Find research datasets worth reusing

opencc-by-4.0Apr 2017View details →

CAD 120 affordance dataset

% ============================================================================== % CAD 120 Affordance Dataset % Version 1.0 % ------------------------------------------------------------------------------ % If you use the dataset please cite: % % Johann Sawatzky, Abhilash Srikantha, Juergen Gall. % Weakly Supervised Affordance Detection. % IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17) % % and % % H. S. Koppula and A. Saxena. % Physically grounded spatio-temporal object affordances. % European Conference on Computer Vision (ECCV'14) % % Any bugs or questions, please email sawatzky AT iai DOT uni-bonn DOT de. % ============================================================================== This is the CAD 120 Affordance Segmentation Dataset based on the Cornell Activity Dataset CAD 120 (see http://pr.cs.cornell.edu/humanactivities/data.php). Content frames/*.png: RGB frames selected from Cornell Activity Dataset. To find out the location of the frame in the original videos, see video_info.txt. object_crop_images/*.png image crops taken from the selected frames and resized to 321*321. Each crop is a padded bounding box of an object the human interacts with in the video. Due to the padding, the crops may contain background and other objects. In each selected frame, each bounding box was processed. The bounding boxes are already given in the Cornell Activity Dataset. The 5-digit number gives the frame number, the second number gives the bounding box number within the frame. segmentation_mat/*.mat 321*321*6 segmentation masks for the image crops. Each channel corresponds to an affordance (openabe, cuttable, pourable, containable, supportable, holdable, in this order). All pixels belonging to a particular affordance are labeled 1 in the respective channel, otherwise 0. segmentation_png/*.png 321*321 png images, each containing the binary mask for one of the affordances. lists/*.txt Lists containing the train and test sets for two splits. The actor split ensures that train and test images stem from different videos with different actors while the object split ensures that train and test data have no (central) object classes in common. The train sets are additionally subdivided into 3 subsets A,B and C. For the actor split, the subsets stem from different videos. For the object split, each subset contains every third crop of the train set. crop_coordinate_info.txt Maps image crops to their coordinates in the frames. hpose_info.txt Maps frames to 2d human pose coordinates. Hand annotated by us. object_info.txt Maps image crops to the (central) object it contains. visible_affordance_info.txt Maps image crops to affordances visible in this crop %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%55 The crops contain the following object classes: 1.table 2.kettle 3.plate 4.bottle 5.thermal cup 6.knife 7.medicine box 8.can 9.microwave 10.paper box 11.bowl 12.mug Affordances in our set: 1.openable 2.cuttable 3.pourable 4.containable 5.supportable 6.holdable Note that our object affordance labeling differs from the Cornell Activity Dataset: E.g. the cap of a pizza box is considered to be supportable.

opencc-by-4.0Apr 2018View details →

parametric CAD model of the lumbar spine

7Tepe Parametric Lumbar Spine Model Tweaking parameters of associative CAD models offer interesting pathways for the application of artificial intelligence methods, such as optimization by genetic algorithms and neural networks. Construction of a robust lumbar verteral assembly requires a holistic design approach. The concept of using a layout-sketch as the core of a cad model is becoming more popular due to its top-down design philosophy. However, there remains local issues such as the contact properties at the transverse facet joints, which cannot be taken care of alone by the top-down approach. Inverting the perspective to a bottom-up approach and observing some of the intricate geometrical features of for example the laminae leads to a model that can simply be represented by a relatively scarce number of parameters, yet capturing the physiological aspect of the organ in quite an accurate way. For those who are interested in what our 7Tepe Parametric Lumbar Spine Model version 0.1 currently looks like, just download the source in Parasolid format (x_t extension) and import it to your favorite CAD system. Currently, we have not shared our source CAD file belonging to proprietary software products, but we intend to do so in the near future. Designed by Ogulcan in proprietary solid modeling software.

opencc-by-4.0Dec 2017View details →

The CAD WALK Healthy Controls Dataset

This dataset contains the raw dynamic plantar pressure measurements of 55 healthy Dutch individuals collected at Sint Maartenskliniek, Nijmegen. For each individual, 24 dynamic plantar pressure measurements were collected from both feet. Also collected are walking speeds for each plantar pressure measurements, and demographic information of all individuals measured (age, height, weight, shoe size, sex, handedness, leg dominance). For more information, please see the Readme.pdf file accompanying this dataset.

opencc-by-4.0Mar 2019View details →

MADIA_732678_SCRIBA_CAD 2Dand3D_01

ONLY METADATA Collection of CAD drawings in scale (2D and 3D) and images of: <ul> <li>microfluidic components: microfluidic channels, aggregation chamber, preconcentration chamber;</li> <li>3D printed rigid cartridge equipped with liquid ports i.e. connection with actuating pumps for aggregation chamber prototype (linear setup);</li> <li>elastomeric valves realized through operative protocol for thermoforming of microfluidic devices;</li> <li>master realized through UV lithography performed upon structural SU8 layer;</li> <li>master realized through 3D printer for PDMS replica;</li> <li>prototype of the introduction chamber realized and integrated with the support for the actuators and valves.</li> </ul> Data produced between from February 2017 to December 2018

opencc-by-4.0Dec 2018View details →

The CAD WALK Hallux Valgus Dataset (Pre-Surgery)

This dataset contains the raw dynamic plantar pressure measurements of 50 Dutch individuals with Hallux Valgus collected prior to surgical intervention at Sint Maartenskliniek centres in the Netherlands. For each individual, between 8-15 dynamic plantar pressure measurements were collected from both feet. Also collected are walking speeds for each plantar pressure measurements, and demographic information of all individuals measured (age, height, weight, shoe size, sex, handedness, leg dominance). Additionally, x-ray images were used to measure the hallux valgus angle and intermetatarsal angle for each hallux valgus case. Finally, each participant also completed two foot self-assessment questionnaires: the Foot Function Index (FFI-5pt) and the Manchester-Oxford foot questionnaire. The score from these self-assessments are also provided. For more information, please see the Readme.pdf file accompanying this dataset.

opencc-by-4.0Aug 2022View details →

STEP CAD models of structural aerospace sheet metal parts

This dataset consists of 26 STEP CAD models of aerospace sheet metal parts. The models were used to test a prototype (A) of an automated feature recognition method (B) for aerospace sheet metal part models. When models are used in a work, they can be credited by citing them directly or by citing whichever of the following papers that are relevant. A - A Prototype of an Automated Feature Recognition Algorithm for Aerospace Sheet Metal Parts B - Feature Recognition for Structural Aerospace Sheet Metal Parts

opencc-by-4.0Jul 2021View details →

Parametric 3D CAD model of human foot

The parametric 3D CAD model of human foot was developed from CT data. A CT (Toshiba® Aquilion 4 equipment) scan was performed on a 29 years old male (65 Kg). 345 slices were captured with a slice distance of 1.0 mm (see Figure 2.a). Scans were made for both feet in their neutral posture in which there is the least tension or pressure on tendons, muscles and bones. Medical images were, then, exported into standard .DICOM format (image resolution 512x512 pixels) and processed by using ScanIP® and SolidWorks. Bone structure was composed of 19 bones: tibia, fibula, talus, calcaneus, cuboid, navicular, 3 cuneiforms (bones of the metatarsus), 5 metatarsals (bones of the metatarsus) and 5 components of the phalanges (bones of the toes). Phalange bones (a proximal and a distal phalanx for the great toe; proximal, middle and distal phalanges for the second to fifth toes) were fused together since their relative motion do not affect plantar pressures. More details can be found in the publications below: <ol> <li>Franciosa, P., Gerbino S., From CT Scan to Plantar Pressure Map Distribution of a 3D Anatomic Human Foot, in Proc. of COMSOL Conference’10, Paris (France), November 17-19, 2010.</li> <li>Franciosa, P., Gerbino, S., Lanzotti A., Silvestri L., Improving Comfort of Shoe Sole through Experiments based on CAD-FEM Modeling, Medical Engineering and Physics, doi:10.1016/j.medengphy.2012.03.007, 2013.</li> </ol>

opencc-by-4.0Oct 2021View details →

ThrowBot CAD Dataset

CAD Dataset of ThrowBot. Contains a STEP file and the native Creo Parametric 6.0 dataset in education version. Additional are pdf's and parts lists of the assemblies and the detailed drawings of the components

dryad40/100

AutoMate: a dataset and learning approach for automatic mating of CAD assemblies

Assembly modeling is a core task of computer aided design (CAD), comprising around one third of the work in a CAD workflow. Optimizing this process therefore represents a huge opportunity in the design of a CAD system, but current research of assembly based modeling is not directly applicable to modern CAD systems because it eschews the dominant data structure of modern CAD: parametric boundary representations (BREPs). CAD assembly modeling defines assemblies as a system of pairwise constraints, called mates, between parts, which are defined relative to BREP topology rather than in world coordinates common to existing work. We propose SB-GCN, a representation learning scheme on BREPs that retains the topological structure of parts, and use these learned representations to predict CAD type mates. To train our system, we compiled the first large-scale dataset of BREP CAD assemblies, which we are releasing along with benchmark mate prediction tasks. Finally, we demonstrate the compatibility of our model with an existing commercial CAD system by building a tool that assists users in mate creation by suggesting mate completions, with 72.2% accuracy.

opencc-zeroMar 2023View details →

opencc-by-4.0Aug 2023View details →

Three-dimensional CAD model of the robotic system used for acquiring samples from bacterial swarms

This CAD model shows the robotic sampling system that was used in the scientific article "Simultaneous spatiotemporal transcriptomics and microscopy of Bacillus subtilis swarm development reveal cooperation across generations" by the following authors: Hannah Jeckel*, Kazuki Nosho*, Konstantin Neuhaus, Alasdair D. Hastewell, Dominic J. Skinner, Dibya Saha, Niklas Netter, Nicole Paczia, Jörn Dunkel, Knut Drescher. The symbol "*" indicates an equal contribution.  The CAD model consists of 81 individual files in IPT or IAM format, which need to be loaded together into a AutoDesk Inventor to be viewed. We used AutoDesk Inventor 2021 to create and view this CAD model.

opencc-by-4.0Aug 2023View details →

3D CAD models exemples to run "ArtificialReef_Complexity" Python script (STL files)

Here you will find 3D CAD models in STL format. These are 3D CAD models of fractal pyramid. These STL files can be used as an example to run the Python script "ArtificialReef_Complexity: v.1.3" available on GitHub (<a href="https://github.com/ELI-RIERA/ArtificialReef_Complexity/tree/V1.3">https://github.com/ELI-RIERA/ArtificialReef_Complexity/tree/V1.3</a>)

dryad40/100

AutoMate: a dataset and learning approach for automatic mating of CAD assemblies

Open the record for dataset details and reuse information.

publicMar 2023View details →

opencc-by-4.0Jun 2020View details →

Computer Aided Design (CAD) files for capillaric circuit with 8 retention burst valves

AutoCAD design file and STL file for capillaric circuit with 8 retention burst valves.

opencc-by-4.0Feb 2020View details →

An ultrasound probe array for a high-pressure, high-temperature solid medium deformation apparatus: CAD drawings

CAD drawings of cooled load plate and base plate for integrating pizoelectric needle sensors. Electrical schema of heating system. Dimensional pdf drawings of sigma 1 piston for integration of pizoelectric needle sensors. Matalb code for basic 1D source localization, synchronization of triggered AE data with mechanical data and plotting of AE rate.

dryad36/100

MVCNN++: CAD model shape classification and retrieval using multi-view convolutional neural networks

Deep neural networks have shown promising success towards the classification and retrieval tasks for images and text data. While there have been several implementations of deep networks in the area of computer graphics, these algorithms do not translate easily across different datasets, especially for shapes used in product design and manufacturing domain. Unlike datasets used in the 3D shape classification and retrieval in the computer graphics domain, engineering level description of 3D models do not yield themselves to neat distinct classes. The current study looks at an improved form of the 3D shape deep learning algorithm for classification and retrieval through the use of techniques such as relaxed classification, use of prime angled camera angles for capturing feature detail and transfer learning for reducing the amount of data and processing time needed to train shape recognition algorithms. The proposed algorithm (MVCNN++) builds on top of multi-view convolutional neural network (MVCNN) algorithm, improving its efficacy for manufacturing part classification by enabling use of part metadata, yielding an improvement of almost 6% over the original version. With the explosive growth of 3D product models available in publicly available repositories, search and discovery of relevant models is critical to democratizing access to design models.

opencc-zeroAug 2020View details →

opencc-by-4.0Feb 2023View details →

Part-by-part interface-based search and automatic reassembly of CAD models for database expansion and model reuse

This dataset contains the generated cad assembly from three differents strategy from the article "Part-by-part interface-based search and automatic reassembly of CAD models for database expansion and model reuse". In ReplacePart strategy, each assembly is available in .FCStd format which has the kinematic constraints in the A2+ workbench. A .STEP format of the assembly as well as a PNG screen of the assembly is also available. For the two other strategies, juste STEP files are availables.

openapache2.0Oct 2023View details →

Modular Components for synthesizing Robotic Arms with CLS-CAD

A set of modular components as Autodesk Fusion 360 files suitable for synthesizing robotic arms with CLS-CAD (https://github.com/tudo-seal/CLS-CAD). The files contain the type information required for synthesis as well as the necessary taxonomy. To use these files or reproduce results, please follow the instructions available at https://github.com/tudo-seal/CLS-CAD in the "Getting Started" Section.

opencc-by-4.0Apr 2024View details →

Novel Macrophage Subpopulation Linked to CAD: raw and processed data files

<div> This directory contains all single-cell datasets analyzed in the "Partitioning heritability using single-cell multi-omics identifies a novel macrophage subpopulation conveying increased genetic risk of coronary artery disease". Associated scripts are available at https://github.com/jhjiang2020/multiome_paper.  Jan 2025 updates: include the 10x Cell Ranger ARC output for the scATAC-seq assay. Please note that 10x peaks were not used for downstream analyses. Instead, we trimmed the atac-seq fragments to retain the 9bp Tn5 cut sites at both ends and aggregated into one consensus bed file. We then recalled peaks using `MACS3 --qvalue 1e-5 --nomodel --shift -50 --extsize 100  --broad` (see discussion in https://github.com/stuart-lab/signac/issues/682).    </div>

opencc-by-4.0Mar 2024View details →

Test models and test results to evaluate CAD assembly modules capabilities to generate component interfaces

Set of 3D CAD assembly models in STEP AP 203 format. Assembly test models are devoted to evaluations of interfaces between components. The interfaces can be of type surface, rectilinear contacts, circular contacts, or point contacts. Test results obtained from some commercially available CAD assembly modules are given as a set of tables organized in accordancce with contact categories (surface, rectilinear, circular, point). The content and use of the test models are described into the pdf document: Test models and test results to evaluate CAD assembly modules capabilities to generate component interfaces.