3D Classification

The ModelNet40 dataset contains synthetic object point clouds. As the most widely used benchmark for point cloud analysis, ModelNet40 is popular because of its various categories, clean shapes, well-constructed dataset, etc. The original ModelNet40 consists of 12,311 CAD-generated meshes in 40 categories (such as airplane, car, plant, lamp), of which 9,843 are used for training while the rest 2,468 are reserved for testing. The corresponding point cloud data points are uniformly sampled from the mesh surfaces, and then further preprocessed by moving to the origin and scaling into a unit sphere. Source: Geometric Feedback Network for Point Cloud Classification

Objaverse is a large dataset of objects with 800K+ (and growing) 3D models with descriptive captions, tags, and animations. Objaverse improves upon present day 3D repositories in terms of scale, number of categories, and in the visual diversity of instances within a category. Source: Objaverse: A Universe of Annotated 3D Objects Image Source: https://objaverse.allenai.org/

ShapeNetCore is a subset of the full ShapeNet dataset with single clean 3D models and manually verified category and alignment annotations. It covers 55 common object categories with about 51,300 unique 3D models. The 12 object categories of PASCAL 3D+, a popular computer vision 3D benchmark dataset, are all covered by ShapeNetCore.

A novel dataset and benchmark, which features 1482 RGB-D scans of 478 environments across multiple time steps. Each scene includes several objects whose positions change over time, together with ground truth annotations of object instances and their respective 6DoF mappings among re-scans. Source: RIO: 3D Object Instance Re-Localization in Changing Indoor Environments

ModelNet40-C is a comprehensive dataset to benchmark the corruption robustness of 3D point cloud recognition. We create ModelNet40-C based on the ModelNet40 validation set with 15 corruption types and 5 severity levels for each corruption type including density, noise, and transformation corruption patterns. Our dataset contains 185,000 distinct point clouds that help provide a comprehensive picture of model robustness.

The RAD-ChestCT dataset is a large medical imaging dataset developed by Duke MD/PhD Rachel Draelos during her Computer Science PhD supervised by Lawrence Carin. The full dataset includes 35,747 chest CT scans from 19,661 adult patients. The public Zenodo repository contains an initial release of 3,630 chest CT scans, approximately 10% of the dataset. This dataset is of significant interest to the machine learning and medical imaging research communities.

Attention Deficit Hyperactivity Disorder (ADHD) affects at least 5-10% of school-age children and is associated with substantial lifelong impairment, with annual direct costs exceeding $36 billion/year in the US. Despite a voluminous empirical literature, the scientific community remains without a comprehensive model of the pathophysiology of ADHD. Further, the clinical community remains without objective biological tools capable of informing the diagnosis of ADHD for an individual or guiding clinicians in their decision-making regarding treatment. The ADHD-200 Sample is a grassroots initiative, dedicated to accelerating the scientific community's understanding of the neural basis of ADHD through the implementation of open data-sharing and discovery-based science. Towards this goal, we are pleased to announce the unrestricted public release of 776 resting-state fMRI and anatomical datasets aggregated across 8 independent imaging sites, 491 of which were obtained from typically developing individuals and 285 in children and adolescents with ADHD (ages: 7-21 years old). Accompanying phenotypic information includes: diagnostic status, dimensional ADHD symptom measures, age, sex, intelligence quotient (IQ) and lifetime medication status. Preliminary quality control assessments (usable vs. questionable) based upon visual timeseries inspection are included for all resting state fMRI scans. In accordance with HIPAA guidelines and 1000 Functional Connectomes Project protocols, all datasets are anonymous, with no protected health information included. http://fcon_1000.projects.nitrc.org/indi/adhd200/

Depth vision has been recently used in many locomotion devices with the objective to ease the life of disabled people toward reaching more ecological lifestyle. This is due to the fact that such cameras are cheap, compact and can provide rich information about the environment. Our dataset provides many recordings of point cloud and other types of data during different locomotion modes in urban context. If you used this data, please cite the following papers below: 1-Depth Vision based Terrain Detection Algorithm during Human Locomotion 2-Using Depth Vision for Terrain Detection during Active Locomotion

Existing image/video datasets for cattle behavior recognition are mostly small, lack well-defined labels, or are collected in unrealistic controlled environments. This limits the utility of machine learning (ML) models learned from them. Therefore, we introduce a new dataset, called Cattle Visual Behaviors (CVB), that consists of 502 video clips, each fifteen seconds long, captured in natural lighting conditions, and annotated with eleven visually perceptible behaviors of grazing cattle. By creating and sharing CVB, our aim is to develop improved models capable of recognizing all important cattle behaviors accurately and to assist other researchers and practitioners in developing and evaluating new ML models for cattle behavior classification using video data. The dataset is presented in the form of following three sub-directories. 1. raw_frames: contains 450 frames in each sub folder representing a 15 second video taken at a frame rate of 30 FPS. 2. annotations: contains the json files corresponding to the raw_frames folder. There is one json file for each video, that contains the bounding-box annotations for each cattle in the video and its associated behavior, and 3. CVB_in_AVA_format: contains the CVB data in the AVA dataset format.

Archive of Global Tropical Cyclone Tracks Tracks from 1980 to May 2019.

Intraoral 3D scans analysis is a fundamental aspect of Computer-Aided Dentistry (CAD) systems, playing a crucial role in various dental applications, including teeth segmentation, detection, labeling, and dental landmark identification. Accurate analysis of 3D dental scans is essential for orthodontic and prosthetic treatment planning, as it enables automated processing and reduces the need for manual adjustments by dental professionals. However, developing robust automated tools for these tasks remains a significant challenge due to the limited availability of high-quality public datasets and benchmarks. This article introduces Teeth3DS+, the first comprehensive public benchmark designed to advance the field of intraoral 3D scan analysis. Developed as part of the 3DTeethSeg 2022 and 3DTeethLand 2024 MICCAI challenges, Teeth3DS+ aims to drive research in teeth identification, segmentation, labeling, 3D modeling, and dental landmarks identification. The dataset includes at least 1,800 intraoral scans (containing 23,999 annotated teeth) collected from 900 patients, covering both upper and lower jaws separately. All data have been acquired and validated by experienced orthodontists and dental surgeons with over five years of expertise. Detailed instructions for accessing the dataset are available at https://crns-smartvision.github.io/teeth3ds

BRISC is a high-quality, expert-annotated MRI dataset curated for brain tumor segmentation and classification. It addresses common limitations in existing datasets (e.g., BraTS, Figshare), including class imbalance, narrow tumor focus, and annotation inconsistencies.

This dataset comprises video files (converted into tif format) that depict glomerular activation in mice. The activation was recorded as the response for 35 monomolecular odors. Wide-field 1-photon calcium imaging was recorded at a framerate of 100 Hz, in Thy1-GCaMP6f mice implanted with cranial windows over the olfactory bulb. Mice were head-fixed during imaging, with monomolecular odors presented in a randomized sequence for 2 seconds apiece during each trial. This dataset can be used to develop novel Image segmentation techniques and ML based techniques for vision.

In this dataset an uppertorso humanoid robot with 7-DOF arm explored 100 different objects belonging to 20 different categories using 10 behaviors: Look, Crush, Grasp, Hold, Lift, Drop, Poke, Push, Shake and Tap.

EUEN17037 Daylight and View Standard Test Dataset.

Tables of the blendshapes from a group of the images of the FER2013 dataset, generated using MediaPipe library, based on the ARKit face blendshapes. with classes of the images in a separate column, describing the categories Happy, Unknown, Sad.

This dataset includes 3D point-cloud and 2D imagery from a flash LiDAR...

This dataset supports the research detailed in the pre-print "Virtual Imaging Trials Improved the Transparency and Reliability of AI Systems in COVID-19 Imaging." The study employs both clinical and simulated CT data to evaluate AI models for COVID-19 diagnosis. By leveraging the Virtual Imaging Trials (VIT) framework, the research addresses reproducibility and generalizability issues prevalent in medical imaging AI models. The dataset includes: Clinical CT Data: Drawn from 10 publicly available datasets, comprising over 12,000 volumes. These datasets span diverse populations, imaging protocols, and scanner configurations. Each of the 10 zip files contains pre-processed CT TFRecords (Train/Validation/Test) used in the study. Detailed information about the data sources, pre-processing steps, and the inclusion and exclusion criteria can be found in the manuscript (https://arxiv.org/abs/2308.09730). Simulated CT Data: Generated using computational anatomical phantoms from the XCAT model and imaged with the DukeSim simulation framework. This synthetic dataset allows controlled experiments that isolate the effects of imaging physics and patient-specific factors. Can be available upon request through Center For virtual Imaging Trial Portal at https://cvit.duke.edu/ The accompanying study analyzes the performance of lightweight convolutional neural networks on both real and synthetic data, comparing results across multiple internal and external validation scenarios. Insights into factors such as infection severity, imaging dose, and modality type are explored. For further details, visit our Project Page: https://fitushar.github.io/ReviCOVID.github.io/ The full source code is available on gitHub and GitLab GitHub: https://github.com/fitushar/CVIT_ReviCOVID19 GitLab : https://gitlab.oit.duke.edu/cvit-public/cvit_revicovid19 Citation: When using this dataset, please cite the manuscript () and the original data-source. Tushar et al., "Virtual Imaging Trials Improved the Transparency and Reliability of AI Systems in COVID-19 Imaging", arXiv:2308.09730. Contact: fakrulislam.tushar@duke.edu

In this dataset UR5 robot used 6 tools: metal-scissor, metal-whisk, plastic-knife, plastic-spoon, wooden-chopstick, and wooden-fork to perform 6 behaviors: look, stirring-slow, stirring-fast, stirring-twist, whisk, and poke. The robot explored 15 objects: cane-sugar, chia-seed, chickpea, detergent, empty, glass-bead, kidney-bean, metal-nut-bolt, plastic-bead, salt, split-green-pea, styrofoam-bead, water, wheat, and wooden-button kept cylindrical containers. The robot performed 10 trials on each object using a tool, resulting in 5,400 interactions (6 tools x 6 behaviors x 15 objects x 10 trials). The robot records multiple sensory data (audio, RGB images, depth images, haptic, and touch images) while interacting with the objects.

This dataset is the images of corn seeds considering the top and bottom view independently (two images for one corn seed: top and bottom). There are four classes of the corn seed (Broken-B, Discolored-D, Silkcut-S, and Pure-P) 17802 images are labeled by the experts at the AdTech Corp. and 26K images were unlabeled out of which 9k images were labeled using the Active Learning (BatchBALD) We have created three different dataset: (1). Primary dataset: contains the 17802 images labeled by the experts. Top-view(8901) and Bottom-view(8901). (2). Dataset with fake images: We generated fake images using Conditional GAN (BigGAN) as follows: broken-2937, discolored-5823, pure-2937, silkcut-5823 instances and added them into the train set to balance the data set. (3). Balanced dataset: In this case of adding newly captured images labeled using the Batch Active Learning method, new 9000 labeled images are added into the primary dataset. This new dataset contains 26,802 images split into train and validation set 80: 20, respectively. Contains the 17802 images and the 9K images labeled by the Active Learning (BatchBALD).

InfiniteRep is a synthetic, open-source dataset for fitness and physical therapy (PT) applications. It includes 1k videos of diverse avatars performing multiple repetitions of common exercises. It includes significant variation in the environment, lighting conditions, avatar demographics, and movement trajectories. From cadence to kinematic trajectory, each rep is done slightly differently -- just like real humans. InfiniteRep videos are accompanied by a rich set of pixel-perfect labels and annotations, including frame-specific repetition counts. The dataset features: + 100 videos per exercise, spanning 5 to 10 repetitions each (1,000 videos total) + 7 unique indoor scenes + Realistic environmental occlusion (+ corresponding labels) + Diverse lighting conditions + Varied body shape, skin tones, and clothing + Rich annotations for 2D and 3D supervision ## Exercises The dataset currently includes the following exercises: + Pushups + Alternating Bicep Curls (with dumbbells) + Delt Flys (with dumbbells) + Squats + Bird Dogs + Supermans + Bicycle Crunches + Leg Raises + Front Raises (with dumbbells) + Overhead Press (with dumbbells) ## Annotations The dataset includes the following annotations: + Bounding boxes + Segmentation masks + Keypoints + Joint angles (quaternions) + Percent occlusion + Avatar characteristics + Camera position + and more Want depth labels? They are not included in the dataset but we can send them to you. Email us at info@toinfinity.ai. ## Download Download the dataset: toinfinity.ai/infiniterep Github repo with additional documentation: https://github.com/toinfinityai/InfiniteRep ## Need more data? Infinity AI specializes in generating custom synthetic data. If you need more (or different data), drop us a line at info@toinfinity.ai (we read every email).

This dataset called Indoor Lodz University of Technology Point Cloud Dataset (InLUT3D) is a point cloud set tailored for real object classification and both semantic and instance segmentation tasks. Comprising of 321 scans, some areas in the dataset are covered by multiple scans. All of them are captured using the Leica BLK360 scanner. The points are divided into 18 distinct categories outlined in the label.yaml file along with their respective codes and colors. Among categories you will find: - ceiling, - floor, - wall, - stairs, - column, - chair, - sofa, - table, - storage, - door, - window, - plant, - dish, - wallmounted, - device, - radiator, - lighting, - other. Several challenges are intrinsic to the presented dataset: 1. Extremely non-uniform categories distribution across the dataset. 1. Presence of virtual images, particularly in reflective surfaces, and data exterior to windows and doors. 1. Occurrence of missing data due to scanning shadows (certain areas were inaccessible to the scanner's laser beam). 1. High point density throughout the dataset. Each PTS file contains 8 columns: | Column ID | Description | |---------------|-------------------------------------------------| | 1 | X Cartesian coordinate | | 2 | Y Cartesian coordinate | | 3 | Z Cartesian Coordinate | | 4 | Red colour in RGB space in the range [0, 255] | | 5 | Green colour in RGB space in the range [0, 255] | | 6 | Blue colour in RGB space in the range [0, 255] | | 7 | Category code | | 8 | Instance ID |

Human activity recognition and clinical biomechanics are challenging problems in physical telerehabilitation medicine. However, most publicly available datasets on human body movements cannot be used to study both problems in an out-of-the-lab movement acquisition setting. The objective of the VIDIMU dataset is to pave the way towards affordable patient tracking solutions for remote daily life activities recognition and kinematic analysis. The VIDIMU dataset includes 54 healthy young adults that were recorded on video and 16 of them were simultaneously recorded using custom IMUs. For each subject, 13 activities were registered using a low-resolution video camera and five Inertial Measurement Units (IMUs). Inertial sensors were placed in the lower or the upper limbs of the subject, respectively for activities that involve movement with the lower or the upper body. Video recordings were postprocessed using the state-of-the-art pose estimator BodyTrack (similar to OpenPose, and included in NVIDIA Maxine-AR-SDK) to provide a sequence of 3D joint positions for each movement. Raw IMU recordings were post-processed to compute joint angles by inverse kinematics with OpenSim. For recordings including simultaneous acquisition of video and IMU data types, these signals were used for data file synchronization. Collected data can be further used in applications related to human activity recognition and biomechanics related experiments in simulated home-like settings.