Point Cloud Registration Method Research Articles

A Novel Point Cloud Registration Method for Multimedia Communication in Automated Driving Metaverse

A Novel Point Cloud Registration Method for Multimedia Communication in Automated Driving Metaverse

Sparse-to-Dense Point Cloud Registration Based on Rotation-Invariant Features

Point cloud registration is a critical problem because it is the basis of many 3D vision tasks. With the popularity of deep learning, many scholars have focused on leveraging deep neural networks to address the point cloud registration problem. However, many of these methods are still sensitive to partial overlap and differences in density distribution. For this reason, herein, we propose a method based on rotation-invariant features and using a sparse-to-dense matching strategy for robust point cloud registration. Firstly, we encode raw points as superpoints with a network combining KPConv and FPN, and their associated features are extracted. Then point pair features of these superpoints are computed and embedded into the transformer to learn the hybrid features, which makes the approach invariant to rigid transformation. Subsequently, a sparse-to-dense matching strategy is designed to address the registration problem. The correspondences of superpoints are obtained via sparse matching and then propagated to local dense points and, further, to global dense points, the byproduct of which is a series of transformation parameters. Finally, the enhanced features based on spatial consistency are repeatedly fed into the sparse-to-dense matching module to rebuild reliable correspondence, and the optimal transformation parameter is re-estimated for final alignment. Our experiments show that, with the proposed method, the inlier ratio and registration recall are effectively improved, and the performance is better than that of other point cloud registration methods on 3DMatch and ModelNet40.

Rigid point cloud registration based on correspondence cloud for image-to-patient registration in image-guided surgery.

Image-to-patient registration aligns preoperative images to intra-operative anatomical structures and it is a critical step in image-guided surgery (IGS). The accuracy and speed of this step significantly influence the performance of IGS systems. Rigid registration based on paired points has been widely used in IGS, but studies have shown its limitations in terms of cost, accuracy, and registration time. Therefore, rigid registration of point clouds representing the human anatomical surfaces has become an alternative way for image-to-patient registration in the IGSsystems. We propose a novel correspondence-based rigid point cloud registration method that can achieve global registration without the need for pose initialization. The proposed method is less sensitive to outliers compared to the widely used RANSAC-based registration methods and it achieves high accuracy at a high speed, which is particularly suitable for the image-to-patient registration inIGS. We use the rotation axis and angle to represent the rigid spatial transformation between two coordinate systems. Given a set of correspondences between two point clouds in two coordinate systems, we first construct a 3D correspondence cloud (CC) from the inlier correspondences and prove that the CC distributes on a plane, whose normal is the rotation axis between the two point clouds. Thus, the rotation axis can be estimated by fitting the CP. Then, we further show that when projecting the normals of a pair of corresponding points onto the CP, the angle between the projected normal pairs is equal to the rotation angle. Therefore, the rotation angle can be estimated from the angle histogram. Besides, this two-stage estimation also produces a high-quality correspondence subset with high inlier rate. With the estimated rotation axis, rotation angle, and the correspondence subset, the spatial transformation can be computed directly, or be estimated using RANSAC in a fast and robust way within only 100iterations. To validate the performance of the proposed registration method, we conducted experiments on the CT-Skull dataset. We first conducted a simulation experiment by controlling the initial inlier rate of the correspondence set, and the results showed that the proposed method can effectively obtain a correspondence subset with much higher inlier rate. We then compared our method with traditional approaches such as ICP, Go-ICP, and RANSAC, as well as recently proposed methods like TEASER, SC2-PCR, and MAC. Our method outperformed all traditional methods in terms of registration accuracy and speed. While achieving a registration accuracy comparable to the recently proposed methods, our method demonstrated superior speed, being almost three times faster thanTEASER. Experiments on the CT-Skull dataset demonstrate that the proposed method can effectively obtain a high-quality correspondence subset with high inlier rate, and a tiny RANSAC with 100 iterations is sufficient to estimate the optimal transformation for point cloud registration. Our method achieves higher registration accuracy and faster speed than existing widely used methods, demonstrating great potential for the image-to-patient registration, where a rigid spatial transformation is needed to align preoperative images to intra-operative patientanatomy.

A fast point cloud registration method based on spatial relations and features

Abstract Point cloud registration plays a crucial role in mobile robot localization, map building and 3D model reconstruction. However, it remains challenged by issues such as compromised accuracy and sluggish efficiency, posing significant obstacles in achieving precise and timely alignments. Therefore, we propose a lightweight and fast point cloud registration method. Firstly, we mesh the 3D point cloud, compared with the traditional gridded point cloud method, it achieves initial point cloud registration by preserving the curvature characteristics of the internal point cloud, and utilizing the spatial relationship between grid cells and the quantitative relationship between the internal point cloud. Moreover, we adopt an iterative nearest point (ICP) based on KD-Tree to realize the fine registration. So, our method does not necessitate intricate feature analysis and data training, and is resilient to similar transformations, non-uniform densities and noise. Finally, we conduct point cloud registration experiments using multiple publicly available point cloud datasets and compare them with several point cloud registration methods. The results demonstrate it is able to accomplish the point cloud registration quickly and exhibit high accuracy. More importantly, it maintains its efficacy and robustness even in the presence of noisy and defective point clouds.

A Registration Method of Overlap Aware Point Clouds Based on Transformer-to-Transformer Regression

Transformer has recently become widely adopted in point cloud registration. Nevertheless, Transformer is unsuitable for handling dense point clouds due to resource constraints and the sheer volume of data. We propose a method for directly regressing the rigid relative transformation of dense point cloud pairs. Specifically, we divide the dense point clouds into blocks according to the down-sampled superpoints. During training, we randomly select point cloud blocks with varying overlap ratios, and during testing, we introduce the overlap-aware Rotation-Invariant Geometric Transformer Cross-Encoder (RIG-Transformer), which predicts superpoints situated within the common area of the point cloud pairs. The dense points corresponding to the superpoints are inputted into the Transformer Cross-Encoder to estimate their correspondences. Through the fusion of our RIG-Transformer and Transformer Cross-Encoder, we propose Transformer-to-Transformer Regression (TTReg), which leverages dense point clouds from overlapping regions for both training and testing phases, calculating the relative transformation of the dense points by using the predicted correspondences without random sample consensus (RANSAC). We have evaluated our method on challenging benchmark datasets, including 3DMatch, 3DLoMatch, ModelNet, and ModelLoNet, demonstrating up to a 7.2% improvement in registration recall. The improvements are attributed to our RIG-Transformer module and regression mechanism, which makes the features of superpoints more discriminative.

GraM: Geometric Structure Embedding into Attention Mechanisms for 3D Point Cloud Registration

3D point cloud registration is a crucial technology for 3D scene reconstruction and has been successfully applied in various domains, such as smart healthcare and intelligent transportation. With theoretical analysis, we find that geometric structural relationships are essential for 3D point cloud registration. The 3D point cloud registration method achieves excellent performance only when fusing local and global features with geometric structure information. Based on these discoveries, we propose a 3D point cloud registration method based on geometric structure embedding into the attention mechanism (GraM), which can extract the local features of the non-critical point and global features of the corresponding point containing geometric structure information. According to the local and global features, the simple regression operation can obtain the transformation matrix of point cloud pairs, thereby eliminating the semantics that ignores the geometric structure relationship. GraM surpasses the state-of-the-art results by 0.548° and 0.915° regarding the relative rotation error on ModelNet40 and LowModelNet40, respectively.

An effective point cloud registration method for three-dimensional reconstruction of pressure piping

Abstract At present, industrial scenes with sparse features and weak textures are widely encountered, and the three-dimensional reconstruction of such scenes is a recognized problem. Pressure pipelines have a wide range of applications in fields such as petroleum engineering, chemical engineering, and hydropower station engineering. However, there is no mature solution for the three-dimensional reconstruction of pressure pipes. The main reason is that the typical scenes in which pressure pipes are found also have relatively few features and textures. Traditional three-dimensional reconstruction algorithms based on feature extraction are largely ineffective for such scenes that are lacking in features. In view of the above problems, this paper proposes an improved interframe registration algorithm based on point cloud fitting with cylinder axis vector constraints. By incorporating geometric feature parameters of a cylindrical pressure pipeline, specifically the axis vector of the cylinder, to constrain the traditional iterative closest point algorithm, the accuracy of point cloud registration can be improved in scenarios lacking features and textures, and some environmental uncertainties can be overcome. Finally, using actual laser point cloud data collected from pressure pipelines, the proposed fitting-based point cloud registration algorithm with cylinder axis vector constraints is tested. The experimental results show that under the same conditions, compared with other open-source point cloud registration algorithms, the proposed method can achieve higher registration accuracy. Moreover, integrating this algorithm into an open-source three-dimensional reconstruction algorithm framework can lead to better reconstruction results.

Robust point cloud registration for map-based autonomous robot navigation

Robust point cloud registration for map-based autonomous robot navigation

Recurrent multi-view collaborative registration network for 3D reconstruction and optical measurement of blade profiles

Aligning multiple viewpoints to reconstruct a complete profile is crucial for the three-dimensional optical measurement of blade profiles. As foundational solutions, rigid pairwise point cloud registration methods often struggle to produce satisfactory results due to significant cumulative errors stemming from pairwise registration errors, while current multi-view registration methods also face challenges when their prerequisites conflict with the practical measurement scenarios of blade profiles. To address these issues, this study proposes a learning framework to recover a transformation vector between the coordinate frames of both the optical sensor and the rotational axis in our developed optical measurement system based on extracted adaptive feature embeddings from the initial coordinate representation of viewpoints, which simultaneously aligns all viewpoints into a complete profile without relying on any prerequisites. Furthermore, an elaborate recurrent updating strategy is incorporated into the framework that enables incremental refinement of the transformation vector, thus aiding the framework in meeting the high-precision measurement requirements at the 0.01 mm level. Experimental results from both theoretical and real-world data, conducted on three representative blades and compared against nine state-of-the-art algorithms, consistently demonstrate the superiority of the proposed method in terms of accuracy, time efficiency, and robustness. The source code is available at https://github.com/Clarkxielf/Recurrent-Multi-View-Collaborative-Registration-Network.

Point cloud registration method for indoor depth sensor acquisition system based on dual graph computation with irregular shape factors

AbstractThe registration performance determines the widespread indoor application of 3D models acquired by depth sensors. Many advanced registration methods lack comprehensive feature aggregation and poor generalization capabilities, which improves the mismatching ratio. Here, a dual graph network is proposed by incorporating irregular shape factors to make point cloud features more expressive. At first, we transform point cloud sets into the stellar graph within the local neighbourhood of each point. The deep feature and shape factor of each point are combined in the directional‐connected irregular projection space. Subsequently, the combined features are modelled as the second graph. By the attention mechanism computation, feature information is continuously aggregated with intra‐graph and inter‐graph. Finally, a loss function is utilized to confirm point correspondence and perform the registration through singular value decomposition. Extensive experiments validate that the proposed point cloud registration method achieves state‐of‐the‐art performance.

Research on 3D point cloud alignment algorithm based on SHOT features.

To overcome the problem of the high initial position of the point cloud required by the traditional Iterative Closest Point (ICP) algorithm, in this paper, we propose a point cloud registration method based on normal vector and directional histogram features (SHOT). Firstly, a hybrid filtering method based on the voxel idea is proposed and verified using the measured point cloud data, and the noise removal rates of 97.5%, 97.8%, and 93.8% are obtained. Secondly, in terms of feature point extraction, the original algorithm is optimized, and the optimized algorithm can better extract the missing part of the point cloud. Finally, a fine alignment method based on normal vector and directional histogram features (SHOT) is proposed, and the improved algorithm is compared with the existing algorithm. Taking the Stanford University point cloud data and the self-measured point cloud data as examples, the plotted iteration-error plots can be concluded that the improved method can reduce the number of iterations by 40.23% and 37.62%, respectively.

MSCS-ICP: point cloud registration method using multi-view spatial coordinate system–ICP

The effectiveness of point cloud registration critically determines three-dimensional (3D) reconstruction accuracy involving multi-view sensors. We introduce a multi-view point cloud registration method based on multi-view spatial coordinate system–ICP to solve the problem of 3D point cloud registration from different viewpoints. By integrating a spatial rotation axis line, our method successfully establishes the spatial coordinate system tailored for multi-view sensors, ensuring that 3D point clouds derived from various perspectives are optimally positioned initially. We employ the ICP technique for point cloud merging, facilitating a seamless transition from coarse to refined registration of these multi-view 3D point clouds. During the process of spatial rotation axis line fitting, we present a Ransac-based algorithm tailored for axis line fitting that effectively removes outliers, thus significantly improving the fitting precision. Experimental results from a standard sphere reconstruction reveal that within a measurement scope of 1.3–1.9 m, our proposed method boasts a maximum error of just 0.069 mm, an average absolute error of 0.039 mm, and a root mean square error of 0.043 mm. The speed of our point cloud registration outpaces that of alternative methods. Our method notably elevates the precision and velocity of 3D point cloud registration across diverse views, demonstrating commendable adaptability and resilience.

Efficient low-overlapping point cloud registration based on two-stage network learning

ABSTRACT This letter introduces an efficient registration method for large-scale point clouds with low overlap, which adopts a two-stage transformation learning process. In the first stage, we integrate a point-voxel encoding structure with an attention mechanism to predict rotation and point-wise importance weight. In the second stage, we employ a PointNet-based structure to estimate translation using optimized data. By adopting this two-stage procedure, our model can effectively learn rotation and translation separately, thereby increasing flexibility. We conducted extensive experiments on two large-scale indoor datasets (3Dmatch and S3DIS) and an outdoor dataset (KITTI odometry). The results demonstrate that our method outperforms traditional and deep learning-based approaches, achieving state-of-the-art performance in registration. Furthermore, our method exhibits superior generalization capabilities, highlighting its effectiveness in various registration scenarios.

SPEAL: Skeletal Prior Embedded Attention Learning for Cross-Source Point Cloud Registration

Point cloud registration, a fundamental task in 3D computer vision, has remained largely unexplored in cross-source point clouds and unstructured scenes. The primary challenges arise from noise, outliers, and variations in scale and density. However, neglected geometric natures of point clouds restricts the performance of current methods. In this paper, we propose a novel method termed SPEAL to leverage skeletal representations for effective learning of intrinsic topologies of point clouds, facilitating robust capture of geometric intricacy. Specifically, we design the Skeleton Extraction Module to extract skeleton points and skeletal features in an unsupervised manner, which is inherently robust to noise and density variances. Then, we propose the Skeleton-Aware GeoTransformer to encode high-level skeleton-aware features. It explicitly captures the topological natures and inter-point-cloud skeletal correlations with the noise-robust and density-invariant skeletal representations. Next, we introduce the Correspondence Dual-Sampler to facilitate correspondences by augmenting the correspondence set with skeletal correspondences. Furthermore, we construct a challenging novel cross-source point cloud dataset named KITTI CrossSource for benchmarking cross-source point cloud registration methods. Extensive quantitative and qualitative experiments are conducted to demonstrate our approach’s superiority and robustness on both cross-source and same-source datasets. To the best of our knowledge, our approach is the first to facilitate point cloud registration with skeletal geometric priors.

Point cloud registration with quantile assignment

Point cloud registration is a fundamental problem in computer vision. The problem encompasses critical tasks such as feature estimation, correspondence matching, and transformation estimation. The point cloud registration problem can be cast as a quantile matching problem. We refined the quantile assignment algorithm by integrating prevalent feature descriptors and transformation estimation methods to enhance the correspondence between the source and target point clouds. We evaluated the performances of these descriptors and methods with our approach through controlled experiments on a dataset we constructed using well-known 3D models. This systematic investigation led us to identify the most suitable methods for complementing our approach. Subsequently, we devised a new end-to-end, coarse-to-fine pairwise point cloud registration framework. Finally, we tested our framework on indoor and outdoor benchmark datasets and compared our results with state-of-the-art point cloud registration methods.

Point Cloud Registration Method Based on Geometric Constraint and Transformation Evaluation.

Existing point-to-point registration methods often suffer from inaccuracies caused by erroneous matches and noisy correspondences, leading to significant decreases in registration accuracy and efficiency. To address these challenges, this paper presents a new coarse registration method based on a geometric constraint and a matrix evaluation. Compared to traditional registration methods that require a minimum of three correspondences to complete the registration, the proposed method only requires two correspondences to generate a transformation matrix. Additionally, by using geometric constraints to select out high-quality correspondences and evaluating the matrix, we greatly increase the likelihood of finding the optimal result. In the proposed method, we first employ a combination of descriptors and keypoint detection techniques to generate initial correspondences. Next, we utilize the nearest neighbor similarity ratio (NNSR) to select high-quality correspondences. Subsequently, we evaluate the quality of these correspondences using rigidity constraints and salient points' distance constraints, favoring higher-scoring correspondences. For each selected correspondence pair, we compute the rotation and translation matrix based on their centroids and local reference frames. With the transformation matrices of the source and target point clouds known, we deduce the transformation matrix of the source point cloud in reverse. To identify the best-transformed point cloud, we propose an evaluation method based on the overlap ratio and inliers points. Through parameter experiments, we investigate the performance of the proposed method under various parameter settings. By conducting comparative experiments, we verified that the proposed method's geometric constraints, evaluation methods, and transformation matrix computation consistently outperformed other methods in terms of root mean square error (RMSE) values. Additionally, we validated that our chosen combination for generating initial correspondences outperforms other descriptor and keypoint detection combinations in terms of the registration result accuracy. Furthermore, we compared our method with several feature-matching registration methods, and the results demonstrate the superior accuracy of our approach. Ultimately, by testing the proposed method on various types of point cloud datasets, we convincingly established its effectiveness. Based on the evaluation and selection of correspondences and the registration result's quality, our proposed method offers a solution with fewer iterations and higher accuracy.

Spatial deformable transformer for 3D point cloud registration

Deformable attention only focuses on a small group of key sample-points around the reference point and make itself be able to capture dynamically the local features of input feature map without considering the size of the feature map. Its introduction into point cloud registration will be quicker and easier to extract local geometric features from point cloud than attention. Therefore, we propose a point cloud registration method based on Spatial Deformable Transformer (SDT). SDT consists of a deformable self-attention module and a cross-attention module where the deformable self-attention module is used to enhance local geometric feature representation and the cross-attention module is employed to enhance feature discriminative capability of spatial correspondences. The experimental results show that compared to state-of-the-art registration methods, SDT has a better matching recall, inlier ratio, and registration recall on 3DMatch and 3DLoMatch scene, and has a better generalization ability and time efficiency on ModelNet40 and ModelLoNet40 scene.

Multi-View consistency-based point cloud registration method with low overlap rate

Accurate and efficient workpiece measurement is crucial for workpiece processing and quality monitoring. Non-contact optical measurement methods have gained more attention due to their simplicity, efficiency, and flexibility compared to complicated and inefficient contact measurement methods. Multi-view registration of measurement data is a key issue in workpiece measurement, as it relies on the system’s geometric accuracy and motion stability, presenting challenges such as the insufficient overlap of multi-viewpoint cloud data and cumulative error. To address these challenges, this paper proposes a multi-view planning and registration algorithm with a low overlap rate. The multi-view planning algorithm employs a greedy method to plan the scanning viewpoints of the workpiece to obtain complete point cloud data efficiently. The multi-view registration algorithm extracts features using a multi-scale geometric feature extraction network, matches the features based on the Hungarian algorithm, builds a graph, and optimizes workpiece positions based on the G2O algorithm for multi-view registration, effectively reducing cumulative error. Measurement experiments on blade workpieces confirm the feasibility of the proposed algorithms.

Fast Multi-View 3D reconstruction of seedlings based on automatic viewpoint planning

Three-dimensional models of plants provide valuable phenotypic information. Phenotypic measurements of plant structures are essential for monitoring plant growth and understanding plant responses to environmental changes. Existing 3D reconstruction techniques have achieved accurate reconstruction models of some plants such as corn and soybeans. However, several drawbacks exist in current plant 3D reconstruction systems, including high cost, fixed capture perspectives and complex operation. To address these issues and considering the influence of camera capture angles on model reconstruction accuracy, we investigated a viewpoint planning reconstruction method. We designed a plant seedling reconstruction system that utilizes a consumer-grade L515 LiDAR sensor and a precision turntable. We establish a viewpoint rule based on the camera imaging model of the three-dimensional spatial structure of leaves, constructing minimum constraints on the leaf normal vector and the camera optical axis. This enables to determine the optimal capture viewpoint for each leaf to obtain the maximum leaf information. The angle β between the leaf normal vector and the camera optical axis serves as the basis for the turntable rotation, systematically planning the rotation of the turntable to enable the camera to capture the maximum useful leaf information. Unlike static camera-based turntable reconstruction systems that capture images at fixed angle intervals, we plan the rotation of the turntable based on the acquired information. This allows us to obtain more effective point cloud information of plant seedlings from the same or even fewer images, reducing the collection of redundant images and reconstructing more accurate plant seedling 3D models. Additionally, we measured commonly used leaf traits in plant phenotypic studies, such as leaf length, leaf width, and leaf area. The leaf area measured based on the reconstructed seedling model exhibited high accuracy (R2 > 0.99). The results of this study demonstrate that the consumer-grade L515 LiDAR sensor combined with the proposed viewpoint planning method can effectively reconstruct accurate seedling 3D models and measure phenotypic information. Due to the absence of error accumulation caused by adjacent view registration, this approach offers advantages such as shorter reconstruction time, higher efficiency and increased accuracy compared to some multi-view point cloud registration and reconstruction methods. Therefore, this system can be applied to three-dimensional reconstruction and phenotype analysis of plant seedlings due to its high efficiency and accuracy.

A Novel Automatic Registration Method for Array InSAR Point Clouds in Urban Scenes

The array interferometric synthetic aperture radar (Array InSAR) system resolves shadow issues by employing two scans in opposite directions, facilitating the acquisition of a comprehensive three-dimensional representation of the observed scene. The point clouds obtained from the two scans need to be transformed into the same coordinate system using registration techniques to create a more comprehensive visual representation. However, the two-point clouds lack corresponding points and exhibit distinct geometric distortions, thereby preventing direct registration. This paper analyzes the error characteristics of array InSAR point clouds and proposes a robust registration method for array InSAR point clouds in urban scenes. It represents the 3D information of the point clouds using images, with pixel positions corresponding to the azimuth and ground range directions. Pixel intensity denotes the average height of points within the pixel. The KAZE algorithm and enhanced matching approach are used to obtain the homonymous points of two images, subsequently determining the transformation relationship between them. Experimental results with actual data demonstrate that, for architectural elements within urban scenes, the relative angular differences of registered facades are below 0.5°. As for ground elements, the Root Mean Square Error (RMSE) after registration is less than 1.5 m, thus validating the superiority of the proposed method.