Search Results (346)

Detecting localized morphological anomalies in three-dimensional point clouds is difficult because geometric deviations are entangled with rigid pose variation, residual registration error, sampling noise, and normal inter-subject variability. This challenge is particularly relevant in translational neuroimaging, where abnormal shape changes may be subtle and abnormal annotations are scarce. We propose an unsupervised framework that formulates 3D anomaly detection as a two-stage factorization problem, termed AdvFlow3D-AD. First, Fast Global Registration, followed by multi-scale Iterative Closest Point refinement, establishes a common geometric reference frame and reduces rigid-body nuisance variation. Second, an adversarially regularized normalizing flow models the residual distribution of aligned normal coordinates, enabling localized anomaly scores based on distance from the learned normal latent support. Percentile calibration on normal data then defines interpretable point-level and object-level operating points without requiring abnormal samples during training. We evaluate AdvFlow3D-AD on the Real3D-AD and Anomaly ShapeNet3D datasets, achieving a point-level area under the receiver operating characteristic curve (AUROC) of 0.747 on Real3D-AD and an object-level AUROC of 0.816 on Anomaly ShapeNet3D. We further present an exploratory neurodevelopmental brain-shape case study involving pediatric perinatal-asphyxia cases. The resulting anomaly maps showed qualitative spatial correspondence with anatomically plausible hippocampal and cerebellar regions under neuroradiological review. These results suggest that separating geometric nuisance variation from residual morphology can support interpretable anomaly localization when abnormal labels are limited. Full article

Magnetic anomaly generated by magnetic target is widely used in many areas. In this paper, a real-time magnetic target localization method based on second-order scalar magnetic gradients at the closest point of approach (CPA) is proposed. By exploiting the geometric symmetry of the magnetic anomaly field at the CPA point, closed-form expressions of the target position and magnetic moment are derived directly from the second-order spatial derivatives of scalar magnetic anomaly under the induced-magnetization assumption, thereby avoiding iterative global optimization. Furthermore, a residual-based error index is constructed to evaluate the consistency between measured and reconstructed second-order scalar magnetic gradients, enabling automatic determination of the CPA point during platform motion. The proposed method is validated by the experiment. The results show that the CPA point on the trajectory can be accurately identified using the proposed error index, and the localization accuracy is significantly improved near the CPA point. At the CPA point, the relative errors of the estimated distances and angles between the target and the two sensors are 0.89% and 0.38%, and 1.0% and 0.52%, respectively, while the relative error of the estimated magnetic moment magnitude is 4.85%. Therefore, the proposed method has great value in target localization based on a mobile magnetic anomaly detection system. Full article

Robust estimation of camera trajectories from unconstrained image sequences remains a fundamental problem in computer vision and robotics. Recently, a diffusion-based camera tracking network has shown strong performance in sparse-view and single-object-centric settings, where a consistent object is observed across frames. However, when multiple objects appear sequentially in a video, the initially observed object may disappear as the sequence progresses, which prevents maintaining the “single-object-centric” paradigm across all frames and degrades pose estimation when the conventional method is applied to the multi-object sequence. In this work, we propose an object-centric camera pose estimation framework that handles such sequences by partitioning a video into object-level sub-scenes. As a baseline network, Ray Diffusion is applied to single-object sub-scenes, while frame-to-frame camera motion in multi-object sub-scenes is estimated using monocular video depth, object masks, and point cloud alignment using Iterative Closest Point (ICP). Since the domain of pose estimation from different sub-scenes is inconsistent in terms of pose scale, it requires seamless concatenation of pose estimation results through all sub-scenes. In this regard, we introduce a scale alignment strategy based on reprojection error minimization. This enables the pose estimates from individual sub-scenes to be integrated into a single and seamless camera trajectory. We evaluate the proposed method on a newly collected indoor dataset consisting of 40 multi-object video sequences. Experimental results compare our camera trajectory estimation with both the diffusion-based method and the state-of-the-art visual SLAM methods. Full article

Martian dust storms cut off communication and break standard robot navigation. We built a hybrid system that keeps robot swarms alive during these blackouts and recovers their data quickly. Our rovers use Spiking Neural Networks (SNNs) on their own edge processors to navigate without a signal. Once the storm passes, we use the Quantum Approximate Optimization Algorithm (QAOA) on a cloud platform to merge the fragmented maps the rovers collected while they were offline. We tested this system in a Robot Operating System 2 (ROS 2) and Gazebo environment using a simulated 10-rover Martian deployment. During the simulated blackout, our SNN edge navigation achieved a 92.0% survival rate, outperforming traditional planners like Dynamic Window Approach (DWA) (29.0%) and Timed Elastic Band (TEB) (24.3%). The neuromorphic approach also reduced overall system power consumption by 80.0% compared to a traditional unoptimized Graphics Processing Unit (GPU)-based Simultaneous Localization and Mapping (SLAM) baseline. For the map recovery phase, our simulated QAOA proof-of-concept evaluated the map constraints in just 1.2 ms, compared to 50.0 ms for a classical Generalized Iterative Closest Point (G-ICP) and g2o pose-graph approach. Despite the noisy sensor data collected during the blackout, the final quantum-stitched map achieved an 8.54 cm Root Mean Square Error (RMSE). These results show that combining edge-based neuromorphic processing with quantum cloud computing secures swarm survival and accelerates post-disaster data recovery for deep-space missions. Full article

In recent decades, humanoids have become more popular in various applications. However, their applications in human life are more than those in industry. In this paper, a humanoid is used to capture the sets of point clouds of an object for three-dimensional reconstruction. The structured light camera is widely used across diverse 3D scanning applications due to its high resolution, rapid acquisition capability, and adaptability to various material surfaces. Therefore, the humanoid developed by our team holds a structured light camera which captures the point clouds of an object put on a platform for the reconstruction of its 3D digital model. The platform is rotated so that the structured light camera can capture the image of all view angles on the object. Meanwhile, the structured light camera captures point clouds, and the camera of the humanoid recognizes the QR code on the platform so that the sets of point clouds can be distinguished by view angles on the object. Then, the automated registration process of the point cloud sets for a 3D model based on the point-to-plane iterative closest point (ICP) algorithm is proposed. The process incorporates preprocessing techniques, such as downsampling and normal vector estimated from plane, and utilizes the ICP algorithm for registration, ultimately achieving markerless and precision automatic merging of multi-view point cloud data. Experimental results demonstrate that the proposed method with the humanoid can effectively improve the completeness and accuracy of 3D reconstruction models, significantly reduce manual intervention, and enhance the system’s versatility and practical feasibility. Key parameters adjusted for more efficient computation of the ICP algorithm are revealed. In addition, the experimental results of the proposed ICP compared with G-ICP are also included. Full article

Accurate attitude measurement of non-cooperative space targets is essential for on-orbit servicing, active debris removal, and autonomous rendezvous missions. To address the challenges associated with unknown geometry, rapid tumbling motion, and the limited observability of single-view systems, this study proposes a cooperative multi-view measurement framework for three-dimensional reconstruction and attitude estimation. Multiple spacecraft are deployed to form a stable observation configuration, and multi-view image sequences are acquired to strengthen geometric constraints. A learning-based multi-view stereo reconstruction module is used to estimate depth information and reconstruct point clouds, which are further processed through iterative closest point (ICP) registration to derive inter-frame attitude variations. An extended Kalman filter (EKF) is then introduced to improve temporal consistency and suppress measurement noise. Validation is conducted in a numerical simulation using a simplified Fengyun-1 (FY-1) satellite model under a three-spacecraft cooperative fly-around scenario. The simulation results demonstrate that the proposed method achieves high-precision attitude estimation, with attitude errors below $0.3°$ and positional errors within $0.05\mathrm{m}$. Comparative experiments show that the method maintains stable measurement performance under varying observation distances and viewing configurations. The proposed framework provides a reliable and robust measurement solution for dynamic attitude determination of free-tumbling space targets. Full article

Background/Objectives: Statistical shape modeling (SSM) is used to describe transtibial residual-limb morphology for prosthetic socket design, simulation, and future structural testing. However, conventional intrinsic metrics such as compactness, generality, and specificity may not directly reflect geometric fidelity to the original shape. This study examined the relationship between geometric fidelity and SSM evaluation and assessed a cross-sectional shape representation framework for transtibial residual limbs. Methods: Residual-limb surfaces were acquired from 62 adults with unilateral transtibial amputation using a structured-light 3D scanner while preserving habitual limb posture. Two surface-based registration methods, non-rigid iterative closest point and Bayesian coherent point drift, were compared with a cross-sectional representation in which proximal and distal regions were sectioned separately and reconstructed by strip triangulation. Geometric fidelity to the original mesh was quantified using average symmetric surface distance (ASSD). SSM performance was evaluated using compactness, generality, and specificity. Results: The optimal cross-sectional configuration was 60 sections × 72 points. The proposed method showed the best geometric fidelity (ASSD, 1.30 ± 0.14 mm), followed by Bayesian coherent point drift (1.33 ± 0.14 mm) and non-rigid iterative closest point (1.48 ± 0.48 mm). Compactness was highest for the proposed method, reaching 95% cumulative variance in four modes, compared with five and seven modes, respectively, for the two surface-based methods. In geometry-space evaluation, the proposed method showed the lowest specificity error, while differences in generality were statistically significant but small in magnitude. Conclusions: Intrinsic SSM metrics alone were insufficient to judge registration quality in transtibial residual-limb modeling. The cross-sectional representation preserved the original surface geometry more faithfully than the evaluated surface-based methods while maintaining competitive SSM performance. Full article

Airborne LiDAR data acquired before and after the 2024 Noto Peninsula earthquake in Japan were used to estimate three-dimensional (3D) ground-surface displacements based on the Iterative Closest Point (ICP) algorithm. Digital elevation (terrain) models (DEMs) were generated from pre-earthquake point cloud data acquired by Ishikawa Prefecture and compared with post-earthquake DEMs developed by the Forestry Agency of Japan. Three-dimensional coseismic displacements were derived from the spatial correlations between pre- and post-event DEMs for 50 m × 50 m tiles. The results depend on the tile size and are influenced by ground movements within and surrounding each tile. Therefore, moving-average windows of 250 m and 550 m were applied to the 50 m tiles to obtain continuous 3D displacement fields across the ground surface. A comparison between GNSS-measured displacements and the corresponding moving-average estimates for tiles containing triangulation points and continuously operating reference stations (CORSs) showed that the accuracy of the estimated displacements in all three components was within 0.2 m in terms of the root mean square error (RMSE). Full article

The digital preservation of built cultural heritage requires precise documentation techniques capable of capturing complex architectural geometries often affected by occlusions and data voids. This study presents a robust multi-sensor fusion workflow integrating Terrestrial Laser Scanning (TLS) and Unmanned Aerial Vehicle (UAV) photogrammetry for the 3D reconstruction of the Hasaköy (Sasima) Church in Niğde, Türkiye. To address the limitations of traditional registration methods, specifically the susceptibility of the Iterative Closest Point (ICP) algorithm to local minima in datasets with partial overlaps, this study proposes a fine-tuning approach based on the Multi-population Based Differential Evolution (MDE) algorithm. The methodology employs a coarse-to-fine strategy, initiating with Fast Point Feature Histogram (FPFH) extraction and RANSAC (Random Sample Consensus) for global alignment, followed by TR-ICP, MDE, PSO, and Aquila Optimizer (AO) evaluation, computational-time analysis, FPFH-radius sensitivity testing, and 6-DoF transformation decomposition to characterize both accuracy and operational cost. In the 30-run fine-tuning evaluation, MDE reduced the mean bidirectional trimmed RMSE from 0.4152 m for TR-ICP to 0.3726 m. With a population parameter of 10, MDE retained a low median RMSE of 0.3718 m, while PSO exhibited a wider stochastic tail under the same bounded 6-DoF search budget. AO produced a higher mean bidirectional trimmed RMSE of 0.5233 m. The decimeter-scale bidirectional RMSE should be interpreted as a cross-source, partial-overlap distance metric rather than sensor precision; the overlapping facade objective was approximately 2.4–2.8 cm, and the UAV block was independently controlled with a 1.34 cm GCP RMSE. This study establishes a transparent and reproducible framework for heritage documentation, supporting the faithful digital preservation of endangered monuments with complex typologies. Full article

As robotics technology advances, quadruped robots have become capable of operating in complex environments with varying elevation, including ramps and level changes that are challenging for conventional wheeled platforms. While this terrain adaptability opens new opportunities for inspection, rescue, and exploration tasks, the repetitive impacts, frequent ground-contact transitions, and abrupt postural changes inherent to legged locomotion pose significant challenges for LiDAR odometry. High-frequency gait vibrations and abrupt attitude changes introduce intra-scan motion distortion that conventional single-twist deskewing cannot adequately suppress. In addition, sparse vertical geometric constraints in elevation-varying environments weaken Z-axis observability, allowing vertical drift to corrupt the horizontal pose estimate through Hessian coupling. To address these failure modes within a LiDAR-only framework, we propose a Piecewise-Constant Velocity deskewing scheme that partitions each scan into multiple temporal segments with safety clamping on vertical and attitude components, together with a two-stage ICP that decouples SE(3) optimization into horizontal (x, y, yaw) and vertical (z, roll, pitch) stages and applies observability-aware weighting in the vertical update. The proposed odometry front-end is evaluated on four real-world sequences collected with a Unitree Go2 quadruped robot equipped with a Velodyne VLP-16 LiDAR. Experimental results show consistently lower Absolute Pose Error (APE) than ICP, KISS-ICP, and F-LOAM across all sequences. Vertical drift suppression is most pronounced in the ramp-containing sequences, where baseline methods exhibit substantial Z-axis divergence. Full article

Three-dimensional (3D) ear morphology is critical for the design of in-the-ear hearing aids, earphones, transcutaneous auricular vagus nerve stimulation (taVNS) electrodes, and auricular reconstruction, yet most existing ear shape models still rely on manually placed landmarks. Here, a fully annotation-free pipeline is presented for constructing a 3D ear atlas and statistical shape model (SSM) of the auricular bowl from 50 surface meshes. Individual ears are iteratively registered to a current atlas using rigid the iterative closest point (ICP) algorithm followed by a bidirectional thin-plate spline (BiTPS) deformation, and dense surface correspondences are established by nearest-neighbour mapping. Registration quality is quantified using mean and maximum nearest-neighbour distance, symmetric Chamfer-$L_2$ distance and coverage. Furthermore, SSM-derived bowl height and width are validated against manual 3D mesh measurements in Geomagic Design X. Across five atlas iterations, the BiTPS pipeline substantially reduces registration errors and increases coverage, and principal component analysis (PCA) derived dimensions show excellent agreement with manual measurements (Pearson $r\ge 0.98$, ICC $\ge 0.98$). The proposed framework yields a stable, anatomically plausible ear atlas and an interpretable low-dimensional SSM without manual landmarks, providing a computational basis for the geometric optimization of ear-related medical and wearable devices. Full article

Accurate complete-arch digital implant impressions remain challenging because cumulative image stitching distortion may increase across geometrically complex edentulous arches. This in vitro study evaluated the influence of implant spatial configuration on the trueness of complete-arch digital implant impressions obtained using current-generation intraoral scanners. Three edentulous mandibular models representing different implant spatial configurations were fabricated: closely spaced parallel implants, widely distributed parallel implants, and angulated implants. Seven intraoral scanners (Trios 3, Trios 4, Trios 5, Medit i500, Primescan 1, Primescan 2, and Aoralscan 3) were evaluated. Ten scans were acquired per model and scanner, generating 210 STL datasets. A CAD replacement workflow based on scan body library geometries was performed prior to deviation analysis. Trueness was evaluated using root-mean-square (RMS) deviation values following iterative closest point alignment with reference datasets obtained using a laboratory scanner. Statistical analysis was performed using two-way ANOVA and post hoc comparisons (α = 0.05). Significant differences were observed among scanners (p < 0.001), implant configurations (p < 0.001), and their interaction (p < 0.001). Lower RMS deviation values were generally observed in the closely spaced implant configuration, whereas widely distributed implants demonstrated the highest deviations across most scanners. Primescan 1 and Primescan 2 exhibited lower RMS deviation values and smaller increases in distortion across geometrically complex configurations. The spatial configuration of implants significantly influenced the trueness of complete-arch digital implant impressions. Increased implant spatial complexity was associated with greater cumulative stitching distortion during intraoral scanning procedures. Scanner performance varied with implant configuration, suggesting differing resistance to cumulative distortion among current-generation intraoral scanners. Full article

Background: Statistical shape modeling and generative tooth synthesis require dental point clouds in canonical poses. This study compared canonicalization methods and proposed a hybrid pipeline pairing principal-axis alignment with a neural orientation guide and a trained residual correction. Methods: Seven classical, neural, and hybrid methods were evaluated on 9060 upper tooth point clouds across seven classes from 3DTeethSeg (891 patients, 1805 held out for validation) and 1465 external first molars from FDI16. Alignment was measured by Chamfer Distance to per-sample target poses (CD Target, validation only), Chamfer Distance to class templates (CD Template, both sets), and geodesic rotation error. Results: Neural-guided PCA selection with residual refinement (gPCA-rPointNet) reached the lowest CD Target (0.62 ± 2.43 × 10⁻³) and geodesic rotation error (3.3 ± 14.5 degrees), with 98.2% of predictions below 15 degrees. On the external set, the four PCA-based methods gave a lower CD Template than methods without geometric initialization. Conclusions: A neural orientation guide placed before principal-axis candidate selection resolved the PCA eigenvector sign ambiguity responsible for 180-degree failures on near-symmetric tooth crowns. Residual correction further reduced rotation error. The same pipeline produced consistent canonical poses for first molars on the external dataset, with validation on other tooth classes remaining limited. Full article

To address the issue where conventional initial registration methods combined with the Iterative Closest Point (ICP) algorithm are highly sensitive to initial parameters such as point cloud density and pose—often resulting in degraded accuracy or even misregistration—this paper proposes a Lidar point cloud registration method integrating triangular mesh features. First, Crust Triangulation is employed to construct a triangular mesh from the input point cloud. Then, the keypoint extraction based on triangular meshes, termed KE-TM, is introduced. Subsequently, a Triangle Feature Histogram (TFH) is constructed as the feature descriptor. Based on this, an initial alignment method grounded in triangular meshes, referred to as TM-IA, is developed to achieve coarse registration of point clouds. Finally, the ICP algorithm is applied to refine the alignment. Comparative experiments conducted on incomplete Bunny point clouds demonstrate that the proposed KE-TM maintains a higher keypoint repeatability under reduced point cloud density. The combined TM-IA and ICP registration method can achieve rotation errors within 1° and translation errors within 1 mm under small initial pose deviations, while also maintaining robust performance under larger initial misalignments. Compared with traditional methods, the proposed method significantly reduces sensitivity to initial parameters and improves the accuracy. This method has certain practical significance for the precise alignment of 3D point clouds. Full article

Additive manufacturing (AM) enables customized, efficient restorative workflows, though the accuracy of 3D-printed restorations may be compromised by polymerization, sintering shrinkage, and post-processing. This study evaluated the geometric accuracy of 3D-printed partial restorations compared with the computer-aided design (CAD) reference. The null hypothesis stated that no significant differences would be found between Varseo Smile Crown^plus (by BEGO, Italy) and IRIXMax (by DWS System, Italy) materials, which are printed and cured with different technologies. A model was prepared for an overlay and designed with a 1.5 mm uniform thickness. Restorations were produced in two groups with two different printing processes: DLP (digital light processing)-printed Varseo Smile Crown^plus and SLA (stereolithography)-printed IRIXMax. Six samples per group were printed at 90° orientation and scanned. Meshes were aligned to the master geometry via pre-alignment and ICP (Iterative Closest Point) registration. Deviations were quantified in CloudCompare using mean, standard deviation (SD), and 90th percentile values. IRIXMax showed the lowest deviations from the ideal geometry, while Varseo Smile Crown^plus exhibited greater variability. Pairwise comparisons found IRIXMax significantly more accurate than Varseo Smile Crown^plus. Color maps confirmed material-specific deviation patterns. IRIXMax provided the highest geometric accuracy. Material-specific calibration is essential for reliable 3D-printed definitive restorations. Full article