The cost and effort of modelling existing bridges from point clouds currently outweighs the perceived benefits of the resulting model. There is a pressing need to automate this process. Previous research has achieved the automatic generation of surface primitives combined with rule-based classification to create labelled cuboids and cylinders from point clouds. While these methods work well in synthetic datasets or idealized cases, they encounter huge challenges when dealing with real-world bridge point clouds, which are often unevenly distributed and suffer from occlusions. In addition, real bridge geometries are complicated. In this paper, we propose a novel top-down method to tackle these challenges for detecting slab, pier, pier cap, and girder components in reinforced concrete bridges. This method uses a slicing algorithm to separate the deck assembly from pier assemblies. It then detects and segments pier caps using their surface normal, and girders using oriented bounding boxes and density histograms. Finally, our method merges over-segments into individually labelled point clusters. The results of 10 real-world bridge point cloud experiments indicate that our method achieves an average detection precision of 98.8%. This is the first method of its kind to achieve robust detection performance for the four component types in reinforced concrete bridges and to directly produce labelled point clusters. Our work provides a solid foundation for future work in generating rich Industry Foundation Classes models from the labelled point clusters.

The LiDAR Point Cloud Processing Software market, currently valued at $958.7 million in 2025, is experiencing robust growth driven by increasing adoption of LiDAR technology across diverse sectors. The automotive industry's push for autonomous vehicles, coupled with the expanding use of LiDAR in surveying, mapping, and infrastructure management, fuels this expansion. Cloud-based solutions are gaining significant traction, offering scalability and accessibility, while on-premise deployments remain relevant for users prioritizing data security and control. Specific application areas like architecture, land surveying, and forestry demonstrate strong growth, with mining and quarries showing promising potential. Competition among established players like Trimble, Bentley Systems, and Leica Geosystems, along with emerging innovative companies, drives product enhancement and market expansion. The market's growth trajectory is expected to be influenced by factors such as technological advancements (e.g., improved processing algorithms, AI integration), government initiatives promoting digitalization in infrastructure development, and the increasing availability of high-quality LiDAR data. Geographical expansion, particularly in regions with developing infrastructure and rising adoption of digital technologies, presents significant opportunities for market players. While data security concerns and the complexity of processing large point cloud datasets present some challenges, the overall market outlook remains positive, indicating sustained growth throughout the forecast period (2025-2033). A conservative estimate of a Compound Annual Growth Rate (CAGR) of 12% for the next eight years appears reasonable, given the factors mentioned above. This projection accounts for both the high growth potential in emerging applications and the potential for market saturation in established sectors. Regional variations in growth are likely, with North America and Europe maintaining strong positions, while Asia-Pacific is expected to witness substantial growth driven by infrastructure development and increasing LiDAR deployment. The segment breakdown—cloud-based versus on-premise, and by application—indicates a diverse market with varied growth trajectories within each segment. The competitive landscape suggests a dynamic market with opportunities for both large established players and specialized niche providers.

The Point Cloud LiDAR Data Processing Software market is experiencing robust growth, driven by the increasing adoption of LiDAR technology across various sectors. The surge in demand for accurate 3D spatial data in applications like autonomous vehicles, precision agriculture, infrastructure management, and urban planning is fueling market expansion. Technological advancements, including the development of sophisticated algorithms for point cloud processing and the integration of AI and machine learning capabilities, are enhancing the efficiency and accuracy of these software solutions. The market is segmented by software type (e.g., point cloud editing, registration, classification, and modeling software), deployment mode (cloud-based and on-premise), and end-user industry. While competition is intense among established players like Trimble, Bentley Systems, Leica Geosystems, Autodesk, and FARO, the market also presents opportunities for specialized niche players focusing on specific industry applications or innovative processing techniques. The global market is geographically diverse, with North America and Europe currently holding significant market share due to early adoption and technological advancements. However, rapid growth is anticipated in Asia-Pacific and other emerging regions driven by infrastructure development and increasing government investments in digitalization initiatives. The forecast period (2025-2033) projects sustained growth, potentially exceeding a Compound Annual Growth Rate (CAGR) of 15%, reflecting the continued integration of LiDAR data processing into mainstream workflows. Challenges remain, including the high cost of LiDAR data acquisition and processing, the complexity of software solutions, and the need for skilled professionals to operate and interpret the results. Nevertheless, ongoing innovation and the increasing affordability of LiDAR technology are mitigating these challenges, contributing to the market's positive outlook. The competitive landscape is dynamic, with both established players and new entrants continually seeking to improve software features, expand their market reach, and enhance customer support. Strategic partnerships and acquisitions are expected to play a significant role in shaping the market's future trajectory.

These airborne lidar data were gathered by the Instituto Nacional de Estadistica y Geografia of Mexico as part of a regional mapping activity in northwestern Mexico. They span the area that ruptured in the April 2010 M7.2 El Mayor Cucupah earthquake which was laser scanned and for which data are available in OpenTopography's holdings. Alejandro Hinojosa of CICESE is the contact person for these data. This version of the data has been empirically corrected by Craig Glennie and colleagues at the University of Houston. Details for the data corrections as follows:

Rather than trying to correct the whole dataset, we just concentrated on the portion that overlaps with the post-event data. Here is a brief summary of what we did:

The LiDAR Point Cloud Processing Software market is experiencing robust growth, driven by the increasing adoption of LiDAR technology across various sectors. The market, estimated at $2.5 billion in 2025, is projected to witness a Compound Annual Growth Rate (CAGR) of 15% from 2025 to 2033. This significant expansion is fueled by several key factors. The rising demand for accurate 3D mapping and modeling in infrastructure development, autonomous vehicles, precision agriculture, and environmental monitoring is a primary driver. Furthermore, advancements in software capabilities, including improved processing speeds, automation features, and integration with other GIS and BIM platforms, are enhancing efficiency and lowering the barrier to entry for users. The emergence of cloud-based solutions is also contributing to market growth, offering scalability and accessibility to a wider range of users. Competition among established players like Trimble, Bentley Systems, and Leica Geosystems, alongside innovative startups, is fostering innovation and driving down costs, making the technology more accessible to various industries. Despite this positive outlook, certain challenges remain. The high cost of LiDAR data acquisition and processing can still hinder widespread adoption, particularly for smaller businesses. The complexity of the software and the need for specialized training can also present a barrier. However, ongoing technological advancements, along with a growing pool of skilled professionals, are gradually addressing these limitations. The future of the LiDAR Point Cloud Processing Software market appears bright, with continued growth expected across all major segments and regions, driven by the increasing reliance on accurate 3D spatial data for informed decision-making across multiple industries.

Timings and statistical data of point model by our method.

Overview

The Korea University Camera-LIDAR (KUCL) dataset contains images and point clouds acquired in indoor and outdoor environments for various applications (e.g., calibration of rigid-body transformation between camera and LIDAR) in robotics and computer vision communities.

• Indoor dataset: contains 63 pairs of images and point clouds ('indoor.zip'). We collected the indoor dataset in a static indoor environment with walls, floor, and ceiling.
• Outdoor dataset: 61 pairs of images and point clouds ('outdoor.zip'). We collected the outdoor dataset in an outdoor environment including buildings and trees.

Setup

The images were taken using a Point Grey Ladybug5 (specifications) camera and point clouds were acquired with a Velodyne VLP-16 LIDAR (specifications). We rigidly mounted both sensors on the sensor frame during the overall data acquisition. Each pair of images and point clouds was discretely acquired while maintaining the sensor system standing still to reduce time-synchronization problems.

Description

Each dataset (zip file) is organized as follows:

• images/pano: This folder contains spherical panorama images (8000 X 4000) collected using the Ladybug5.
• images/pinhole/cam0~cam5: These folders contain rectified pinhole images (2448 X 2048) collected using six cameras (cam0~cam5) of the Ladybug5.
• images/pinhole/mask: This folder contains the mask (BW image) of each camera of the Ladybug5.
• images/pinhole/cam_param_pinhole.txt: This file contains extrinsic (transformation from the Ladybug5 to each lens) and intrinsic (focal length and center) parameters of each lens of the Ladybug5. For details of Ladybug5 coordinate system, please refer to the technical application note.
• scans: This folder contains point clouds collected using the VLP-16 LIDAR in text files. The first line of each file is the number of points (N), and the remaining lines are points and corresponding reflectivities (N X 4).

We also provide MATLAB functions projecting point cloud onto spherical panorama and pinhole images. Before running the following functions, please unzip the dataset file ('indoor.zip' or 'outdoor.zip') under the main directory.

• run_pano_projection.m: This function projects points onto a spherical panorama image. Lines 19-20 select dataset and index of an image and a point cloud.
• run_pinhole_projection.m: This function projects points onto a pinhole image. Lines 19-21 select dataset, index of an image and a point cloud, and pinhole camera index.

The rigid-body transformation between the Ladybug5 and the VLP-16 in each function is acquired using our edge-based Camera-LIDAR calibration method with Gaussian Mixture Model (GMM). For the details, please refer to our paper (https://doi.org/10.1002/rob.21893).

Citation

Please cite the following paper when using this dataset in your work.

• Jaehyeon Kang and Nakju L. Doh, "Automatic Targetless Camera-LIDAR Calibration by Aligning Edge with Gaussian Mixture Model," Journal of Field Robotics, vol. 37, no. 1, pp.158-179, 2020.
• @ARTICLE {kang-2020-jfr,
  AUTHOR = {Jaehyeon Kang and Nakju Lett Doh},
  TITLE = {Automatic Targetless Camera–{LIDAR} Calibration by Aligning Edge with {Gaussian} Mixture Model},
  JOURNAL = {Journal of Field Robotics},
  YEAR = {2020},
  VOLUME = {37},
  NUMBER = {1},
  PAGES = {158--179},
  }

License information

The KUCL dataset is released under a Creative Commons Attribution 4.0 International License, CC BY 4.0

Contact Information

If you have any issues about the KUCL dataset, please contact us at kangjae07@gmail.com.

While 3D content generation has advanced significantly, existing methods still face challenges with input formats, latent space design, and output representations. This paper introduces a novel 3D generation framework that addresses these challenges, offering scalable, high-quality 3D generation with an interactive Point Cloud-structured Latent space. Our framework employs a Variational Autoencoder (VAE) with multi-view posed RGB-D(epth)-N(ormal) renderings as input, using a unique latent space design that preserves 3D shape information, and incorporates a cascaded latent diffusion model for improved shape-texture disentanglement. The proposed method, GaussianAnything, supports multi-modal conditional 3D generation, allowing for point cloud, caption, and single/multi-view image inputs. Notably, the newly proposed latent space naturally enables geometry-texture disentanglement, thus allowing 3D-aware editing. Experimental results demonstrate the effectiveness of our approach on multiple datasets, outperforming existing methods in both text- and image-conditioned 3D generation.

Parameter setting in our method.

Plant scientists and breeders require high-quality phenotypic data. However, obtaining accurate manual measurements for large plant populations is often infeasible, due to the high labour requirement involved. This is especially the case for more complex plant traits, like the traits defining the plant architecture. Computer-vision methods can help in solving this bottleneck. The current work focusses on methods using 3D point cloud data to obtain phenotypic datasets of traits related to the plant architecture. A first step is the segmentation of the point clouds into plant organs. One of the issues in point-cloud segmentation is that not all plant parts are equally represented in the data and that the segmentation performance is typically lower for minority classes than for majority classes. To address this class-imbalance problem, we used a common practice to divide large point clouds into chunks that were independently segmented and recombined later. In our case, the chunks were created by selecting anchor points and combining those with points in their neighbourhood. As a baseline, the anchor points were selected in a class-independent way, representing the class distribution in the original data. Then, we propose a class-dependent sampling strategy to battle class imbalance. The difference in segmentation performance between the class-independent and the class-dependent training set was analysed first. Additionally, the effect of the number of points selected as the neighbourhood was investigated. Smaller neighbourhoods resulted in a higher level of class balance, but also in a loss of context that was contained in the points around the anchor point. The overall segmentation quality, measured as the mean intersection-over-union (IoU), increased from 0.94 to 0.96 when the class-dependent training set was used. The biggest class improvement was found for the “node,” for which the percentage of correctly segmented points increased by 46.0 percentage points. The results of the second experiment clearly showed that higher levels of class balance did not necessarily lead to better segmentation performance. Instead, the optimal neighbourhood size differed per class. In conclusion, it was demonstrated that our class-dependent sampling strategy led to an improved point-cloud segmentation method for plant phenotyping.

The 3D Point Cloud Annotation Services market has emerged as a pivotal segment within the realms of computer vision, artificial intelligence, and geospatial technologies, addressing the increasing demand for accurate data interpretation across various industries. As enterprises strive to leverage 3D data for enhance

CRT monitor model raw dataContains 7 views of a CRT monitor that were used to create the gold standard modelCRT_model_raw_data.matBike helmet model raw dataBike helmet model raw data containing 9 views of the gold standard model.Bike_helmet_model_raw_data.matSonotrode model raw dataContains 9 views of the sonotrode (conical transducer) gold standard modelSonotrode_model_raw_data.matCRT Bike helmet Sonotrode scenes3 scenes containing the CRT monitor, one scene each containing a bike helmet and a sonotrode (conical transducer)CRT_Bike_helmet_Sonotrode_scenes.mat

This data set concerns a total of 55 cocoa trees grown in cocoa based agroforestry systems from Central region of Cameroon. The data collection campaign was carried out in the district of Bokito (4°34 latitude N and 11°07 longitude E), in the village of Yorro located in a forest-savannah transition zone. The cocoa trees of this data set belong to five different architectural types [Jagoret et al 2017]. The cocoa trees has been sampled in 5 different plots (in 4 different sites) of ages ranging from 5 to 70 year old. The data set consists in Terrestrial Lidar scanning data acquired using a Leica C10 scan station. For each tree, the data set contains the point cloud of the whole tree. There are also the point clouds of the leaves and the point clouds of the wood for 29 of the trees for which the leaf/wood segmentation has been done using the LeWoS software [Di Wang et al 2018]. From all those point clouds, many in silico measurements of the trees can be done to better characterize their architecture, their photosynthetic capacity and the biomass distribution. The scans have been done from the 27th to the 30th of August in 2019.

Semantic3D is a point cloud dataset of scanned outdoor scenes with over 3 billion points. It contains 15 training and 15 test scenes annotated with 8 class labels. This large labelled 3D point cloud data set of natural covers a range of diverse urban scenes: churches, streets, railroad tracks, squares, villages, soccer fields, castles to name just a few. The point clouds provided are scanned statically with state-of-the-art equipment and contain very fine details.

Manual rib inspections in computed tomography (CT) scans are clinically critical but labor-intensive, as 24 ribs are typically elongated and oblique in 3D volumes. Automatic rib segmentation methods can speed up the process through rib measurement and visualization. However, prior arts mostly use in-house labeled datasets that are publicly unavailable and work on dense 3D volumes that are computationally inefficient. To address these issues, we develop a labeled rib segmentation benchmark, named RibSeg, including 490 CT scans (11,719 individual ribs) from a public dataset. For ground truth generation, we used existing morphology-based algorithms and manually refined its results. Then, considering the sparsity of ribs in 3D volumes, we thresholded and sampled sparse voxels from the input and designed a point cloud-based baseline method for rib segmentation. The proposed method achieves state-of-the-art segmentation performance (Dice\(\approx95\%\)) with significant efficiency (\(10\sim40\times\) faster than prior arts). The RibSeg dataset, code, and model in PyTorch are available at https://github.com/M3DV/RibSeg.

Note: This repository provides rib segmentation ("RibFrac31-rib-seg.nii.gz") and centerline ("RibFrac31-rib-cl.nii.gz") annotations for 490 cases in RibFrac dataset. Please download the corresponding CT images ("RibFrac31-image.nii.gz") at https://ribfrac.grand-challenge.org/ (1-click registration is needed via "Join").

The LiDAR Point Cloud Processing Software market has witnessed remarkable growth, driven by the increasing demand for high-precision geospatial data across various industries, including construction, forestry, urban planning, and environmental monitoring. LiDAR, or Light Detection and Ranging, technology enables use

Timings and parameter setting of 3D model.

The market is segmented into the following types and applications: Report Coverage & Deliverables Market Segmentations: Type:

Point Cloud Processing Software GIS Integration Software Others

Application:

Land Surveying and Mapping Urban Planning and Design Environmental Monitoring Water Resources Management Others

Regional Insights:

North America: Largest market due to high adoption in construction and infrastructure projects Europe: Growing demand for environmental monitoring and urban planning Asia-Pacific: Rapid urbanization and increasing investments in infrastructure Rest of the World: Emerging markets with potential for growth

Lidar Data Processing Software Trends Driving Forces:

Increasing adoption of lidar technology in various industries Growing need for accurate and detailed data for decision-making Advancements in cloud computing and artificial intelligence

Challenges and Restraints:

High cost of lidar data collection and processing Limited availability of skilled professionals Data storage and management challenges

Emerging Trends:

Integration of lidar data with other data sources Real-time data processing and visualization Automated workflows and machine learning

Growth Catalysts:

Government initiatives to promote lidar technology Increasing awareness of the benefits of lidar data Collaboration between industry players

Leading Players in the Lidar Data Processing Software

Trimble: Faro Technologies: ESRI: L3Harris Geospatial: Leica Geosystems: Autodesk: PointCloud International: Beijing Yupont Electric Power Technology Co., Ltd.: Blue Marble Geographics: Terrasolid: Beijing Green Valley Technology Co., Ltd: RIEGL Laser Measurement Systems: QCoherent Software: TopoDOT: Merrick & Company: Teledyne Optech: RiAcquisition: RIEGL Software: SLAMTEC: LizarTech:

Significant Developments in Lidar Data Processing Software Sector

Partnerships between software providers and lidar sensor manufacturers Investment in research and development to enhance software capabilities Growing adoption of cloud-based solutions for data storage and processing

HRHD-HK: A Benchmark Dataset of High-Rise and High-Density Urban Scenes for 3D Semantic Segmentation of Photogrammetric Point CloudsThis is the official repository of the HRHD-HK dataset. For technical details, please refer to:Li, M., Wu, Y., Yeh, A. G. O., & Xue, F. (2023). HRHD-HK: A benchmark dataset of high-rise and high-density urban scenes for 3D semantic segmentation of photogrammetric point cloud. Proceedings of 2023 IEEE International Conference on Image Processing Challenges and Workshops, 3714-3718. IEEE. https://doi.org/10.1109/ICIPC59416.2023.10328383Overview of HRHD-HKThis paper presents a benchmark dataset of high-rise high-density urban point clouds, namely High-Rise, High-Density urban scenes of Hong Kong (HRHD-HK) for 3D semantic segmentation.The semantic labels of HRHD-HK include 1) building, 2) vegetation, 3) road, 4) waterbody, 5) facility, 6) terrain, and 7) vehicle.Point clouds of HRHD-HK were collected in HK with two features, i.e., color and coordinates in the HK 1980 Grid system (EPSG:2326).HRHD-HK arranged in 150 tiles, contains approximately 273 million points, covering 9.375 km2.Each tile of point clouds was saved in the "ply" format with seven channels, i.e., x, y, z, red, green, blue, and label.HRHD-HK aims to supplement the existing benchmark datasets with Asian HRHD urban scenes as well as subtropical natural landscapes, such as sea, vegetation, and mountains.For any inquiries, please feel free to contact Maosu at maosulee@connect.hku.hk or Dr. Frank at xuef@hku.hk.Please cite our paper, if you find our work useful for your research.