Fig 4 - uploaded by Chenlei Lv
Content may be subject to copyright.
An instance of density adjustment. The red point cloud is the input point cloud with non-uniform density. The green point cloud is processed by octree with uniform density.
Source publication
With rapid development of 3D scanning technology, 3D point cloud based research and applications are becoming more popular. However, major difficulties are still exist which affect the performance of point cloud utilization. Such difficulties include lack of local adjacency information, non-uniform point density, and control of point numbers. In th...
Context in source publication
Similar publications
Problems such as redundancy of detection model parameters make it difficult to apply to factory embedded device applications. This paper focuses on the analysis of different existing deep learning model compression algorithms and proposes a model pruning algorithm based on geometric median filtering for structured pruning and compression of defect...
In point cloud compression, exploiting temporal redundancy for inter predictive coding is challenging because of the irregular geometry. This paper proposes an efficient block-based inter-coding scheme for color attribute compression. The scheme includes integer-precision motion estimation and an adaptive graph based in-loop filtering scheme for im...
Citations
... Based on the optimized distance field, the accuracy of local regions can be assured and the quality of the reconstructed mesh is improved. Considering the time cost of Voronoi cell estimation, some methods [22,23] attempt to optimize the distance field directly. However, the solution changes the original point cloud in local tangent space excessively. ...
... The advantages of such works include high quality of the triangulation result and robust to different local points' density. Based on the isotropic remeshing, Lv et al. proposed a point cloud-based reconstruction method [22] to generate isotropic mesh. After that, he extended the framework to output curvature adaptive result [23]. ...
Shape reconstruction from 3D point clouds is one of the most important topic in the field of computer graphics. In this paper, we propose a subdivision-based framework for this topic. The framework includes two parts: distance field optimization and mesh generation. The first part optimizes a point cloud into an approximately isotropic one based on a subdivision structure. The second part is to generate a triangular mesh from the optimized point cloud. The mesh is regarded as the result of shape reconstruction. The advantages of our method includes accurate geometric consistency, improved mesh quality, controllable point number, and fast speed. Experiments indicate that our method has good performance for shape reconstruction (compare to the state-of-the-art, our method achieves five and six times improvement in Hausdorff distance-based measurement and density estimation). The executable file is available: (https://github.com/vvvwo/Parallel-Structure-ShapeReconstruction)
... The DIN detection aims to search intrinsic neighbors under the geodesic distance metric according to the manifold constraint. It has been shown that the intrinsic neighbors can improve local region representation [5]. The intrinsic neighbors reduce the probability of misidentifying points with small Euclidean distances produced by sharp curvature changes. ...
... In general, the curve parametric function is defined by the geodesic path, and the intrinsic neighbor is detected based on the geodesic distance. It is shown in [5] that the performance of intrinsic neighbor detection is good in point cloud-based applications, including simplification, resampling, and reconstruction. However, the implementation of intrinsic neighbor detection is complicated in practice. ...
As a significant geometric feature of 3D point clouds, sharp features play an important role in shape analysis, 3D reconstruction, registration, localization, etc. Current sharp feature detection methods are still sensitive to the quality of the input point cloud, and the detection performance is affected by random noisy points and non-uniform densities. In this paper, using the prior knowledge of geometric features, we propose a Multi-scale Laplace Network (MSL-Net), a new deep-learning-based method based on an intrinsic neighbor shape descriptor, to detect sharp features from 3D point clouds. Firstly, we establish a discrete intrinsic neighborhood of the point cloud based on the Laplacian graph, which reduces the error of local implicit surface estimation. Then, we design a new intrinsic shape descriptor based on the intrinsic neighborhood, combined with enhanced normal extraction and cosine-based field estimation function. Finally, we present the backbone of MSL-Net based on the intrinsic shape descriptor. Benefiting from the intrinsic neighborhood and shape descriptor, our MSL-Net has simple architecture and is capable of establishing accurate feature prediction that satisfies the manifold distribution while avoiding complex intrinsic metric calculations. Extensive experimental results demonstrate that with the multi-scale structure, MSL-Net has a strong analytical ability for local perturbations of point clouds. Compared with state-of-the-art methods, our MSL-Net is more robust and accurate. The code is publicly available at
... To improve the performance for alignment, such points should be processed first. We employ the simplification processing [20] and outlier deletion [21] as a preprocessing step. After preprocessing, the density of point cloud is optimized and point number is uniformed. ...
As an important topic in 3D vision, the point cloud registration has been widely used in various applications, including location, reconstruction, and shape recognition. In this paper, we propose a new registration method for this topic, which utilizes statistical shape features (SSFs) and manifold metrics to estimate the transformation matrix. The SSFs are extracted to establish a compact representation for the original point cloud. Then, the representation is mapped into a manifold to reduce the influences of different scales and translations. Finally, the manifold metric is used to minimize the distance based on the compact representation and the pose can be estimated. The advantages of our method include robustness to nonuniform densities, insensitivity to missing parts, and better performance to handle large difference of poses. Experimental results show that our method achieves significant improvements compared to the state of the art methods.
... The mesh need not be structured, whilst the uniformity of facets is the focus of this work. This is an established topic (e.g. in computer graphics) where various approaches are permissible, such as resampling-based [28], Voronoi-based [29], and virtual-interaction-force-based [30] methods. A more uniform construction of the discrete mesh certainly improves the uniformity of the solved path with the proposed algorithm. ...
A novel mechanism to generate nonrevisiting uniform coverage (NUC) paths on arbitrarily shaped object surfaces is presented in this work. Given a nonplanar surface, nonzero curvature makes traditional homeomorphic fitting of regular template coverage paths from planar regions onto the object surface non-distance-preserving. Any coverage path with a realistic tooling size derived in this way will suffer from overlaps and missing gaps when transformed onto the object surfaces, unable to uniformly cover the target. To overcome this, a discretization process is adopted to represent the object surface as a uniform unstructured mesh, with resolution set in accordance to the tool size. It is proven that a coverage skeleton path must exist by mesh subdivision refinement which, after a local optimization step to improve overlap, missing gaps, and smoothness, gives rise to template-free superior NUC paths. Extensive simulation examples are presented to prove the validity of the proposed strategy in realistic settings. The proposed scheme is able to achieve 95.9% coverage on benchmark surface tests, outperforming comparable coverage algorithms, such as a homeomorphic boustrophedon mapping, which can at best achieve 80.9% coverage, or more recent state-of-the-art methods able to reach 94.7% coverage. An accompanying video is supplied with examples, including a real-world implementation of an NUC path tracked by a manipulator. An open-source implementation has been made available.
... 为了提高收敛速度和收敛稳定性, 国内外学者做出了 很多改进, 如TDM(tangent distance minimization)算 法 [18] 基于点到面距离建立目标函数进行优化, 该算法 具有二次收敛速度, 但收敛稳定性降低; Li等人 [19] . 诸如不依赖于初始参数克服跨源点云的配准 算法 [27] 和以Welsch函数度量结合Anderson加速的MM 框架配准算法 [28] 均提高了点云配准的鲁棒性. 然而, 上述算法在面对结构偏差、点云缺失、密度不均、余 量不均等问题时, 会陷入局部最优解, 应用范围有限. ...
... The center extracted from the point cloud is stable and reliable, even the input point cloud has non-uniform density. In our previous work [52], the performance of the alignment with a rough implementation has been verified. However, centers of point clouds with incomplete geometric structures cannot be aligned. ...
Point cloud registration is a popular topic that has been widely used in 3D model reconstruction, location, and retrieval. In this paper, we propose a new registration method, KSS-ICP, to address the rigid registration task in Kendall shape space (KSS) with Iterative Closest Point (ICP). The KSS is a quotient space that removes influences of translations, scales, and rotations for shape feature-based analysis. Such influences can be concluded as the similarity transformations that do not change the shape feature. The point cloud representation in KSS is invariant to similarity transformations. We utilize such property to design the KSS-ICP for point cloud registration. To tackle the difficulty to achieve the KSS representation in general, the proposed KSS-ICP formulates a practical solution that does not require complex feature analysis, data training, and optimization. With a simple implementation, KSS-ICP achieves more accurate registration from point clouds. It is robust to similarity transformation, non-uniform density, noise, and defective parts. Experiments show that KSS-ICP has better performance than the state-of-the-art.
... Zhang et al. [33] proposed a remeshing method with several hard constraints, including bounding approximation errors and ensuring Delaunay conditions. Lv et al. [34] introduced isotropic resampling for mesh reconstruction. The obtuse triangles are effectively reduced to fit the Delaunay conditions. ...
With the development of 3D digital geometry technology, 3D triangular meshes are becoming more useful and valuable in industrial manufacturing and digital entertainment. A high quality triangular mesh can be used to represent a real world object with geometric and physical characteristics. While anisotropic meshes have advantages of representing shapes with sharp features (such as trimmed surfaces) more efficiently and accurately, isotropic meshes allow more numerically stable computations. When there is no anisotropic mesh requirement, isotropic triangles are always a good choice. In this paper, we propose a remeshing method to convert an input mesh into an adaptively isotropic one based on a curvature smoothed field (CSF). With the help of the CSF, adaptively isotropic remeshing can retain the curvature sensitivity, which enables more geometric features to be kept, and avoid the occurrence of obtuse triangles in the remeshed model as much as possible. The remeshed triangles with locally isotropic property benefit various geometric processes such as neighbor-based feature extraction and analysis. The experimental results show that our method achieves better balance between geometric feature preservation and mesh quality improvement compared to peers. We provide the implementation codes of our resampling method at
https://github.com/vvvwo/Adaptively-Isotropic-Remeshing</uri
... The center extracted from the point cloud is stable and reliable, even the input point cloud has non-uniform density. In our previous work [52], the performance of the alignment with a rough implementation has been verified. However, centers of point clouds with incomplete geometric structures cannot be aligned. ...
Point cloud registration is a popular topic which has been widely used in 3D model reconstruction, location, and retrieval. In this paper, we propose a new registration method, KSS-ICP, to address the rigid registration task in Kendall shape space (KSS) with Iterative Closest Point (ICP). The KSS is a quotient space that removes influences of translations, scales, and rotations for shape feature-based analysis. Such influences can be concluded as the similarity transformations that do not change the shape feature. The point cloud representation in KSS is invariant to similarity transformations. We utilize such property to design the KSS-ICP for point cloud registration. To tackle the difficulty to achieve the KSS representation in general, the proposed KSS-ICP formulates a practical solution that does not require complex feature analysis, data training, and optimization. With a simple implementation, KSS-ICP achieves more accurate registration from point clouds. It is robust to similarity transformation, non-uniform density, noise, and defective parts. Experiments show that KSS-ICP has better performance than the state of the art.
Sampling is a crucial concern for outdoor light detection and ranging (LiDAR) point cloud registration due to the large amounts of point cloud. Numerous algorithms have been devised to tackle this issue by selecting key points. However, these approaches often necessitate extensive computations, giving rise to challenges related to computational time and complexity. This letter proposes a multi‐domain uniform sampling method (MDU‐sampling) for large‐scale outdoor LiDAR point cloud registration. The feature extraction based on deep learning aggregates information from the neighbourhood, so there is redundancy between adjacent features. The sampling method in this paper is carried out in the spatial and feature domains. First, uniform sampling is executed in the spatial domain, maintaining local point cloud uniformity. This is believed to preserve more potential point correspondences and is beneficial for subsequent neighbourhood information aggregation and feature sampling. Subsequently, a secondary sampling in the feature domain is performed to reduce redundancy among the features of neighbouring points. Notably, only points on the same ring in LiDAR data are considered as neighbouring points, eliminating the need for additional neighbouring point search and thereby speeding up processing rates. Experimental results demonstrate that the approach enhances accuracy and robustness compared with benchmarks.
