Point Clouds - Science topic

The Krasnodar Reservoir on the Kuban River is the most important object of the reclamation system in southern Russia with an annual water intake for irrigation of 3.35 billion m 3. The valley reservoir is located on the Azov-Kuban Plain and has an area of 400 km 2 according to operational characteristics. It has been in operation since 1973. As a r...

High-definition (HD) maps for autonomous driving rely on data from mobile mapping systems (MMS), but the high cost of MMS sensors has led researchers to explore cheaper alternatives like low-cost LiDAR sensors. While cost effective, these sensors produce sparser point clouds, leading to poor feature representation and degraded performance in deep l...

In this study, we consider the question of repairing and recovering a low-dimensional manifold embedded in high-dimensional space from noisy scattered data. Given a noisy point cloud sampled from a low-dimensional manifold, suppose that part of the scattered data is missing, which results in holes. In these settings, the main goal is to accurately...

Contact pattern measurement is commonly applied to assess gear transmission and meshing performance in aviation spiral bevel gear (ASBG) manufacturing enterprises. However, these patterns cannot be directly segmented and obtained from point clouds or images because each tooth of the spiral bevel gear has complex 3D spiral surface and texture inform...

New technological developments open novel possibilities for widely applicable methods of ecosystem analyses. We investigated a novel approach using smartphone-based 3D scanning for non-destructive, high-resolution monitoring of above-ground plant biomass. This method leverages Structure from Motion (SfM) techniques with widely accessible smartphone...

LiDAR Simultaneous Localization and Mapping (SLAM) plays a crucial role in intelligent robotics, finding extensive applications in autonomous driving and exploration. The traditional feature-based LiDAR SLAM holds a prominent position due to its robustness and accuracy. However, these methods still exhibit limitations in point cloud preprocessing a...

This paper presents a deep learning-based Scan-vs-BIM methodology for evaluating structural integrity through the extraction of features from As-Built scan and As-Planned Building Information Modeling (BIM) comparison data. Traditional Scan-vs-BIM frameworks often rely on Scan-to-BIM processes to generate point cloud-based mesh models for compariso...

Supervised 3D part segmentation models are tailored for a fixed set of objects and parts, limiting their transferability to open-set, real-world scenarios. Recent works have explored vision-language models (VLMs) as a promising alternative, using multi-view rendering and textual prompting to identify object parts. However, naively applying VLMs in...

Large-scale dynamic three-dimensional (3D) photoacoustic imaging (PAI) is significantly important in clinical applications. In practical implementations, large-scale 3D real-time PAI systems typically utilize sparse two-dimensional (2D) sensor arrays with certain angular deficiencies, necessitating advanced iterative reconstruction (IR) algorithms...

The rice panicle traits substantially influence grain yield, making them a primary target for rice phenotyping studies. However, most existing techniques are limited to controlled indoor environments and have difficulty in capturing the rice panicle traits under natural growth conditions. Here, we developed PanicleNeRF, a novel method that enables...

Ensuring that ground point density after raw point cloud processing meets the accuracy requirements for subsequent DEM construction represents a challenge for field operators during airborne LiDAR data acquisition. In this study, we propose a method to quantify DEM quality by combining the RMSE of elevation and terrain complexity, analyzing the DEM...

Terrestrial laser scanning (TLS) provides highly detailed 3D information of forest environments but is limited to small spatial scales, as data collection is time consuming compared to other remote sensing techniques. Furthermore, TLS data collection is heavily dependent on wind conditions, as the movement of trees negatively impacts the acquired d...

This contribution proposes workflows that allow the transition from photographic and laser surveys to point clouds and geometric meshes designed for structural analysis. The process is complex and, even today, is typically handled using uncontrolled methods. These methods are often unregulated, relying on the transfer of data across multiple softwa...

Due to the scattered, unordered, and unstructured nature of point clouds, it is challenging to extract local features. Existing methods tend to design redundant and less‐discriminative spatial feature extraction methods in the encoder, while neglecting the utilisation of uneven distribution in the decoder. In this paper, the authors fully exploit t...

The sudden development of systems capable of rapidly acquiring dense point clouds has underscored the importance of data processing and pre-processing prior to modeling. This work presents the implementation of a denoising algorithm for point clouds acquired with LiDAR SLAM systems, aimed at optimizing data processing and the reconstruction of surv...

The SLAM problem is a common challenge faced by ROVs working underwater, with the key issue being the accurate estimation of pose. In this work, we make full use of the positional information of point clouds and the surrounding pixel data. To obtain better feature extraction results in specific directions, we propose a method that accelerates the c...

Reconstructing complex structures from planar cross-sections is a challenging problem, with wide-reaching applications in medical imaging, manufacturing, and topography. Out-of-the-box point cloud reconstruction methods can often fail due to the data sparsity between slicing planes, while current bespoke methods struggle to reconstruct thin geometr...

The growing demand for high-accuracy mapping and 3D modeling using unmanned aerial vehicles (UAVs) has accelerated advancements in flight dynamics, positioning accuracy, and imaging technology. Structure from motion (SfM), a computer vision-based approach, is increasingly replacing traditional photogrammetry through facilitating the automation of p...

Protoclusters are high- z overdense regions that will evolve into clusters of galaxies by z = 0, making them ideal for studying galaxy evolution expected to be accelerated by environmental effects. However, it has been challenging to identify protoclusters beyond z = 3 only by photometry due to large redshift uncertainties hindering statistical stu...

Three-dimensional point cloud recognition is a very fundamental work in fields such as autonomous driving and face recognition. However, in real industrial scenarios, input point cloud data are often accompanied by factors such as occlusion, rotation, and noise. These factors make it challenging to apply existing point cloud classification algorith...

Loop closure detection is a crucial component of laser SLAM (Simultaneous Localization and Mapping) systems, used to eliminate long-term accumulated errors. However, describing the discrete point cloud data collected by laser SLAM using simple geometric structures is more challenging than using the rich image information in visual SLAM. This makes...

This paper presents a dense depth estimation approach from light-field (LF) images that is able to compensate for strong rolling shutter (RS) effects. Our method estimates RS compensated views and dense RS compensated disparity maps. We present a two-stage method based on a 2D Gaussians Splatting that allows for a ``render and compare" strategy wit...

Discontinuities exist widely in high rock slopes and threaten their stability at all times. To accurately characterize the information of rock mass discontinuities in high slopes, the layered rock slope on the north side of the Fushun West Open-pit Mine was taken as a typical sample, the high-definition images were collected using unmanned aerial v...

Handing over objects is an essential task in humanrobot collaborative scenarios. Previous studies have predominantly employed rigid grippers to perform the handover, focusing on generating grasps that avoid physical contact with people. In this paper, we present a vision-based open-palm handover solution where a soft robotic hand exploits contact w...

Forests play a crucial role in carbon sequestration and climate change mitigation, offering ecosystem services, biodiversity conservation, and water resource management. As global efforts to reduce greenhouse gas emissions intensify, the demand for accurate spatial information to monitor forest conditions and assess carbon absorption capacity has g...

Bevezetés A szélerózió a Föld számos területén, így hazánkban is komoly problémákat és jelentős károkat okoz (zHeNG, x. 2009). Ez a jelenség elsősorban a homoktalajokat veszélyezteti, de a kötöttebb talajok termőképességének leromlá-sában is fontos szerepet tölt be (Guo et al. 2014). A károk egy része lehet mezőgazdasági (talaj-veszteség, termőképe...

The continuous monitoring of tall industrial buildings is necessary to ensure safe operation. With technological advances in terrestrial laser scanning and other non-contact measurement methods, the methods and techniques for assessing the stability of tall industrial chimneys are evolving. This paper presents a method for determining the non-verti...

In recent years, the challenge of 3D shape analysis within point cloud data has gathered significant attention in computer vision. Addressing the complexities of effective 3D information representation and meaningful feature extraction for classification tasks remains crucial. This paper presents Point-GR, a novel deep learning architecture designe...

This paper introduces Point-GN, a novel non-parametric network for efficient and accurate 3D point cloud classification. Unlike conventional deep learning models that rely on a large number of trainable parameters, Point-GN leverages non-learnable components-specifically, Farthest Point Sampling (FPS), k-Nearest Neighbors (k-NN), and Gaussian Posit...

3D single object tracking is essential in autonomous driving and robotics. Existing methods often struggle with sparse and incomplete point cloud scenarios. To address these limitations, we propose a Multimodal-guided Virtual Cues Projection (MVCP) scheme that generates virtual cues to enrich sparse point clouds. Additionally, we introduce an enhan...

In many applications, there is a need for algorithms that can align partially overlapping point clouds while remaining invariant to corresponding transformations. This research presents a method that achieves these goals by minimizing a binary linear assignment-least squares (BLALS) energy function. First, we reformulate the BLALS problem as the mi...

In the realm of large-scale point cloud registration, designing a compact symbolic representation is crucial for efficiently processing vast amounts of data, ensuring registration robustness against significant viewpoint variations and occlusions. This paper introduces a novel point cloud registration method, i.e., QuadricsReg, which leverages conc...

Point cloud completion is a crucial task in the field of 3D imaging and is becoming a current research hotspot. However, traditional point cloud completion methods often fail to accurately restore the local details of objects due to the lack of detailed descriptions of the missing parts. This paper proposes a performance enhancement scheme for poin...

Metric depth estimation from visual sensors is crucial for robots to perceive, navigate, and interact with their environment. Traditional range imaging setups, such as stereo or structured light cameras, face hassles including calibration, occlusions, and hardware demands, with accuracy limited by the baseline between cameras. Single- and multi-vie...

Indoor point clouds often present significant challenges due to the complexity and variety of structures and high object similarity. The local geometric structure helps the model learn the shape features of objects at the detail level, while the global context provides overall scene semantics and spatial relationship information between objects. To...

Due to the growth of the 3D technology, digital 3D models represented in the form of point clouds have attracted a lot of attention from both industry and academia. In this paper, due to a variety of applications, we study a fundamental problem called the 3D object retrieval, which is to find a set of 3D point clouds stored in a database that are s...

Dynamic point cloud (DPC) represents a realistic 3D scene in motion and has a wide range of applications. Compressing point clouds has become crucial for storing and transmitting such data. Video-based point cloud compression (V-PCC) developed by the Moving Picture Expert Group can achieve remarkable performance in DPC compression. However, it also...

El arbolado urbano es un componente fundamental de la infraestructura verde urbana y desempeña un papel crucial en el bienestar de los ciudadanos al proporcionar servicios ecosistémicos esenciales. Estos servicios incluyen la regulación del microclima, la mejora del confort térmico, la mejora de la calidad del aire, la mitigación del ruido, el aume...

Deformable object manipulation remains a key challenge in developing autonomous robotic systems that can be successfully deployed in real-world scenarios. In this work, we explore the challenges of deformable object manipulation through the task of sculpting clay into 3D shapes. We propose the first coarse-to-fine autonomous sculpting system in whi...

MVImgNet is a large-scale dataset that contains multi-view images of ~220k real-world objects in 238 classes. As a counterpart of ImageNet, it introduces 3D visual signals via multi-view shooting, making a soft bridge between 2D and 3D vision. This paper constructs the MVImgNet2.0 dataset that expands MVImgNet into a total of ~520k objects and 515...

Silvicultural operations such as planting, pruning, and thinning are vital for the forest value chain, requiring efficient monitoring to prevent value loss. While effective, traditional field plots are time-consuming, costly, spatially limited, and rely on assumptions that they adequately represent a wider area. Alternatively, unmanned aerial vehic...

Language-guided robotic grasping is a rapidly advancing field where robots are instructed using human language to grasp specific objects. However, existing methods often depend on dense camera views and struggle to quickly update scenes, limiting their effectiveness in changeable environments. In contrast, we propose SparseGrasp, a novel open-vocab...

Generative models have significantly improved the generation and prediction quality on either camera images or LiDAR point clouds for autonomous driving. However, a real-world autonomous driving system uses multiple kinds of input modality, usually cameras and LiDARs, where they contain complementary information for generation, while existing gener...

Cross-modal localization has drawn increasing attention in recent years, while the visual relocalization in prior LiDAR maps is less studied. Related methods usually suffer from inconsistency between the 2D texture and 3D geometry, neglecting the intensity features in the LiDAR point cloud. In this paper, we propose a cross-modal visual relocalizat...

Currently, many digital elevation models (DEMs) are derived from airborne LiDAR data acquisition flights. The vertical accuracy of both products has typically been evaluated using methods based on randomly sampled control points. However, due to the superficial nature of the DEM, logic suggests that it is more appropriate to use a superficial objec...

When using image data for signage extraction, poor visibility conditions such as insufficient light, rainy days, and low light intensity are encountered, leading to low accuracy and poor boundary segmentation in vision-based detection methods. To address this problem, we propose a cross-modal latent feature fusion network for signage detection, whi...

Stereo 3D reconstruction is pivotal in computer vision, requiring effective fusion of local detail and global semantic features. This paper introduces a novel multi-scale, multi-view cascading network that enhances both accuracy and completeness in 3D reconstruction. In this paper, we addresse the critical challenge of fusing local detail and globa...

In this paper, we present a novel benchmark, GSOT3D, that aims at facilitating development of generic 3D single object tracking (SOT) in the wild. Specifically, GSOT3D offers 620 sequences with 123K frames, and covers a wide selection of 54 object categories. Each sequence is offered with multiple modalities, including the point cloud (PC), RGB ima...

The construction of scene point-cloud maps is an important prerequisite for the registration-based localization of autonomous vehicles. In order to address the issues of the large cumulative error and low utilization efficiency of sensing information in existing SLAM methods, this paper proposes an offline static point-cloud map construction method...

3D cadastral issues have been the subject of scientific research for more than 20 years. However, the initial registration of objects in 3D cadastres remains a significant challenge. The purpose of this study is to verify whether it is possible to register objects for future 3D cadastres based on data from various sources such as laser scanning mea...

Point cloud semantic segmentation (PCSS) shows great potential in generating accurate 3D semantic maps for digital twin railways. Deep learning-based methods have seen substantial advancements, driven by numerous PCSS datasets. Nevertheless, existing datasets tend to neglect railway scenes, with limitations in scale, categories, and scene diversity...

Accurate panoptic segmentation of 3D point clouds in outdoor scenes is critical for the success of applications such as autonomous driving and robot navigation. Existing methods in this area typically assume that the differences between instances are greater than the differences between points belonging to the same instance and use heuristic techni...

UAVs equipped with various sensors offer a promising approach for enhancing orchard management efficiency. Up-close sensing enables precise crop localization and mapping, providing valuable a priori information for informed decision-making. Current research on localization and mapping methods can be broadly classified into SfM, traditional feature-...

The acquisition of both local and global features from irregular point clouds is crucial for 3D object detection (3DOD). Current mainstream 3D detectors neglect significant local features during pooling operations or disregard many global features of the overall scene context. This paper proposes new techniques for simultaneously learning local-glo...

We introduce DexDiffuser, a novel dexterous grasping method that generates, evaluates, and refines grasps on partial object point clouds. DexDiffuser includes the conditional diffusion-based grasp sampler DexSampler and the dexterous grasp evaluator DexEvaluator. DexSampler generates high-quality grasps conditioned on object point clouds by iterati...

Graph Neural Networks (GNNs) are becoming increasingly popular for graph-based learning tasks such as point cloud processing due to their state-of-the-art (SOTA) performance. Nevertheless, the research community has primarily focused on improving model expressiveness, lacking consideration of how to design efficient GNN models for edge scenarios wi...

In recent years, due to the significant advancements in hardware sensors and software technologies, 3D environmental point cloud modeling has gradually been applied in the automation industry, autonomous vehicles, and construction engineering. With the high-precision measurements of 3D LiDAR, its point clouds can clearly reflect the geometric struc...

Point cloud segmentation is an essential task in three-dimensional (3D) vision and intelligence. It is a critical step in understanding 3D scenes with a variety of applications. With the rapid development of 3D scanning devices, point cloud data have become increasingly available to researchers. Recent advances in deep learning are driving advances...

As space technology advances, an increasing number of spacecrafts are being launched into space, making it essential to monitor and maintain satellites to ensure safe and stable operations. Acquiring 3D information of space targets enables the accurate assessment of their shape, size, and surface damage, providing critical support for on-orbit serv...

In this study, we address a gap in existing unsupervised domain adaptation approaches on LiDAR-based 3D object detection, which have predominantly concentrated on adapting between established, high-density autonomous driving datasets. We focus on sparser point clouds, capturing scenarios from different perspectives: not just from vehicles on the ro...

Automotive radar is the commonly used sensor for autonomous driving and active safety. Modern automotive radars provide high spatial information on the host vehicle surroundings, and therefore, automotive radar targets appear as point clouds of radar detections. This work addresses the problem of discriminating between adjacent distributed targets...

In this work, we introduce a novel multimodal descriptor, the image-assisting binary and triangle combined (iBTC) descriptor, which fuses LiDAR (Light Detection and Ranging) and camera measurements for 3D place recognition. The inherent invariance of a triangle to rigid transformations inspires us to design triangle-based descriptors. We first extr...