DiffMatch,leveraging diffusion prior information to enhance feature extraction consistency and alignment across modalities.To strengthen cross-modal consistency in complex scenes,diffusion priors generated by a pre-trained diffusion model are used to guide the feature extraction process toward semantically and geometrically consistent representations.These representations are further refined through a hierarchical fusion process,in which the most consistent diffusion features are adaptively selected using centered kernel alignment(CKA)and integrated with multi-scale backbone features,thereby mitigating the impact of modality gaps.Furthermore,to address feature-space misalignment between images and point clouds,we propose a crossmodal feature consistency loss that adaptively constrains correspondences,separates positive and negative pairs,and optimizes the agreement of positive pairs,enabling high-quality,detector-free matching.Experimental results on the 7Scenes and RGB-D Scenes V2 Datasets demonstrate superior registration recall rates of 81.2%and 61.0%,respectively,outperforming state-of-the-art methods and exhibiting robustness in challenging scenarios.This research advances the collaborative processing of multi-modal data,offering a robust solution for image–point cloud matching in challenging scenarios. 展开更多
关键词 image and point cloud matching cross-modal consistent features diffusion model diffusion prior information
暂未订购 下载PDF
Rock Discontinuity Extraction from 3D Point Clouds:Application to Identifying Geological Structures in the Miocene-Pliocene Deposits,Japan 认领 引用
20
作者 Masahiro Ohkawa Kota Osawa +1 位作者 Ryo Okino Shigeaki Matsuo 《Journal of Environmental & Earth Sciences》 CAS 2026年第1期29-46,共18页
Evaluating rock mass quality using three-dimensional(3D)point clouds is crucial for discontinuity extraction and is widely applied in various industrial sectors.However,the utilization of this method in geological sur... Evaluating rock mass quality using three-dimensional(3D)point clouds is crucial for discontinuity extraction and is widely applied in various industrial sectors.However,the utilization of this method in geological surveys remains limited.Notable limitations of current research include the scarcity of validation using simple geometric shapes for discontinuity extraction methods,and the lack of studies that target both planar and linear discontinuity.To address these gaps,this study proposes a workflow for identifying discontinuity planes and traces in rock outcrops from photogrammetric 3D modeling,employing the Compass and Facets plugins in the open-source CloudCompare software.Prior to field application,the efficacy of the extraction methods was first evaluated using experimental datasets of a cube and an isosceles triangular prism generated under laboratory-controlled conditions.This validation demonstrated exceptional accuracy,with the dip and dip direction(DDD)of extracted structures consistently within±2°of the actual values.Following this rigorous laboratory validation,this methodology was applied to a more complex natural rock outcrop(Miocene–Pliocene deposits in Japan),demonstrating its applicability in realistic geological settings for identifying structures.The results showed that the dip and dip direction trends of the extracted bedding planes and faults were consistent with field measurements,achieving a time reduction of approximately 40%compared to traditional methods.In conclusion,through strictly controlled initial verification and subsequent successful application to a complex natural setting,this study confirmed that the proposed workflow can effectively and efficiently extract discontinuous geological structures from point clouds. 展开更多
关键词 Digital Outcrop Model Rock Discontinuities Geological Information Point Cloud
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 20 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈