Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
222
datasets available to search
ShareScore release 0.7.1
Dataset results
222 results for “point cloud”
Svetitskhoveli area point cloud
Svetitskhoveli catedral point cloud. Mavic air 2 footage processed with agisoft metashape. Mtskheta, Georgia. Source: Objaverse 1.0 / Sketchfab
3D Point Cloud Data for LiDAR-based Mobile Robot
<p>LiDAR point cloud data serves as an machine vision alternative other than image. Its advantages when compared to image and video includes depth estimation and distance measurement. Low-density LiDAR point cloud data can be used to achieve navigation, obstacle detection and obstacle avoidance for mobile robots. autonomous vehicle and drones. In this metadata, we scanned over 1400 objects and classified it into 6 groups of object namely, human, cars, motorcyclist, signboard, road divider and others.</p>
Digital Twin Technologies Towards Understanding the Interactions between Transportation and other Civil Infrastructure Systems: LIDAR Point Cloud of a Portion of UTEP Campus
<p>This Autodesk ReCap file is a combination of numerous individual LiDAR scans captured using a Leica Terrestial LiDAR system. The scan includes some black and white and some color scans. The area of campus generally focuses on the southwestern portion of campus including the Interdisciplinary Research Building, the Mining Minds roundabout, the Sun Bowl 2 Parking Lot, the University Bookstore, and the Sun Bowl Parking Garage, and roads including University Ave. and Sun Bowl Drive.</p>
Some original, intermediate, and result data in the papar entited "Highway marking extraction and degradation analysis by using MLS point clouds"
<p>Some original, intermediate, and result data in the papar entited "Highway marking extraction and degradation analysis by using MLS point clouds"</p>
Shadowcasting from 3D point clouds
<p>This video shows a time-lapse of shadows modelled by using a 3D point cloud of an urban garden, Villa Revedin Bolasco. </p>
Point Cloud-Mediveal Hermitage of Alarcos, Spain
The medieval hermitage of Nuestra Señora de Alarcos is located 10 kilometers from Ciudad Real (Spain) in the Archaeological Park of Alarcos. Possibly it was built between the 13th and 14th centuries on top of the Alarcos hill, next to the Guadiana river. This place had previously been an important Iberian fortified (oppida) town. During the Middle Ages a castle was built and an attempt was made to build a walled city that was never completed. The hermitage has three naves and two chapels. The naves are separated from each other by ten limestone pillars that support eight pointed arches characteristic of Gothic art. The capitals of the pillars are decorated with leaves and with representations of human heads. Outside there is a large rose window decorated with six-petal flowers that illuminates the interior of the building. Source: Objaverse 1.0 / Sketchfab
Metropolis Maschinenmensch - Point Cloud
Metropolis is a 1927 German expressionist science-fiction drama film directed by Fritz Lang. Written by Thea von Harbou in collaboration with Lang, it stars Gustav Fröhlich, Alfred Abel, Rudolf Klein-Rogge and Brigitte Helm. Erich Pommer produced it in the Babelsberg Studios for Universum Film A.G. The silent film is regarded as a pioneering science-fiction movie, being among the first feature-length movies of that genre. Filming took place over 17 months in 1925–26 at a cost of over five million Reichsmarks. Made in Germany during the Weimar Period, Metropolis is set in a futuristic urban dystopia and follows the attempts of Freder, the wealthy son of the city master, and Maria, a saintly figure to the workers, to overcome the vast gulf separating the classes in their city and bring the workers together with Joh Fredersen, the city master. The film's message is encompassed in the final inter-title: "The Mediator Between the Head and the Hands Must Be the Heart". Source: Wikipedia Source: Objaverse 1.0 / Sketchfab
Court Cell Raw Point Cloud
The raw pointcloud from an AR worldmap scan of one of the felons' cells at York Castle Museum. Scanned using ARKit. Source: Objaverse 1.0 / Sketchfab
Saint Helena Chapel - Photogrammetry Point cloud
Photogrammetric point cloud of the Chapel of Saint Helena Jerusalem. The Chapel of Saint Helena is a 12th-century Armenian church in the lower level of the Church of the Holy Sepulchre in Jerusalem, constructed during the Kingdom of Jerusalem. The Armenians call it the Chapel of St. Gregory the Illuminator, after the saint who brought Christianity to the Armenians. Wikipedia Source: Objaverse 1.0 / Sketchfab
Coastal bluff point clouds derived from SfM near Elwha River mouth, Washington from 2016-04-18 to 2020-05-08
<p>Point Clouds of an approximately 2.0 km alongshore reach of seaward-facing coastal bluff faces on the Strait of Juan de Fuca, Washington State, were derived using structure-from-motion (SfM) photogrammetry from digital photos collected at least quarterly between 2016 and 2022. The point clouds were derived to assess spatial and temporal patterns of erosion on the bluff face and deposition at the base of the bluff. Photos from Miller, et al. (2022) were aligned using a modified USGS published workflow (Over, et al., 2022) with Agisoft Metashape Professional 1.8.5. Photos were aligned within a single chunk in a 4D approach described by Wernette, et al. (2022), and the sparse point cloud was filtered by reconstruction uncertainty (Ru) and projection accuracy (Pa). Dense point clouds were generated independently for each survey date by disabling all cameras except for a single photo date and then generating the dense cloud. This was repeated for each of the 30 photo survey dates, resulting in 30 dense point clouds (one point cloud per photo survey date).</p>
Innovative 3D Cone Point Cloud Fitting via Landweber Iteration
<p>Cone surface fitting is essential in various fields, including computer graphics, computer vision, and robotics. However, factors such as noise, initial parameter selection, and the varying distribution of point clouds can significantly impact fitting accuracy and stability. To address these challenges, we propose a novel optimization method based on Landweber iteration. This method solves an objective function that includes the cone vertex. Initially, Landweber iteration is used to calculate high-precision initial values for the conical surface by leveraging all point cloud data. Subsequently, the RANSAC algorithm filters the point cloud data based on these initial values, eliminating points that do not meet the distance threshold. Finally, an error equation is formulated, and the cone surface parameters are further refined using an optimization algorithm based on Landweber iteration. Simulation experiments validate the feasibility and robustness of our approach, demonstrating superior accuracy and stability in 3D cone surface fitting.</p>
Detection of Structural Components in Point Clouds of Existing RC Bridges
<p><em>The cost and effort </em><em>of</em><em> 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.</em></p>
The dataset used in the article "A point cloud graph neural network for protein-ligand binding site prediction"
Open the record for dataset details and reuse information.
Photorealistic and classified urban point cloud dataset (Helsinki)
<p>The dataset contains a photorealistic and classified urban point cloud from Kalasatama region in Helsinki, Finland. Data was created using both terrestrial laser scanning (Leica RTC360) and UAV-based (DJI P4 Pro+) photogrammetry. 3D reconstruction was completed with RealityCapture and point cloud classification with TerraScan. The dataset is georeferenced in ETRS-TM35FIN (EPSG 3067) coordinate system. Work was done in Aalto University (The Research Institute of Measuring and Modeling for the Built Environment) with support from the City of Helsinki.</p>
Indoor point cloud dataset for BIM related applications
<p>Annotated point cloud of the CRAS labs@FEUP. The point cloud is in ASCII format. Variables: Point X coordinate (m); Point Y coordinate (m); Point Z coordinate (m); Point colour (R); Point colour (G); Point colour (B); Intensity; Label. A total of 21 scans were made, producing 584,701,977 points. The point clouds from the 21 scans were registered with Leica Cyclone Register 360 (3 mm average error). The points were labeled according to 33 classes: 0-unassigned; 1-ceiling; 2-floor; 3-wall; 4-door; 5-window; 6-desk; 7-chair; 8-cabinet; 9-mobile cabinet; 10-shelf; 11-vents; 12-water tank; 13-bin; 14-box; 15-board; 16-computer; 17-screen; 18-printer; 19-vest; 20-switch; 21-paper dispenser; 22-alcohol dispenser; 23-cable; 24-phone; 25-robot; 26-water kettle; 27-stairs; 28-ladder; 29-oil heater; 30-divider; 31-hanger; 32-fan; 33-water dispenser.</p> <p>Additionally, the as-built IFC model of the space is provided in order to test Scan-to-BIM and Scan-vs-BIM algorithms.</p>
Points cloud of 3D CAD models of artificial reefs designed by E.Riera from "Unleashing the Potential of Artificial Reefs Design" (txt files)
<p>Here you will find points cloud of 3D CAD models in txt format.</p> <p>These are 3D CAD models of artificial reefs designed by E.Riera from the paper "Unleashing the Potential of Artificial Reefs Design" (<a href="https://doi.org/10.32942/X2G300">https://doi.org/10.32942/X2G300</a>).</p> <p>These txt files (with others not available on open access) have been used to run a script on R "Computation of fractal dimension" to compute the fractal dimension from the point clouds using the Minkowski-Bouligand method (or "box-counting") using the R statistical framework (version 4.0.3) and “est.boxcount” function of the package “Rdimtools” (You and Shung, 2022). </p>
NPM3D dataset with instance label. Dataset used in paper "A Review of Panoptic Segmentation for Mobile Mapping Point Clouds"
<p>NPM3D is a public benchmark for point cloud semantic segmentation, with 10 classes including: ground, building, pole (road sign and traffic light), bollard, trash can, barrier, pedestrian, car, natural (vegetation) and unclassified. Results are evaluated only w.r.t. 9 classes, disregarding the "unclassified" label. The data has been captured with a mapping-grade mobile laser scanning system in different cities in France. There are 4 regions designated for training, all captured in Paris and Lille; and 3 regions for testing, captured in Dijon and Ajaccio. The standard 10-class version described above has actually been derived from a more fine-grained version of the dataset by keeping only the most frequent labels. The original annotations feature 50 different semantic classes (most of which are very rare), and also individual object instance labels for the training regions. For panoptic segmentation, a new version has been generated that still uses the 10 semantic category labels listed above, but also includes instance labels. The classes ground, building and barrier are considered "stuff" and are not separated into instances. As no instance labels are available for the 3 test regions, our version for panoptic (or pure instance) segmentation only contains 4 different regions from Paris and Lille. Instead of a fixed training/test split all experiments therefore use 4-fold cross-validation.</p>
The mmWave radar point cloud dataset for person identification under various occluded conditions
<p>The dataset is collected by a COTS, Freqency Modulated Continuous Wave radar and an RGB-D camera. The dataset has been collected from 9 recruited individuals, which are instructed to walk behind the obstacle in an inbound/outbound manner, with each subject perfoms 5 consecutive minutes of walking. The RGB dataset is accessible on https://zenodo.org/record/8401329</p>
Virtual Forest Twins based on Marteloscope point cloud data from different forest ecosystem types and its associated teaching workload
<p>The 8th intellectual output (IO-8) titled "Virtual Forest Twins based on Marteloscope point cloud data from different forest ecosystems type and its associated teaching workload" [of the Erasmus+ project "Virtualization of Forest Studies (Virtual Forests)"] was led by Eberswalde University for Sustainable Development (HNEE) in Eberswalde, Germany. The main objectives of IO-8 were two-fold: (1) the development of an analytical pipeline for the virtualization of real forest stands from selected marteloscope sites into 3D virtual twins, and (2) the preparation of open-access, blended teaching and training materials based on the aforementioned analytical pipeline. Specifically, 3D virtual forest twins were created based on point cloud data derived from UAV-mounted and hand-held terrestrial laser scanning technology, followed by a series of software- and hardware-supported analytical steps, and finally rendered for visualization and presentation. The point cloud data collected represents the first significant product of IO8. All further results and products are compiled into open-source resources for teaching, training and research purposes in higher education and forest science. These include technical guidelines, MSc.-level learning materials available for self-directed study on the project Moodle, and a stand-alone online multimedia tutorial narrated in a published ArcGIS StoryMap. </p>
Hadrian bust (point cloud)
This is a dense point cloud obtained using SfM10 (Structure from Motion free software) and MVS10 (Multi-View Stereo free software) available at [3D Software](http://3dstereophoto.blogspot.com/p/software.html). This is my own implementation of Structure from Motion and Multi-View Stereo as applied to stereo photogrammetry. Source: Objaverse 1.0 / Sketchfab
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.